Abstract

The University of the Philippines School of Library and Information Studies (UPSLIS) conducted a study of Philippine Librarians from November 2018 to October 2019. This endeavor was the first-ever wide-scale study undertaken to collect the occupational profile of Librarians in the Philippines. The survey was designed to be an online questionnaire via Mentimeter and was presented for dissemination during the 2018 Philippine Librarians Association Inc. (PLAI) Congress at Novotel in Quezon City. To further disseminate, the link was posted on the UPSLIS Facebook account and was shared to library association group pages. A total of 685 responses were recorded which is only 7.5% of the almost 9000 registered librarians in the Philippines but can be used in making statistical inference with a 4% margin of error.

About this document

This paper aims to discuss the methds and process used in cleaning, visuzlizing, and processing of the Philippine Librarian Census Dataset (see https://zenodo.org/record/6450452). It details the:

R packages used
Data cleaning methods
Data wrangling methods
Data summarization methods
Data computation methods
Data visualization methods

The researchers hope that this would provide a framework for future LIS research to be more open by sharing theirs datasets and documentation. This would allow research verification and provide an opportunity for other researchers to use different theories and approaches to shared datasets in order to promote the culture of research in the LIS field.

R packages and dataset

# Load needed package
library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.2.1

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.7     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.0
## ✔ readr   2.1.2     ✔ forcats 0.5.1

## Warning: package 'ggplot2' was built under R version 4.2.1

## Warning: package 'tidyr' was built under R version 4.2.1

## Warning: package 'readr' was built under R version 4.2.1

## Warning: package 'dplyr' was built under R version 4.2.1

## Warning: package 'forcats' was built under R version 4.2.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(tm)

## Warning: package 'tm' was built under R version 4.2.1

## Loading required package: NLP

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

library(infer)

## Warning: package 'infer' was built under R version 4.2.1

#Load the raw "librariancensus.csv" dataset
dataset <- read_csv("librariancensus.csv")

## Warning: One or more parsing issues, see `problems()` for details

## Rows: 684 Columns: 67

## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (62): licensed, philippines, gender, working, industry, institution, ten...
## dbl  (5): voter, age, years_service, gross_salary, net_salary
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

#Inspect the loaded dataset
glimpse(dataset)

## Rows: 684
## Columns: 67
## $ voter               <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,…
## $ licensed            <chr> "Yes, I have a valid and up-to-date PRC license fo…
## $ philippines         <chr> NA, "No, I am in the Philippines right now but onl…
## $ gender              <chr> NA, "Prefer not to say", "Woman", "Man", "Man", "M…
## $ age                 <dbl> 59, 100, 40, 46, 32, 46, 48, 44, 25, 24, 34, 39, 3…
## $ working             <chr> NA, "No, I am a retiree.", "Yes, I am currently em…
## $ industry            <chr> NA, "information technology", "academic institutio…
## $ years_service       <dbl> NA, 60, 14, 23, 10, 24, 23, 12, 5, 1, 12, 18, 14, …
## $ institution         <chr> NA, "private (BPO)", "government", "government", "…
## $ tenure              <chr> NA, "self-employed, freelancing or working with mu…
## $ gross_salary        <dbl> NA, 100, 51, 53, 40, 56, 36, 38, 19, 11, 95, 58, 3…
## $ net_salary          <dbl> NA, 100, 30, 38, 30, 42, 29, 26, NA, 10, 95, 36, 2…
## $ benefits1           <chr> NA, "night differential pay", "paid vacation and/o…
## $ benefits2           <chr> NA, NA, "monetary allowances", "monetary allowance…
## $ benefits3           <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "h…
## $ benefits4           <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ benefits5           <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ otherbenefits1      <chr> NA, "123", "Rice allowance\r\nClothing allowance\r…
## $ otherbenefits2      <chr> NA, "123", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ otherbenefits3      <chr> NA, "Hello Philippines and hello world", NA, NA, N…
## $ otherbenefits4      <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ materials1          <chr> NA, "law materials and resources", NA, "archives (…
## $ materials2          <chr> NA, NA, NA, "hardcopy theses and dissertations", N…
## $ materials3          <chr> NA, NA, NA, "hardcopy books / pamphlets / etc", NA…
## $ materials4          <chr> NA, NA, NA, "institutional files and records", NA,…
## $ materials5          <chr> NA, NA, NA, "data sets", NA, "archives (physical)"…
## $ materials6          <chr> NA, NA, NA, "electronic material (digital titles, …
## $ materials7          <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ othermaterials1     <chr> NA, "Huehs", "Grading sheets\r\nExam papers", "Boo…
## $ othermaterials2     <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ othermaterials3     <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ othermaterials4     <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ position            <chr> NA, "supervisory / mid-management level", "supervi…
## $ fiveyears           <chr> NA, "No (planning to shift to other fields or indu…
## $ pursue              <chr> NA, "Hfeudnr", NA, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ education           <chr> NA, "Doctor of Philosophy (Ph.D)", "Master's degre…
## $ enrolled            <chr> NA, "Yes", "Yes", "Yes", "No.", "Yes", "Yes", "No.…
## $ completing          <chr> NA, "Post-graduate Certificate or Diploma (non-LIS…
## $ study_again         <chr> NA, NA, "No", "Yes", "Yes", "Yes", "Yes", "Yes", "…
## $ `5yearsdegree`      <chr> NA, NA, NA, "Short | Certificate | Diploma Program…
## $ cpd1                <chr> NA, NA, "trainings and symposiums facilitated by p…
## $ cpd2                <chr> NA, NA, "government facilitated trainings and symp…
## $ cpd3                <chr> NA, NA, NA, NA, "within the work place (in-house t…
## $ cpd4                <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ cpdsupport1         <chr> NA, NA, "from the government (scholarships, free t…
## $ cpdsupport2         <chr> NA, NA, NA, "from the government (scholarships, fr…
## $ cpdsupport3         <chr> NA, NA, NA, "from the work place (private sponsors…
## $ cpdsatisfaction     <chr> NA, NA, "Yes, the amount of trainings I received w…
## $ cpdbarriers1        <chr> NA, NA, "CPD program sources that I really like", …
## $ cpdbarriers2        <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ cpdbarriers3        <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ topics1             <chr> NA, NA, "Ethics\r\nCommunication skills\r\nCooking…
## $ topics2             <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ topics3             <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ topics4             <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ topics5             <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ location            <chr> NA, NA, "NCR", "NCR", "NCR", "NCR", "NCR", "NCR", …
## $ worktravel          <chr> NA, NA, "Yes", "Yes", "Yes", "Yes", "No", "No", "N…
## $ filipino            <chr> NA, NA, "No", "Yes", "Yes", "Yes", "No", "Yes", "Y…
## $ dialect             <chr> NA, NA, "Ilocano", NA, "Others", NA, "Kapampangan"…
## $ foreignlang         <chr> NA, NA, "None", NA, "Chinese", NA, NA, "English", …
## $ type                <chr> NA, NA, "Slis", "Library school", NA, "Library sch…
## $ roles               <chr> NA, NA, "Cleaner\r\nCook", NA, "Faculty", "Asst pr…
## $ institutionposition <chr> NA, NA, "Head", "Asst prof 5", "Asst. Prof.", "Ass…
## $ primaryjob          <chr> NA, NA, NA, "Education", "Research, Extention, Tea…
## $ affiliation         <chr> NA, NA, "Plai\r\nCodhlis\r\nPatls", "Plai, patls, …
## $ factor              <chr> NA, NA, "Friends", "Similar thrusts", "colleagues"…

#controls how many digits will be printed
options(digits=4) 

#Initialize a pseudorandom number generator to obtain the same output during simulation
set.seed(12)

Data Cleaning, Wrangling, and Visualization

Question: Are you currently a licensed librarian (R.A. 9246) ?

Yes, I have a valid and up-to-date PRC license for librarians
No, I have not renewed my license
No, I have never taken any licensure examination for librarians and/or never applied for a PRC license for librarians

# Change the factor type
dataset$licensed <- as.factor(dataset$licensed)
# Recode responses
dataset$licensed <- fct_recode(dataset$licensed, "Licensed librarian" = "Yes, I have a valid and up-to-date PRC license for librarians", "Librarian with unrenewed license" = "No, I have not renewed my license",  "Non-licensed librarian" = "No, I have never taken any licensure examination for librarians and/or never applied for a PRC license for librarians")
# Rearrange the responses
dataset$licensed <- factor(dataset$licensed, levels = c("Licensed librarian", "Librarian with unrenewed license", "Non-licensed librarian"))
# Graph the data
dataset %>%
filter(!is.na(licensed)) %>%
ggplot(aes(x = licensed, fill = licensed)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: PRC License", "n=659") + guides(fill = "none") + scale_fill_viridis_d()

Question: Are you currently residing in the Philippines?

Yes, I am currently residing and staying in the Philippines
No, I am in the Philippines right now but only for vacation
No, I am currently residing outside the Philippines

# Change the factor type
dataset$philippines <- as.factor(dataset$philippines)
# Recode responses
dataset$philippines <- fct_recode(dataset$philippines, "Residing in the Philippines" = "Yes, I am currently residing and staying in the Philippines", "Residing outside of the Philippines" = "No, I am in the Philippines right now but only for vacation", "Residing outside of the Philippines" = "No, I am currently residing outside the Philippines")
# Rearrange the responses
dataset$philippines <- factor(dataset$philippines, levels = c("Residing in the Philippines", "Residing outside of the Philippines"))
# Graph the data
dataset %>%
filter(!is.na(philippines)) %>%
ggplot(aes(x = philippines, fill = philippines)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Residency", "n=657") + guides(fill = "none") + scale_fill_viridis_d()

Question: Kindly indicate which gender you identify the most

Man
Woman
LGBTQ+
Prefer not to say

# Change the factor type
dataset$gender <- as.factor(dataset$gender)
# Recode responses
dataset$gender <- fct_recode(dataset$gender, "With diverse SOGIE" = "LGBTQ+", "Male" = "Man", "Female" = "Woman")
# Rearrange the responses
dataset$gender <- factor(dataset$gender, levels = c("Female", "Male", "With diverse SOGIE", "Prefer not to say"))
# Graph the data
dataset %>%
filter(!is.na(gender)) %>%
ggplot(aes(x = gender, fill = gender)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Gender", "n=659") + guides(fill = "none") + scale_fill_viridis_d()

Question: Kindly indicate your age

# Inspect the responses
summary(dataset$age)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    18.0    25.0    31.0    33.8    40.0   100.0      24

# Create a new column: age_group
age_group <- cut(dataset$age, c(20,30,40,50,60,70,80), right = FALSE)
# Attach age_group to dataset
dataset <- cbind(dataset, age_group)
# Recode responses
dataset$age_group <- fct_recode(dataset$age_group, "21-30" = '[20,30)', "31-40" = '[30,40)', "41-50" = '[40,50)', "51-60" = '[50,60)', "Greater than 60" = '[60,70)', "Greater than 60" = '[70,80)' )
# Graph the data: bar graph
dataset %>%
filter(!is.na(age_group)) %>%
ggplot(aes(x = age_group, fill = age_group)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Age", "n=655") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: histogram
dataset %>%
filter(!is.na(age)) %>%
filter(age > 20) %>%
filter(age < 90) %>%
ggplot(aes(x = age, fill = age)) + geom_histogram(bins = 8) + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Age", "n=645") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: boxplot + violin plot + dot plot
dataset %>%
filter(!is.na(age)) %>%
filter(age > 20) %>%
filter(age < 90) %>%
ggplot(aes(x = 1, y = age)) + geom_violin(adjust=.7) + geom_boxplot(width = .1, fill = "black") + geom_dotplot(aes(y = age), binaxis = "y", binwidth = .5, stackdir = "center", alpha = .5) + stat_summary(fun = mean, geom = "point", fill = "white", shape = 21, size = 2.5) + coord_flip() + theme(axis.text.y = element_blank()) + xlab("Distribution") + ylab("Age") + ggtitle("Distribution of Responses: Age(Boxplot)", "n=646")

Question: Are you currently employed and/or working?

Yes, I am currently employed by an institution, agency, individual or similar.
Yes, I am currently self-employed and/or doing freelance and consultancy work.
No, I am currently not working for reasons other than retirement.
No, I am a retiree.

# Change the factor type
dataset$working <- as.factor(dataset$working)
# Recode responses
dataset$working <- fct_recode(dataset$working, "Retired" = 'No, I am a retiree.', "Not working" = 'No, I am currently not working for reasons other than retirement.', "Employed" = 'Yes, I am currently employed by an institution, agency, individual or similar.', "Self-employed" = 'Yes, I am currently self-employed and/or doing freelance and consultancy work.')
# Rearrange the responses
dataset$working <- factor(dataset$working, levels = c('Employed', 'Not working', 'Self-employed', 'Retired'))
# Graph the data
dataset %>%
filter(!is.na(working)) %>%
ggplot(aes(x = working, fill = working)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Currently Working", "n=657") + guides(fill = "none") + scale_fill_viridis_d()

Question: Kindly indicate the setting, field or industry you are primarily working in

library
archives and/or records management
academic institution (non-librarian position)
information technology, computer science, software / database engineering and other similar line of work
museum and heritage work
social services

# Change the factor type
dataset$industry <- as.factor(dataset$industry)
# Recode responses
dataset$industry <- fct_recode(dataset$industry, "Academe" = 'academic institution (non-librarian position)',"A&RM" = 'archives and/or records management', "ICT" = 'information technology', "Library" = 'library', "Heritage Work" ='museum and heritage work', "Social Service" = 'social services')
# Rearrange the responses
dataset$industry <- factor(dataset$industry, levels = c('Library', 'Academe', 'A&RM', 'ICT', 'Social Service', 'Heritage Work'))
# Graph the data
dataset %>%
filter(!is.na(industry)) %>%
ggplot(aes(x = industry, fill = industry)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Industry", "n=651") + guides(fill = "none") + scale_fill_viridis_d()

Question: How long have you been working as a professional after passing the licensure exam for librarians (cumulative years)

# Inspect the responses
summary(dataset$years_service)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    1.00    3.00    7.00    9.21   14.00   60.00      34

# Create a new column: years_service_group
years_service_group <- cut(dataset$years_service, c(0,5,10,15,20,25,30,35,40), right = FALSE)
# Attach years_service_group to dataset
dataset <- cbind(dataset, years_service_group)
# Recode responses
dataset$years_service_group <- fct_recode(dataset$years_service_group, "0-4" = '[0,5)',"5-9" = '[5,10)', "10-14" = '[10,15)', "15-19" = '[15,20)', "20-24" = '[20,25)', "25-29" = '[25,30)',"30 or more" = '[30,35)', "30 or more" = '[35,40)')
# Graph the data: bar graph
dataset %>%
filter(!is.na(years_service_group)) %>%
ggplot(aes(x = years_service_group, fill = years_service_group)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Years of Service", "n=648") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: histogram
dataset %>%
filter(!is.na(years_service)) %>%
filter(years_service < 40) %>%
ggplot(aes(x = years_service, , fill = years_service)) + geom_histogram(bins = 8) + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Years of Service", "n=648") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: boxplot + violin plot + dot plot
dataset %>%
filter(!is.na(years_service)) %>%
filter(years_service < 40) %>%
ggplot(aes(x = 1, y = years_service)) + geom_violin(adjust=.7) + geom_boxplot(width = .1, fill = "black") + geom_dotplot(aes(y = years_service), binaxis = "y", binwidth = .3, stackdir = "center", alpha = .5) + stat_summary(fun = mean, geom = "point", fill = "white", shape = 21, size = 2.5) + coord_flip() + theme(axis.text.y = element_blank()) + xlab("Distribution") + ylab("Years of Service") + ggtitle("Distribution of Responses: Years of Service(Boxplot)", "n=648")

Question: Kindly indicate the type of institution (in terms of ownership) you are primarily working in

government
private (in-house)
private (BPO)
non-profit

# Change the factor type
dataset$institution <- as.factor(dataset$institution)
# Recode responses
dataset$institution <- fct_recode(dataset$institution, "Government" = 'government', "NGO" = 'non-profit', "Private" = 'private (BPO)', "Private" = 'private (in-house)')
# Rearrange the responses
dataset$institution <- factor(dataset$institution, levels = c('Private', 'Government', 'NGO'))
# Graph the data
dataset %>%
filter(!is.na(institution)) %>%
ggplot(aes(x = institution, fill = institution)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Institution", "n=643") + guides(fill = "none") + scale_fill_viridis_d()

Question: Kindly indicate your current tenure status

permanent
contractual
voluntary work
job order (J.O.)
self-employed, freelancing or working with multiple institutions

# Change the factor type
dataset$tenure <- as.factor(dataset$tenure)
# Recode responses
dataset$tenure <- fct_recode(dataset$tenure, "Contractual" = 'contractual', "Job order" = 'job order (J.O.)', "Permanent" = 'permanent', "Self-employed" = 'self-employed, freelancing or working with multiple institutions', "Volunteer" = 'voluntary work')
# Rearrange the responses
dataset$tenure <- factor(dataset$tenure, levels = c('Permanent', 'Contractual', 'Job order', 'Self-employed', 'Volunteer'))
# Graph the data
dataset %>%
filter(!is.na(tenure)) %>%
ggplot(aes(x = tenure, fill = tenure)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Tenure", "n=639") + guides(fill = "none") + scale_fill_viridis_d()

Question: Kindly indicate your current monthly gross salary or income range (before deductions)

# Inspect the responses
summary(dataset$gross_salary)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##     1.0    17.0    22.0    26.9    30.0   100.0     122

# Create a new column: gross_salary_group
gross_salary_group <- cut(dataset$gross_salary, c(10,20,30,40,50,60,70,80,90,100), right = TRUE)
# Attach gross_salary_group to dataset
dataset <- cbind(dataset, gross_salary_group)
# Recode responses
dataset$gross_salary_group <- fct_recode(dataset$gross_salary_group, "11-20" = '(10,20]', "21-30" = '(20,30]', "31-40" = '(30,40]', "41-50" = '(40,50]', "Greater than 50k" = '(50,60]', "Greater than 50k" = '(60,70]', "Greater than 50k" = '(70,80]', "Greater than 50k" = '(80,90]', "Greater than 50k" = '(90,100]')
# Graph the data: bar graph
dataset %>% 
filter(!is.na(gross_salary_group)) %>%
ggplot(aes(x = gross_salary_group, fill = gross_salary_group)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Gross Salary", "n=562") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: histogram
dataset %>%
filter(!is.na(gross_salary)) %>%
filter(gross_salary > 10) %>%
ggplot(aes(x = gross_salary, fill = gross_salary)) + geom_histogram(bins = 8) + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Gross Salary", "n=508") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: boxplot + violin plot + dot plot
dataset %>%
filter(!is.na(gross_salary)) %>%
filter(gross_salary > 10) %>%
ggplot(aes(x = 1, y = gross_salary)) + geom_violin(adjust=2) + geom_boxplot(width = .1, fill = "black") + geom_dotplot(aes(y = gross_salary), binaxis = "y", binwidth = .9, stackdir = "center", alpha = .5) + stat_summary(fun = mean, geom = "point", fill = "white", shape = 21, size = 2.5) + coord_flip() + theme(axis.text.y = element_blank()) + xlab("Distribution") + ylab("Gross Salary") + ggtitle("Distribution of Responses: Gross Salary(Boxplot)", "n=508")

Kindly indicate your current monthly net salary or income range (after deductions)

# Inspect the responses
summary(dataset$net_salary)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##     1.0    12.0    18.0    21.1    24.0   100.0     134

# Create a new column: gross_salary_group
net_salary_group <- cut(dataset$net_salary, c(10,20,30,40,50,60,70,80,90,100), right = TRUE)
# Attach net_salary_group to dataset
dataset <- cbind(dataset, net_salary_group)
# Recode responses
dataset$net_salary_group <- fct_recode(dataset$net_salary_group, "11-20" = '(10,20]', "21-30" = '(20,30]', "31-40" = '(30,40]', "41-50" = '(40,50]', "Greater than 50k" = '(50,60]', "Greater than 50k" = '(60,70]', "Greater than 50k" = '(70,80]', "Greater than 50k" = '(80,90]', "Greater than 50k" = '(90,100]')
# Graph the data: bar graph
dataset %>%
filter(!is.na(net_salary_group)) %>%
ggplot(aes(x = net_salary_group, fill = net_salary_group)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Net Salary", "n=550") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: bar graph
dataset %>%
filter(!is.na(net_salary)) %>%
filter(net_salary > 10) %>%
ggplot(aes(x = net_salary, fill = net_salary)) + geom_histogram(bins = 11) + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Net Salary", "n=446") + guides(fill = "none") + scale_fill_viridis_d()

# Graph the data: boxplot + violin plot + dot plot
dataset %>%
filter(!is.na(net_salary)) %>%
filter(net_salary > 10) %>%
ggplot(aes(x = 1, y = net_salary)) + geom_violin(adjust=2) + geom_boxplot(width = .1, fill = "black") + geom_dotplot(aes(y = net_salary), binaxis = "y", binwidth = .9, stackdir = "center", alpha = .5) + stat_summary(fun = mean, geom = "point", fill = "white", shape = 21, size = 2.5) + coord_flip() + theme(axis.text.y = element_blank()) + xlab("Distribution") + ylab("Net Salary") + ggtitle("Distribution of Responses: Net Salary(Boxplot)", "n=446")

Question: Kindly indicate additional benefits, if any (please check all that apply)

free shuttle service
night differential pay
paid vacation and/or sick leaves
health card and/or insurance other than PhilHealth
monetary allowances
NONE / Not Applicable

# Combine columns: benefits1, benefits2, benefits3, benefits4, benefits5
dataset$benefits <- paste(dataset$benefits1, dataset$benefits2, dataset$benefits3, dataset$benefits4, dataset$benefits5)
#Create new columns: shuttle, night_differential, paid_leaves, hmo, allowances, no_benefits
dataset <- transform(dataset, shuttle = grepl("shuttle", benefits), night_differential = grepl("night", benefits), paid_leaves = grepl("leaves", benefits), hmo = grepl("insurance", benefits), allowances = grepl("allowances", benefits), no_benefits = grepl("NONE", benefits))
# Summarize by counting the TRUE values per benefits
dataset %>%
summarise("Shuttle service" = sum(shuttle == TRUE), "Night differential" = sum(night_differential == TRUE), "Paid leaves" = sum(paid_leaves == TRUE), "HMO" = sum(hmo == TRUE), "Allowances" = sum(allowances == TRUE), "No benefits" = sum(no_benefits == TRUE)) %>%
gather() %>%
ggplot(aes(x = key, y = value, fill = key)) + geom_col(position = "dodge") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Benefits", "n=630") + guides(fill = "none") + scale_fill_viridis_d() + theme(axis.text.x = element_text(angle = 90)) +
geom_text(x = 1, y = 254, label = "244", colour = "black", size = 4) + 
geom_text(x = 2, y = 269, label = "259", family = "serif", colour = "black", size = 4) +
geom_text(x = 3, y = 38, label = "28", family = "serif", colour = "black", size = 4) +
geom_text(x = 4, y = 124, label = "114", family = "serif", colour = "black", size = 4) +
geom_text(x = 5, y = 463, label = "453", family = "serif", colour = "black", size = 4) +
geom_text(x = 6, y = 46, label = "36", family = "serif", colour = "black", size = 4)

# Change the factor type
dataset$benefits1 <- as.factor(dataset$benefits1)
# Recode responses
dataset$benefits6 <- fct_recode(dataset$benefits1, "With Benefits" = 'free shuttle service', "With Benefits" = 'health card and/or insurance other than PhilHealth', "With Benefits" = 'monetary allowances', "With Benefits" = 'night differential pay', "Without Benefits" = 'NONE / Not Applicable', "With Benefits" = 'paid vacation and/or sick leaves')
# Rearrange the responses
dataset$benefits6 <- factor(dataset$benefits6, levels = c('With Benefits', 'Without Benefits'))
# Graph the data
dataset %>%
filter(!is.na(benefits6)) %>%
ggplot(aes(x = benefits6, fill = benefits6)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Benefits", "n=630") + guides(fill = "none") + scale_fill_viridis_d()

Question: Other benefits not mentioned in the previous page

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en")))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text dataset
benefits.text <- paste(dataset$otherbenefits1, dataset$otherbenefits2, dataset$otherbenefits3, dataset$otherbenefits4)
# Create a text corpus
benefit.corpus <- benefits.text %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
benefit.corpus <- clean_corpus(benefit.corpus)
# Create a dendogram
benefit.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.98) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Question: What kind of materials are you currently working with? Kindly check all that applies.

hardcopy theses and dissertations
hardcopy books / pamphlets / etc
electronic material (digital titles, digital archives, etc)
law materials and resources
archives (physical)
data sets
institutional files and records
NA

# Combine columns: materials1, materials2, materials3, materials4, materials5, materials6, materials7
dataset$materials <- paste(dataset$materials1, dataset$materials2, dataset$materials3, dataset$materials4, dataset$materials5, dataset$materials6, dataset$materials7)
# Create new columns: theses, books, electronic_materials, law_materials, datasets, institutional_files
dataset <- transform(dataset, theses = grepl("theses", materials), books = grepl("books", materials), electronic_materials = grepl("electronic", materials), law_materials = grepl("law", materials), datasets = grepl("data sets", materials), archives = grepl("archives", materials), institutional_files = grepl("institutional files and records", materials))
# Summarize by counting the TRUE values per materials
dataset %>%
summarise("These" = sum(theses == TRUE), "Books" = sum(books == TRUE), "Electronic Materials" = sum( electronic_materials == TRUE), "Law Materials" = sum(law_materials == TRUE), "Datasets" = sum(datasets == TRUE), "Archives" = sum(archives == TRUE), "Institutional Materials" = sum(institutional_files == TRUE)) %>%
gather() %>%
ggplot(aes(x = key, y= value, fill = key)) + geom_col(position = "dodge") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Materials", "n=542") + guides(fill = "none") + scale_fill_viridis_d() + theme(axis.text.x = element_text(angle = 90)) +
geom_text(x = 1, y = 298, label = "288", colour = "black", size = 4) + 
geom_text(x = 2, y = 459, label = "449", colour = "black", size = 4) + 
geom_text(x = 3, y = 66, label = "56", colour = "black", size = 4) +
geom_text(x = 4, y = 273, label = "263", colour = "black", size = 4) +
geom_text(x = 5, y = 233, label = "223", colour = "black", size = 4) +
geom_text(x = 6, y = 75, label = "65", colour = "black", size = 4) +
geom_text(x = 7, y = 304, label = "294", colour = "black", size = 4)

Question: Kindly indicate your current work position

entry level / junior staff
regular / senior staff (non-supervisory)
supervisory / mid-management level
upper management level / top tier executive
consultant / freelancer / self-employed

# Change the factor type
dataset$position <- as.factor(dataset$position)
# Recode responses
dataset$position <- fct_recode(dataset$position, "Self-employed" =  'consultant / freelancer / self-employed', "Junior level" =  'entry level / junior staff', "Senior level" =  'regular / senior staff (non-supervisory)', "Supervisory" =  'supervisory / mid-management level', "Management" =  'upper management level / top tier executive')
# Graph the data
dataset %>%
filter(!is.na(position)) %>%
ggplot(aes(x = position, fill = position)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Position", "n=578") + guides(fill = "none") + scale_fill_viridis_d()

Question: Within the next five (5) years, do you see your self working in the same industry?

Yes
No (planning to shift to other fields or industry)
Maybe / Undecided

# Change the factor type
dataset$fiveyears <- as.factor(dataset$fiveyears)
# Recode responses
dataset$fiveyears <- fct_recode(dataset$fiveyears, "Undecided" = 'Maybe / Undecided', "No" = 'No (planning to shift to other fields or industry)', "Yes" = 'Yes')
# Rearrange the responses
dataset$fiveyears <- factor(dataset$fiveyears, levels = c('Yes', 'Undecided', 'No'))
# Graph the data
dataset %>%
filter(!is.na(fiveyears)) %>%
ggplot(aes(x = fiveyears, fill = fiveyears)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: 5-year plan", "n=585") + guides(fill = "none") + scale_fill_viridis_d()

Question: If your answer was NO or MAYBE in the previous page, indicate the field you wish to pursue

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en"), "none", "yes", "like", "library", "librarianship", "want", "work"))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text corpus
fiveyearplan.corpus <- dataset$pursue %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
fiveyearplan.corpus <- clean_corpus(fiveyearplan.corpus)
# Create a dendogram
fiveyearplan.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.995) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Question: Kindly indicate your highest educational attainment

High School
Bachelor’s degree (BLIS)
Bachelor’s degree (non-BLIS)
Master’s degree (MLIS)
Master’s degree (non-MLIS)
Juris Doctor / Bachelor of Laws
Doctor of Philosophy (Ph.D)

# Change the factor type
dataset$education <- as.factor(dataset$education)
# Recode responses
levels(dataset$education)[1] <- "BLIS"
levels(dataset$education)[2] <- "Bachelor degree"
levels(dataset$education)[3] <- "Ph.D"
levels(dataset$education)[4] <- "Juris Doctor"
levels(dataset$education)[5] <- "MLIS"
levels(dataset$education)[6] <- "Master degree"
# Rearrange the responses
dataset$education <- fct_relevel(dataset$education, 'BLIS', 'Bachelor degree', 'MLIS', 'Master degree', 'Ph.D', 'Juris Doctor')
# Graph the data
dataset %>%
filter(!is.na(education)) %>%
ggplot(aes(x = education, fill = education)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Highest Educational Attainment", "n=580") + guides(fill = "none") + scale_fill_viridis_d()

Question: Are you currently enrolled in formal studies? (Short Courses, Certificate Program, Diploma Program, Master Program, PhD)

# Change the factor type
dataset$enrolled <- as.factor(dataset$enrolled)
# Recode responses
levels(dataset$enrolled)[1] <- "No"
# Rearrange the responses
dataset$enrolled <- fct_relevel(dataset$enrolled, 'Yes', 'No')
# Graph the data
dataset %>%
filter(!is.na(enrolled)) %>%
ggplot(aes(x = enrolled, fill = enrolled)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Currently Enroled", "n=579") + guides(fill = "none") + scale_fill_viridis_d()

Question: If your answer was YES, indicate the degree you are currently completing

Short | Certificate | Diploma Program
Bachelor’s degree (BLIS)
Master’s degree (MLIS)
Master’s degree (non-MLIS)
Juris Doctor / Bachelor of Laws
Doctor of Philosophy (Ph.D)
Post-graduate Certificate or Diploma (LIS)
Post-graduate Certificate or Diploma (non-LIS)

# Change the factor type
dataset$completing <- as.factor(dataset$completing)
# Recode responses
levels(dataset$completing)[1] <- "BLIS"
levels(dataset$completing)[2] <- "Ph.D."
levels(dataset$completing)[3] <- "Juris Doctor"
levels(dataset$completing)[4] <- "MLIS"
levels(dataset$completing)[5] <- "Masters non-MLIS"
levels(dataset$completing)[6] <- "Post Graduate LIS"
levels(dataset$completing)[7] <- "Post Graduate non-LIS"
levels(dataset$completing)[8] <- "Short Course"
# Rearrange the responses
dataset$completing <- factor(dataset$completing, levels = c("Short Course", "BLIS", "MLIS", "Masters non-MLIS", "Ph.D.", "Juris Doctor", "Post Graduate LIS", "Post Graduate non-LIS"))
# Graph the data
dataset %>%
filter(!is.na(completing)) %>%
ggplot(aes(x = completing, fill = completing)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Current Enrollment", "n=286") + guides(fill = "none") + theme(axis.text.x = element_text(angle = 90)) + scale_fill_viridis_d()

Question: Are you planning to study again in a formal university setting within the next five (5) years?

Yes
No
Maybe

# Change the factor type
dataset$study_again <- as.factor(dataset$study_again)
# Rearrange the responses
dataset$study_again <- factor(dataset$study_again, levels = c("Yes", "Maybe", "No"))
# Graph the data
dataset %>%
filter(!is.na(study_again)) %>%
ggplot(aes(x = study_again, fill = study_again)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Current Enrollment", "n=573") + guides(fill = "none") + scale_fill_viridis_d()

Question: If your answer was YES, kindly provide the degree you wish to study within the next five (5) years

Short | Certificate | Diploma Program
Bachelor’s degree (BLIS)
Master’s degree (MLIS)
Master’s degree (non-MLIS)
Juris Doctor / Bachelor of Laws
Doctor of Philosophy (Ph.D)
Post-graduate Certificate or Diploma (LIS)
Post-graduate Certificate or Diploma (non-LIS)

# Change the column name of '5yearsdegree'
colnames(dataset)[40] <- "after5years"
# Change the factor type
dataset$after5years <- as.factor(dataset$after5years)
# Recode responses
levels(dataset$after5years)[1] <- "Ph.D."
levels(dataset$after5years)[2] <- "Juris Doctor"
levels(dataset$after5years)[3] <- "MLIS"
levels(dataset$after5years)[4] <- "Master non-MLIS" 
levels(dataset$after5years)[5] <- "Post Graduate LIS"
levels(dataset$after5years)[6] <- "Post Graduate non-LIS"
levels(dataset$after5years)[7] <- "Short Course"
# Rearrange the responses
dataset$after5years <- factor(dataset$after5years, levels = c("Short Course", "MLIS", "Master non-MLIS", "Ph.D.", "Juris Doctor", "Post Graduate LIS", "Post Graduate non-LIS"))
# Graph the data
dataset %>%
filter(!is.na(after5years)) %>%
ggplot(aes(x = after5years, fill = after5years)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Plan within 5 years", "n=430") + guides(fill = "none") + theme(axis.text.x = element_text(angle = 90)) + scale_fill_viridis_d()

Question: Where do you usually acquire your CPD trainings in LIS? Kindly check all that applies

within the work place (in-house trainings)
government facilitated trainings and symposiums
trainings and symposiums facilitated by private entities, individuals and/or corporations
NA (Have not attended CPD Trainings yet)

# Combine columns: cpd1, cpd2, cpd3, cpd4
dataset$cpd <- paste(dataset$cpd1, dataset$cpd2, dataset$cpd3, dataset$cpd4)
# Create new columns: inhouse, government, private, xattended
dataset <- transform(dataset, inhouse = grepl("within the work place", cpd), government = grepl("government", cpd), private = grepl("private", cpd), xattended = grepl("attended", cpd))
# Summarize by counting the TRUE values per materials
dataset %>%
summarise("in-house trainings" = sum(inhouse == TRUE), "government facilitated" = sum(government == TRUE), "private entities" = sum(private == TRUE), "Have not attended CPD Trainings" = sum(xattended == TRUE)) %>%
gather() %>%
ggplot(aes(x = key, y= value, fill = key)) + geom_col(position = "dodge") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: CPD Training", "n=562") + guides(fill = "none") + scale_fill_viridis_d() + theme(axis.text.x = element_text(angle = 90)) +
geom_text(x = 1, y = 199, label = "189", colour = "black", size = 4) + 
geom_text(x = 2, y = 103, label = "93", colour = "black", size = 4) + 
geom_text(x = 3, y = 168, label = "158", colour = "black", size = 4) +
geom_text(x = 4, y = 434, label = "424", colour = "black", size = 4)

Where do you usually get funding or support for your trainings in LIS?

from the work place (private sponsorship)
from the government (scholarships, free trainings and seminars, etc)
personal funding (personally attended trainings and symposiums and shouldered most of the expenses)
NA (Have not attended CPD Trainings yet)

# Combine columns: cpdsupport1, cpdsupport2, cpdsupport3
dataset$cpdsupport <- paste(dataset$cpdsupport1, dataset$cpdsupport2, dataset$cpdsupport3)
# Create new columns: support_inhouse, sgovernment, sprivate, sxattended
dataset <- transform(dataset, support_self = grepl("personal", cpdsupport), support_government = grepl("government", cpdsupport), support_private = grepl("private", cpdsupport), support_xattended = grepl("attended", cpdsupport))
# Summarize by counting the TRUE values per materials
dataset %>%
summarise("personal funding" = sum(support_self == TRUE), "government facilitated" = sum(support_government == TRUE), "private entities" = sum(support_private == TRUE), "Have not attended CPD Trainings" = sum(support_xattended == TRUE)) %>%
gather() %>%
ggplot(aes(x = key, y= value, fill = key)) + geom_col(position = "dodge") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: CPD Support", "n=562") + guides(fill = "none") + scale_fill_viridis_d() + theme(axis.text.x = element_text(angle = 90)) +
geom_text(x = 1, y = 162, label = "152", colour = "black", size = 4) +
geom_text(x = 2, y = 372, label = "362", colour = "black", size = 4) +
geom_text(x = 3, y = 300, label = "290", colour = "black", size = 4) +
geom_text(x = 4, y = 264, label = "254", colour = "black", size = 4)

Question: Are you satisfied with the amount of CPD trainings you have attended for the last two (2) years?

Yes, the amount of trainings I received within the last two (2) years is enough.
No, the amount of trainings I received within the last two (2) years is not enough.
No, the amount of trainings received within the last two (2) years is too much.
Maybe
NA (Have not attended CPD Trainings yet)

# Change the factor type
dataset$cpdsatisfaction <- as.factor(dataset$cpdsatisfaction)
# Recode responses
levels(dataset$cpdsatisfaction)[1] <- "Maybe"
levels(dataset$cpdsatisfaction)[2] <- "Have not attended CPD Trainings"
levels(dataset$cpdsatisfaction)[3] <- "No, not enough"
levels(dataset$cpdsatisfaction)[4] <- "No, too much"
levels(dataset$cpdsatisfaction)[5] <- "Yes"
# Rearrange the responses
dataset$cpdsatisfaction <- factor(dataset$cpdsatisfaction, levels = c("Yes", "No, not enough", "No, too much", "Maybe", "Have not attended CPD Trainings"))
# Graph the data
dataset %>%
filter(!is.na(cpdsatisfaction)) %>%
ggplot(aes(x = cpdsatisfaction, fill = cpdsatisfaction)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: CPD Satisfaction", "n=562") + guides(fill = "none") + theme(axis.text.x = element_text(angle = 90)) + scale_fill_viridis_d()

Question: Kindly indicate any challenges you encounter when fulfilling the required CPD trainings

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en")))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text dataset
cpdbarriers.text <- paste(dataset$cpdbarriers1, dataset$cpdbarriers2, dataset$cpdbarriers3)
# Create a text corpus
cpdbarriers.corpus <- cpdbarriers.text %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
cpdbarriers.corpus <- clean_corpus(cpdbarriers.corpus)
# Create a dendogram
cpdbarriers.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.98) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Kindly indicate any topics you wish to explore in future trainings

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en"), "library", "librarianship"))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text dataset
topics.text <- paste(dataset$topics1, dataset$topics2, dataset$topics3, dataset$topics4, dataset$topics5)
# Create a text corpus
topics.corpus <- topics.text %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
topics.corpus <- clean_corpus(topics.corpus)
# Create a dendogram
topics.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.985) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Kindly indicate your primary work location

NCR
Region I
Region II
CAR
Region III
Region IV
Region V
Region VI
Region VII
Region VIII
Region IX
Region X
Region XI
Region XII
CARAGA
ARMM

# Change the factor type
dataset$location <- as.factor(dataset$location)
# Rearrange the responses
dataset$location <- factor(dataset$location, levels = c( 'Region I', 'Region II', 'CAR', 'Region III', 'NCR' , 'Region IV', 'Region V', 'Region VI', 'Region VII', 'Region VIII', 'Region IX','Region X', 'Region XI', 'Region XII', 'CARAGA' ,'ARMM'))
# Graph the data
dataset %>%
filter(!is.na(location)) %>%
ggplot(aes(x = location, fill = location)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Location", "n=537") + guides(fill = "none") + theme(axis.text.x = element_text(angle = 90)) + scale_fill_viridis_d()

# Create lvm column
dataset <- dataset %>%
mutate(lvm = location)
# Recode responses
dataset$lvm <- as.factor(dataset$lvm)
levels(dataset$lvm)[16] <- "Mindanao"
levels(dataset$lvm)[15] <- "Mindanao"
levels(dataset$lvm)[14] <- "Mindanao"
levels(dataset$lvm)[13] <- "Mindanao"
levels(dataset$lvm)[12] <- "Mindanao"
levels(dataset$lvm)[11] <- "Mindanao"
levels(dataset$lvm)[10] <- "Visayas"
levels(dataset$lvm)[9] <- "Visayas"
levels(dataset$lvm)[8] <- "Visayas"
levels(dataset$lvm)[7] <- "Luzon"
levels(dataset$lvm)[6] <- "Luzon"
levels(dataset$lvm)[5] <- "NCR"
levels(dataset$lvm)[4] <- "Luzon"
levels(dataset$lvm)[3] <- "Luzon"
levels(dataset$lvm)[2] <- "Luzon"
levels(dataset$lvm)[1] <- "Luzon"
# Graph the data
dataset %>%
filter(!is.na(lvm)) %>%
ggplot(aes(x = lvm, fill = lvm)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Location", "n=537") + guides(fill = "none") + theme(axis.text.x = element_text(angle = 90)) + scale_fill_viridis_d()

Question: Have you moved out of your original / permanent residence in order to work on your current work place?

# Change the factor type
dataset$worktravel <- as.factor(dataset$worktravel)
# Rearrange the responses
dataset$worktravel <- factor(dataset$worktravel, levels = c("Yes", "No"))
# Graph the data
dataset %>%
filter(!is.na(worktravel)) %>%
ggplot(aes(x = worktravel, fill = worktravel)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + guides(fill = "none") + ggtitle("Distribution of Responses: Work Travel", "n=565") + scale_fill_viridis_d()

Is Filipino / Tagalog your native language?

# Change the factor type
dataset$filipino <- as.factor(dataset$filipino)
# Rearrange the responses
dataset$filipino <- factor(dataset$filipino, levels = c("Yes", "No"))
# Graph the data
dataset %>%
filter(!is.na(filipino)) %>%
ggplot(aes(x = filipino, fill = filipino)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + guides(fill = "none") + ggtitle("Distribution of Responses: Filipino as First Language", "n=550") + scale_fill_viridis_d()

Kindly check the local languages or dialects you can speak on a conversational level other than Filipino / Tagalog

Ilocano
Cebuano
Ilonggo
Kapampangan
Pangasinense
Waray
Bicolano
Others

# Change the factor type
dataset$dialect <- as.factor(dataset$dialect)
# Rearrange the responses
dataset$dialect <- factor(dataset$dialect, levels = c('Cebuano', 'Ilocano', 'Bicolano', 'Ilonggo', 'Kapampangan', 'Waray', 'Pangasinense', 'Others'))
# Graph the data
dataset %>%
filter(!is.na(dialect)) %>%
ggplot(aes(x = dialect, fill = dialect)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + guides(fill = "none") + ggtitle("Distribution of Responses: Dialect", "n=391") + scale_fill_viridis_d()

Kindly indicate any foreign languages or dialects you can speak on a conversational level other than English (if any)

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en"), "none", "can", "kankanaey"))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text corpus
topics.corpus <- dataset$foreignlang %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
topics.corpus <- clean_corpus(topics.corpus)
# Create a wordcount
term.frequency <- topics.corpus %>%
TermDocumentMatrix() %>%
as.matrix() %>%
rowSums() %>%
sort( , decreasing=TRUE)
term.frequency[1:10]

##  spanish  english  tagalog   french  ilonggo   korean  chinese filipino 
##       24       15       11        9        8        8        6        6 
##  ilocano   bahasa 
##        6        4

Kindly indicate the type of library you are currently working in

# Change the factor type
dataset$type <- as.factor(dataset$type)
# Recode responses
dataset$type <- fct_recode(dataset$type, 
"NA" = '#NAME?', 
"NA" = '...', 
"Academic" = 'academic', 
"Academic" = 'Academic', 
"Academic" = 'Academic-Special', 
"Academic" = 'Academic - Seminary', 
"Academic" = 'Academic (College)', 
"Academic" = 'Academic (Government)', 
"Academic" = 'Academic (Private-Catholic School)', 
"Academic" = 'Academic (University)', 
"Academic" = 'academic / private', 
"Academic" = 'Academic and Research Library (SUC-University)', 
"Academic" = 'academic and school', 
"Academic" = 'Academic and school libraries', 
"Academic" = 'academic and school library', 
"Academic" = 'academic college library', 
"Academic" = 'academic library', 
"Academic" = 'Academic library', 
"Academic" = 'Academic Library', 
"Academic" = 'ACADEMIC LIBRARY', 
"Academic" = 'Academic Library (Medical/Allied Health)', 
"Academic" = 'academic library (university)', 
"Academic" = 'Academic library / State university library', 
"Academic" = 'Academic library in a Government Institution', 
"Academic" = 'Academic library under LGU', 
"Academic" = 'Academic Medical Library', 
"Academic" = 'Academic State University', 
"Academic" = 'academic SUCs', 
"Academic" = 'Academic SUCs HEIs', 
"Academic" = 'Academic.', 
"Academic" = 'Academic/ Research Library', 
"Academic" = 'Academic/Government Institutionalize', 
"Special" = 'Academic/institutional archives', 
"Academic" = 'Academic/Public Library', 
"Academic" = 'Academic/Secondary library', 
"Academic" = 'Academic/Special Library', 
"Academic" = 'Alliance Graduate School Library', 
"Academic" = 'An academic library with a 10, 000 student population. The library has 3 sub libraries aside from the main library. The main library also caters to the SHS students. Currently within the main library, the SHS collection is identified separately.', 
"Special" = 'Archives', 
"Special" = 'Archives or Records Management', 
"Special" = 'Archives/Records Management', 
"School" =  'Chinese private school', 
"Academic" = 'college', 
"Academic" = 'college library', 
"Academic" = 'College library', 
"Academic" = 'College Library', 
"Academic" = 'College Library funded by LGU', 
"NA" = 'Confidential', 
"School" = 'DepEd (School) Library', 
"School" = 'DepEd division Library', 
"School" = 'Deped library hub', 
"School" = 'Division library', 
"NA" = 'Freelance', 
"Public" = 'Government', 
"Special" = 'Government Archives', 
"Public" = 'Government library', 
"Public" = 'Government Public Library', 
"Special" = 'government special library', 
"Academic" = 'Government/ Academic', 
"Academic" = 'Graduate school', 
"School" = 'High school library', 
"Academic" = 'I am currently the audio-visual librarian of our university', 
"School" = 'IBO K-12', 
"School" = 'Junior High School Library', 
"Special" = 'Law library', 
"Special" = 'Law Library', 
"Special" = 'Law Library (Special)', 
"Special" = 'Law Library/Special Library', 
"Public" = 'LGU library', 
"Public" = 'Library Hub', 
"School" = 'Library school', 
"Academic" = 'LIS school', 
"Special" = 'Media Library', 
"Academic" =  'Medical and\r\nAllied Health Library', 
"Academic" = 'Medical/Academic library', 
"Special" = 'Military Library (Special academic library', 
"Public" = 'municipal library', 
"Public" = 'Municipal Library', 
"Special" = 'Museum', 
"NA" = 'n/a', 
"NA" = 'N/A', 
"NA" = 'NA. publishing company', 
"NA" = 'NA. Working in a BPO', 
"Public" = 'National', 
"Special" = 'NGO Digital Library', 
"NA" = 'None', 
"NA" = 'Not applicable', 
"Special" = 'Not in a library but in an archives', 
"NA" = 'Not library. GOCC.', 
"NA" = 'Not working in a library', 
"NA" = 'Not working in a library setting', 
"NA" = 'Not working in a library setting since two years ago', 
"Special" = 'Not working in a library. Working in a Data Office', 
"NA" = 'Private', "Academic" = 'Private academic/school (hybrid) library', 
"Academic" =  'private HEI',
"Academic" ='Privately owned libraries (academic)', 
"Public" = 'Provincial Library.', 
"Public" = 'Public high school library', 
"Public" = 'public library', 
"Public" = 'Public library', 
"Public" = 'Public Library', 
"Academic" = 'Public Library/ Academic', 
"School" = 'Public school library', 
"School" = 'Public School Library', 
"School" = 'Public School LIbrary', 
"School" = 'Public School Library (Deped Division Office)', 
"Special" = 'records center', 
"School" = 'school', 
"School" = 'School', 
"School" = 'School (primary and secondary)', 
"Academic" = 'School and Academic library', 
"Academic" = 'School and Academic Library', 
"School" = 'school library', 
"School" = 'School library', 
"School" = 'School Library', 
"School" = 'School library ( Private)', 
"School" = 'School Library (Elementary)', 
"School" = 'School Library (Senior High School Library)', 
"School" = 'School library (under both DepED and TESDA)', 
"Academic" = 'School Library and academic Library', 
"School" = 'School library and prefer to be with the academic library soon', 
"School" = 'School library and reading center', 
"School" = 'School Library specifically Library Hub, a project of the Department of Education', 
"School" = 'School library, catering exclusively junior high school students and staff', 
"School" = 'School library.', 
"Academic" = 'School/Academic Library', 
"Academic" = 'School/academic library - Technical Section', 
"School" = 'School/Public', 
"School" = 'Secondary school library', 
"Academic" = 'Slis', 
"NA" = 'Spanish, bahasa', 
"Special" = 'special', 
"Special" = 'Special', 
"Special" = 'Special-Public', 
"Special" = 'Special (government law) library', 
"Special" = 'special academic library', 
"Special" = 'special library', 
"Special" = 'Special library', 
"Special" = 'Special Library', 
"Special" = 'SPECIAL LIBRARY', 
"Special" = 'Special Library in an Auditing Firm', 
"Special" = 'Special library/Archives\r\nDigital records', 
"Special" = 'Special library/Government', 
"Special" = 'Special Public Library', 
"Special" = 'Special/public/research library', 
"Special" = 'Special/Research Library', 
"Special" = 'specual libray', 
"Academic" = 'State u', 
"Academic" = 'State University', 
"Academic" = 'State university library', 
"Academic" = 'State/ Academic', 
"Academic" = 'SUC', 
"Academic" = 'SUC (Academic Library)', 
"Academic" = 'SUC library', 
"Academic" = 'SUC Library', 
"Special" = 'University Archives', 
"Academic" = 'University library', 
"Academic" = 'University Library', 
"Academic" = 'University Library - at the regional campus specializing in Law')
# Rearrange the responses
dataset$type <- factor(dataset$type, levels = c("Academic", "School", "Special", "Public"))
# Graph the data
dataset %>%
filter(!is.na(type)) %>%
ggplot(aes(x = type, fill = type)) + geom_bar() + geom_text(aes(label = ..count..), stat = "count", vjust = -0.2, colour = "black") + xlab("Distribution of responses") + ylab("Frequency") + guides(fill = "none") + ggtitle("Distribution of Responses: Library Type", "n=473") + scale_fill_viridis_d()

Other than being a librarian, what other roles do you serve in your institution/ organization?

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en"), "library", "librarianship", "none", "librarian"))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text corpus
roles.corpus <- dataset$roles %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
roles.corpus <- clean_corpus(roles.corpus)
# Create a dendogram
roles.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.99) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Kindly indicate your current work position

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en"),"iii", "library", "librarianship", "none", "librarian", "sole", "librarians"))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text corpus
institutionposition.corpus <- dataset$institutionposition %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
institutionposition.corpus <- clean_corpus(institutionposition.corpus)
# Create a dendogram
institutionposition.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.99) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Kindly indicate your primary job / designation inside the library

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en"),"iii", "library", "librarianship", "none", "librarian", "sole", "librarians"))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text corpus
primaryjob.corpus <- dataset$primaryjob %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
primaryjob.corpus <- clean_corpus(primaryjob.corpus)
# Create a dendogram
primaryjob.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.99) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

Kindly indicate your current / existing professional affiliations

# Change the factor type
dataset$affiliation <- as.factor(dataset$affiliation)
# Recode factors
levels(dataset$affiliation)[143] <- "PLAI, PAARL, RIzalenos Librarians Association, USTLISAA"
levels(dataset$affiliation)[144] <- "PLAI, PAARL, RLA Rizalenos Librarians Association"
dataset$affiliation <- fct_recode(dataset$affiliation, 
"ALPS" = 'ALPS',
"ASLP" = 'ASLP' ,
"PASLI" = 'before member of PASLI and PLAI-CeLRLC' ,
"NA" = 'Bplai' ,
"NA" = 'CLAI' ,
"NA" = 'DepEd' ,
"NA" = 'Dont renew yet my membership in PLAI' ,
"NA" = 'Haven\'t join any organization' ,
"NA" = 'I have not yet member seen i have a license' ,
"NA" = 'Inactive member of PLAI' ,
"LAQUEP" = 'Laquep, Plai stlrc' ,
"MAHLAP" = 'MAHLAP' ,
"MAHLAP PATLS" = 'MAHLAP /PATLS /PLAI' ,
"MAHLAP PAARL" = 'MAHLAP, PLAI, PAARL, ABCLI, PUPLSAAI, PAMJE, MLA' ,
"NA" = 'n/a' ,
"NA" = 'N/A' ,
"NA" = 'Na' ,
"NA" = 'NELAI (Nueva Ecija Librarian\'s Association, Inc.)' ,
"PAARL" = 'NELAI,  PLAI,  PAARL' ,
"NA" = 'none' ,
"NA" = 'None' ,
"NA" = 'NONE' ,
"NA" = 'None this year.' ,
"NA" = 'None yet' ,
"PAARL" = 'Paarl' ,
"PAARL" = 'PAARL' ,
"PAARL PASLI" = 'PAARL, PASLI' ,
"PAARL" = 'paarl, plai' ,
"PAARL" = 'PAARL, PLAI' ,
"PAARL PATLS" = 'PAARL, PLAI, PATLS, CODHLIS' ,
"PASLI" = 'PADLI' ,
"PASLI" = 'Pasli' ,
"PASLI" = 'PASLI' ,
"PASLI" = 'PASLI, PLAI' ,
"PASLI" = 'PASLI, PLAI, MUNPARLAS' ,
"PASLI" = 'PASLI, PNULISAA' ,
"PATLS" = 'PATLS' ,
"NA" = 'PLA' ,
"NA" = 'plai' ,
"NA" = 'Plai' ,
"NA" = 'PLAI' ,
"NA" = 'PLAI-CARAGA' ,
"NA" = 'PLAI-Caraga, CLLA, MINLA, MISORLA' ,
"NA" = 'PLAI-Davao' ,
"NA" = 'PLAI-IRLC' ,
"PAARL PATLS" = 'PLAI \r\nPAARL\r\nPATLS' ,
"MAHLAP" = 'PLAI & MAHLAP\r\nbut not renewed membership with PLAI and MAHLAP for the past 2 years.' ,
"PASLI" = 'PLAI & PASLI' ,
"NA" = 'PLAI (PLAI-BRLC)' ,
"NA" = 'PLAI , CoLiNet' ,
"PGLL ASLP SFA" = 'PLAI / PGLL / ASLP / SFA' ,
"NA" = 'PLAI and Bicol Region Librarians Council' ,
"NA" = 'PLAI and CLAI' ,
"MAHLAP" = 'PLAI and MAHLAP' ,
"MAHLAP" = 'PLAI AND MAHLAP' ,
"NA" = 'PLAI and MASTLINET' ,
"PAARL" = 'PLAI and Paarl' ,
"PAARL" = 'PLAI and PAARL' ,
"PASLI" = 'PLAI and PASLI' ,
"SFA" = 'PLAI and SFA' ,
"ASLP" = 'plai aslp' ,
"PAARL" = 'PLAI PAARL CAMANAVA' ,
"PAARL" = 'PLAI PAARL PNULISAA  Asso of Laguna Librarians' ,
"PGLL SFA" = 'PLAI PGLL SFA' ,
"NA" = 'PLAI STRLC, ALLPI\r\nPAARL (but have not yet renewed)' ,
"NA" = 'PLAI WVRLC' ,
"ASLP PAARL" = 'PLAI\r\nASLP\r\nPAARL' ,
"PATLS" = 'Plai\r\nCodhlis\r\nPatls' ,
"NA" = 'PLAI\r\nFORATL' ,
"MAHLAP" = 'PLAI\r\nMAHLAP' ,
"PAARL" = 'plai\r\npaarl' ,
"PAARL" = 'Plai\r\nPaarl' ,
"PAARL" = 'PLAI\r\nPAARL' ,
"PAARL" = 'PLAI\r\nPAARL\r\nAASDI' ,
"PAARL ASLP" = 'PLAI\r\nPAARL\r\nASLP' ,
"PAARL" = 'PLAI\r\nPAARL\r\nLAQueP-LInc' ,
"PAARL PATLS" = 'PLAI\r\nPAARL\r\nPATLS' ,
"PAARL" = 'Plai\r\nPaarl\r\nQCLC' ,
"PAARL SFA" = 'plai\r\nPaarl\r\nSfa\r\nAasdi\r\nKbp' ,
"PASLI" = 'PLAI\r\nPASLI' ,
"PASLI" = 'PLAI\r\nPASLI\r\nLLAI\r\nPLAI -ARMM' ,
"NA" = 'PLAI\r\nPNULISAA' ,
"NA" = 'PLAI\r\nPUP LSAA' ,
"NA" = 'PLAI\r\nSOCOLA' ,
"NA" = 'PLAI,' ,
"NA" = 'PLAI,  NIRLC' ,
"PAARL" = 'PLAI,  PAARL' ,
"NA" = 'PLAI, AASDI' ,
"ALAP" = 'PLAI, ALAP' ,
"ASFA" = 'PLAI, ALINET, ASFA, IAMSLIC' ,
"NA" = 'PLAI, ALINET, MASTLINET, LLAI' ,
"NA" = 'PLAI, ALINET, PLAI CRLC' ,
"ALPS" = 'PLAI, ALPS' ,
"ALPS" = 'PLAI, ALPS, LAQueP-LInc' ,
"PASLI" = 'PLAI, and PASLI' ,
"ALPS" = 'PLAI, APLIN, ALPS' ,
"NA" = 'PLAI, APPLI, NEFLI' ,
"ASLP" = 'PLAI, ASLP' ,
"ASLP SFA" = 'PLAI, ASLP, ICA, SFA' ,
"ASLP SLA" = 'PLAI, ASLP, SLA' ,
"ASLP" = 'PLAI, ASLP, UELISAAI' ,
"NA" = 'PLAI, ASSDI' ,
"NA" = 'PLAI, BPLAI' ,
"NA" = 'PLAI, BRLC' ,
"NA" = 'PLAI, Cagayan Valley Regional Librarians Association, Inc.; Nueva Vizcaya Librarians Association' ,
"NA" = 'PLAI, Cavite Librarians Inc.,' ,
"NA" = 'PLAI, CLAI' ,
"MAHLAP" = 'Plai, clai, mahlap' ,
"PAARL" = 'PLAI, CLAI, PAARL' ,
"NA" = 'PLAI, CLLA, Inc.' ,
"NA" = 'PLAI, DACUN' ,
"NA" = 'PLAI, DACUN, MASTLINET' ,
"NA" = 'PLAI, ICA, UPLSAA' ,
"NA" = 'PLAI, LAQUEPLINC,' ,
"MAHLAP" = 'Plai, mahlap' ,
"MAHLAP" = 'PLAI, MAHLAP' ,
"NA" = 'PLAI, MUNPARLAS' ,
"ASLP" = 'PLAI, MUNPARLAS, ASLP' ,
"NA" = 'PLAI, OMLA' ,
"PAARL" = 'plai, paarl' ,
"PAARL" = 'Plai, paarl' ,
"PAARL" = 'PLAi, PAARL' ,
"PAARL" = 'PLAI, pAARL' ,
"PAARL" = 'PLAI, PAARL' ,
"PAARL" = 'PLAI, PAARL and QCLC' ,
"PAARL" = 'PLAI, PAARL,' ,
"PAARL" = 'PLAI, PAARL, AASDI' ,
"PAARL" = 'PLAI, PAARL, ABCLI, QCLC' ,
"PAARL" = 'PLAI, PAARL, ALA' ,
"PAARL ALAP" = 'PLAI, PAARL, ALAP' ,
"PAARL ALAP" = 'PLAI, PAARL, ALAP, AASDI' ,
"PAARL ALAP" = 'PLAI, PAARL, ALAP, ALLPI' ,
"PAARL ASLP" = 'PLAI, PAARL, ASLP' ,
"PAARL ASLP MAHLAP SLA" = 'PLAI, PAARL, ASLP, MAHLAP, SLA' ,
"PAARL" = 'PLAI, PAARL, BLAI' ,
"PAARL MAHLAP" = 'PLAI, PAARL, MAHLAP' ,
"PAARL MAHLAP" = 'PLAI, PAARL, MAHLAP (Local), MLA (international)' ,
"PAARL PGLL" = 'PLAI, PAARL, PGLL, PUPLSAA' ,
"PAARL" = 'PLAI, PAARL, PLAI-STRLC' ,
"PAARL" = 'PLAI, PAARL, PNULISAA' ,
"PAARL" = 'PLAI, PAARL, PUPLSAA' ,
"PAARL" = 'PLAI, PAARL, QCLC (Quezon City Library Consortium)' ,
"PAARL" = 'PLAI, PAARL, RIzalenos Librarians Association, USTLISAA' ,
"PAARL" = 'PLAI, PAARL, RLA Rizalenos Librarians Association' ,
"PAARL" = 'PLAI, PAARL, UPLSAA' ,
"PAARL" = 'PLAI, PAARL, UPLSAA, PUPLSAA' ,
"PAARL" = 'PLAI, PAARL, Vanuatu Librarians\' Association' ,
"PAARL" = 'PLAI, PAARL, Western Visayas Association of Museums' ,
"PAARL PASLI" = 'PLAI, PAARL,PASLI' ,
"PAARL PASLI" = 'PLAI, PADLI' ,
"PAARL PASLI" = 'PLAI, PASLI' ,
"PAARL PASLI" = 'PLAI, PASLI, LAQueP-LInc, MUNPARLAS' ,
"PAARL PASLI" = 'PLAI, PASLI, UPLSAA' ,
"PAARL PATLS" = 'PLAI, PATLS' ,
"PAARL PATLS SFA" = 'Plai, patls, sfa' ,
"PAARL PATLS SFA" = 'PLAI, PATLS, SFA' ,
"NA" = 'Plai, pearl, clla' ,
"PGLL" = 'PLAI, PGLL' ,
"PGLL" = 'PLAI, PGLL, and LLIWA' ,
"PGLL SFA" = 'PLAI, PGLL, SFA' ,
"NA" = 'Plai, Plai-Central luzon, Nueva ecija librarian association' ,
"NA" = 'PLAI, PLAI-NIRLC' ,
"NA" = 'PLAI, PLAI-RLC' ,
"ALPS" = 'PLAI, PLAI-STRLC, ALPS, LAQueP-LInc' ,
"NA" = 'PLAI, PLAI-STRLC, OMLA' ,
"NA" = 'PLAI, PLAI - IRLC' ,
"NA" = 'PLAI, PSPL, BOLA' ,
"NA" = 'plai, regional council for librarians' ,
"SFA" = 'PLAI, SFA' ,
"NA" = 'PLAI, UPLSAA' ,
"ASLP" = 'PLAI,ASLP' ,
"PASLI" = 'PLAI,PASLI' ,
"PATLS" = 'PLAI,PATLS, CODHLIS' ,
"NA" = 'PLAI.' ,
"PAARL" = 'PLAI; PAARL' ,
"PAARL" = 'PLAI< PAARL' ,
"PASLI" = 'Plain and Philippine Association of DepEd Librarians,Inc. (PADLI)' ,
"NA" = 'PLAL' ,
"NA" = 'PNULISAA' ,
"NA" = 'QCLC' ,
"NA" = 'RLA' ,
"NA" = 'UPLSAA')

## Warning: Unknown levels in `f`: PLAI, PAARL, QCLC (Quezon City Library
## Consortium), PLAI, PAARL, UPLSAA

# Create new columns: PAARL, PASLI, ASLP, MAHLAP, PATLS, ALAP, ALPS, PGLL, SFA
dataset <- transform(dataset, 
                     PAARL = grepl("PAARL",affiliation), 
                     PASLI = grepl("PASLI", affiliation), 
                     ASLP = grepl("ASLP", affiliation), 
                     MAHLAP = grepl("MAHLAP", affiliation), 
                     PATLS = grepl("PATLS", affiliation),
                     ALAP = grepl("ALAP", affiliation),
                     ALPS = grepl("ALPS", affiliation),
                     PGLL = grepl("PGLL", affiliation),
                     SFA = grepl("SFA", affiliation))
# Summarize by counting the TRUE values per materials
dataset %>%
summarise("PAARL" = sum(PAARL == TRUE), 
          "PASLI" = sum(PASLI == TRUE), 
          "ASLP" = sum(ASLP == TRUE), 
          "MAHLAP" = sum(MAHLAP == TRUE), 
          "ALAP" = sum(ALAP == TRUE), 
          "ALPS" = sum(ALPS == TRUE), 
          "PGLL" = sum(PGLL == TRUE), 
          "SFA" = sum(SFA == TRUE)) %>%
gather() %>%
ggplot(aes(x = key, y= value, fill = key)) + geom_col(position = "dodge") + xlab("Distribution of responses") + ylab("Frequency") + ggtitle("Distribution of Responses: Materials", "n=195") + guides(fill = "none") + scale_fill_viridis_d() + theme(axis.text.x = element_text(angle = 90)) +
geom_text(x = 1, y = 10, label = "7", colour = "black", size = 4) + 
geom_text(x = 2, y = 9, label = "6", colour = "black", size = 4) + 
geom_text(x = 3, y = 25, label = "23", colour = "black", size = 4) + 
geom_text(x = 4, y = 21, label = "18", colour = "black", size = 4) + 
geom_text(x = 5, y = 131, label = "128", colour = "black", size = 4) + 
geom_text(x = 6, y = 40, label = "37", colour = "black", size = 4) + 
geom_text(x = 7, y = 9, label = "6", colour = "black", size = 4) + 
geom_text(x = 8, y = 14, label = "11", colour = "black", size = 4)

Kindly indicate what factors influence your decision when it comes to joining a professional organization?

# Create a clean_corpus function 
clean_corpus <- function(corpus) {
    corpus <- tm_map(corpus, removePunctuation)
    corpus <- tm_map(corpus, removeNumbers)
    corpus <- tm_map(corpus, content_transformer(tolower))
    corpus <- tm_map(corpus, removeWords, c(stopwords("en")))
    corpus <- tm_map(corpus, stripWhitespace)
    return(corpus)
}
# Create a text corpus
factor.corpus <- dataset$factor %>%
VectorSource() %>%
VCorpus()
# Clean the created corpus
factor.corpus <- clean_corpus(factor.corpus)
# Create a dendogram
factor.corpus %>%
TermDocumentMatrix() %>%
removeSparseTerms(sparse = 0.985) %>%
as.matrix() %>%
dist() %>%
hclust() %>%
plot()

glimpse(dataset)

## Rows: 684
## Columns: 107

## Warning in grepl(",", levels(x), fixed = TRUE): input string 1 is invalid UTF-8

## Warning in grepl(",", levels(x), fixed = TRUE): input string 30 is invalid UTF-8

## $ voter                <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15…
## $ licensed             <fct> Licensed librarian, Licensed librarian, Licensed …
## $ philippines          <fct> NA, Residing outside of the Philippines, Residing…
## $ gender               <fct> NA, Prefer not to say, Female, Male, Male, Male, …
## $ age                  <dbl> 59, 100, 40, 46, 32, 46, 48, 44, 25, 24, 34, 39, …
## $ working              <fct> NA, Retired, Employed, Employed, Employed, Employ…
## $ industry             <fct> NA, ICT, Academe, Academe, Academe, Academe, Acad…
## $ years_service        <dbl> NA, 60, 14, 23, 10, 24, 23, 12, 5, 1, 12, 18, 14,…
## $ institution          <fct> NA, Private, Government, Government, Government, …
## $ tenure               <fct> NA, Self-employed, Permanent, Permanent, Contract…
## $ gross_salary         <dbl> NA, 100, 51, 53, 40, 56, 36, 38, 19, 11, 95, 58, …
## $ net_salary           <dbl> NA, 100, 30, 38, 30, 42, 29, 26, NA, 10, 95, 36, …
## $ benefits1            <fct> NA, night differential pay, paid vacation and/or …
## $ benefits2            <chr> NA, NA, "monetary allowances", "monetary allowanc…
## $ benefits3            <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "…
## $ benefits4            <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ benefits5            <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ otherbenefits1       <chr> NA, "123", "Rice allowance\r\nClothing allowance\…
## $ otherbenefits2       <chr> NA, "123", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ otherbenefits3       <chr> NA, "Hello Philippines and hello world", NA, NA, …
## $ otherbenefits4       <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ materials1           <chr> NA, "law materials and resources", NA, "archives …
## $ materials2           <chr> NA, NA, NA, "hardcopy theses and dissertations", …
## $ materials3           <chr> NA, NA, NA, "hardcopy books / pamphlets / etc", N…
## $ materials4           <chr> NA, NA, NA, "institutional files and records", NA…
## $ materials5           <chr> NA, NA, NA, "data sets", NA, "archives (physical)…
## $ materials6           <chr> NA, NA, NA, "electronic material (digital titles,…
## $ materials7           <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ othermaterials1      <chr> NA, "Huehs", "Grading sheets\r\nExam papers", "Bo…
## $ othermaterials2      <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ othermaterials3      <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ othermaterials4      <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ position             <fct> NA, Supervisory, Supervisory, Senior level, Senio…
## $ fiveyears            <fct> NA, No, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Undeci…
## $ pursue               <chr> NA, "Hfeudnr", NA, NA, NA, NA, NA, NA, NA, NA, NA…
## $ education            <fct> NA, Ph.D, Master degree, MLIS, Master degree, MLI…
## $ enrolled             <fct> NA, Yes, Yes, Yes, No, Yes, Yes, No, Yes, No, No,…
## $ completing           <fct> NA, Post Graduate non-LIS, Ph.D., Ph.D., Ph.D., P…
## $ study_again          <fct> NA, NA, No, Yes, Yes, Yes, Yes, Yes, Yes, Yes, Ma…
## $ after5years          <fct> NA, NA, NA, Short Course, Ph.D., Short Course, Ph…
## $ cpd1                 <chr> NA, NA, "trainings and symposiums facilitated by …
## $ cpd2                 <chr> NA, NA, "government facilitated trainings and sym…
## $ cpd3                 <chr> NA, NA, NA, NA, "within the work place (in-house …
## $ cpd4                 <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ cpdsupport1          <chr> NA, NA, "from the government (scholarships, free …
## $ cpdsupport2          <chr> NA, NA, NA, "from the government (scholarships, f…
## $ cpdsupport3          <chr> NA, NA, NA, "from the work place (private sponsor…
## $ cpdsatisfaction      <fct> NA, NA, "Yes", "Yes", "Maybe", "Yes", "Yes", "Yes…
## $ cpdbarriers1         <chr> NA, NA, "CPD program sources that I really like",…
## $ cpdbarriers2         <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ cpdbarriers3         <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ topics1              <chr> NA, NA, "Ethics\r\nCommunication skills\r\nCookin…
## $ topics2              <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ topics3              <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ topics4              <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ topics5              <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ location             <fct> NA, NA, NCR, NCR, NCR, NCR, NCR, NCR, Region IV, …
## $ worktravel           <fct> NA, NA, Yes, Yes, Yes, Yes, No, No, No, No, Yes, …
## $ filipino             <fct> NA, NA, No, Yes, Yes, Yes, No, Yes, Yes, Yes, Yes…
## $ dialect              <fct> NA, NA, Ilocano, NA, Others, NA, Kapampangan, NA,…
## $ foreignlang          <chr> NA, NA, "None", NA, "Chinese", NA, NA, "English",…
## $ type                 <fct> NA, NA, Academic, School, NA, School, NA, NA, Sch…
## $ roles                <chr> NA, NA, "Cleaner\r\nCook", NA, "Faculty", "Asst p…
## $ institutionposition  <chr> NA, NA, "Head", "Asst prof 5", "Asst. Prof.", "As…
## $ primaryjob           <chr> NA, NA, NA, "Education", "Research, Extention, Te…
## $ affiliation          <fct> NA, NA, PATLS, PAARL PATLS SFA, PATLS, PAARL PATL…
## $ factor               <chr> NA, NA, "Friends", "Similar thrusts", "colleagues…
## $ age_group            <fct> 51-60, NA, 41-50, 41-50, 31-40, 41-50, 41-50, 41-…
## $ years_service_group  <fct> NA, NA, 10-14, 20-24, 10-14, 20-24, 20-24, 10-14,…
## $ gross_salary_group   <fct> NA, Greater than 50k, Greater than 50k, Greater t…
## $ net_salary_group     <fct> NA, Greater than 50k, 21-30, 31-40, 21-30, 41-50,…
## $ benefits             <chr> "NA NA NA NA NA", "night differential pay NA NA N…
## $ shuttle              <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ night_differential   <lgl> FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, F…
## $ paid_leaves          <lgl> FALSE, FALSE, TRUE, TRUE, FALSE, TRUE, TRUE, FALS…
## $ hmo                  <lgl> FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, F…
## $ allowances           <lgl> FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,…
## $ no_benefits          <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ benefits6            <fct> NA, With Benefits, With Benefits, With Benefits, …
## $ materials            <chr> "NA NA NA NA NA NA NA", "law materials and resour…
## $ theses               <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, TRU…
## $ books                <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, TRU…
## $ electronic_materials <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, TRU…
## $ law_materials        <lgl> FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, TRUE, FA…
## $ datasets             <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, FALSE, TR…
## $ archives             <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, TRU…
## $ institutional_files  <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, FAL…
## $ cpd                  <chr> "NA NA NA NA", "NA NA NA NA", "trainings and symp…
## $ inhouse              <lgl> FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, FALSE, TR…
## $ government           <lgl> FALSE, FALSE, TRUE, FALSE, TRUE, TRUE, FALSE, TRU…
## $ private              <lgl> FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE,…
## $ xattended            <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ cpdsupport           <chr> "NA NA NA", "NA NA NA", "from the government (sch…
## $ support_self         <lgl> FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, FALSE, TRU…
## $ support_government   <lgl> FALSE, FALSE, TRUE, TRUE, FALSE, TRUE, TRUE, TRUE…
## $ support_private      <lgl> FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, FALS…
## $ support_xattended    <lgl> FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, FALSE, TRU…
## $ lvm                  <fct> NA, NA, NCR, NCR, NCR, NCR, NCR, NCR, Luzon, Luzo…
## $ PAARL                <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, FALSE, FA…
## $ PASLI                <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ ASLP                 <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ MAHLAP               <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ PATLS                <lgl> FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, FALSE, TRUE…
## $ ALAP                 <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ ALPS                 <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ PGLL                 <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ SFA                  <lgl> FALSE, FALSE, FALSE, TRUE, FALSE, TRUE, FALSE, FA…

# Save the updated dataset
write_rds(dataset, "LibrarianCensus.rds")

Librarian Census Data Code

Dan Anthony Dorado

2022-07-20