Sentiment Identification for Collaborative, Geographically Dispersed, Cross-Functional Software Development Teams

1. Does the paper propose a new opinion mining approach?

Yes

2. Which opinion mining techniques are used (list all of them, clearly stating their name/reference)?

It's a custom ML-based approach, using as features words and n-grams extracted from written communication. Messages were annotated by five experts using three class labels with positive sentiment (denoted by label 0), negative sentiment (denoted by label 1) and neutral state (denoted by label 2). Then, ML approaches were trained and tested.

3. Which opinion mining approaches in the paper are publicly available? Write down their name and links. If no approach is publicly available, leave it blank or None.

None

4. What is the main goal of the whole study?

Sentiment analysis was used to implement an emotion dashboard to measure the project success and emotional health across various cross-functional software development teams.

5. What the researchers want to achieve by applying the technique(s) (e.g., calculate the sentiment polarity of app reviews)?

Calculate the sentiment polarity of communications within development teams.

6. Which dataset(s) the technique is applied on?

Emails exchanged across teams, internal management and leadership blogs, discussions from the internal website forums and project websites, code review comments, and bug tracking reports were collected for three months.

7. Is/Are the dataset(s) publicly available online? If yes, please indicate their name and links.

No

8. Is the application context (dataset or application domain) different from that for which the technique was originally designed?

No

9. Is the performance (precision, recall, run-time, etc.) of the technique verified? If yes, how did they verify it and what are the results?

Yes, using precision/recall/FM with a 10-fold cross validation. Best approach is MultilayerPerceptron with 60% of correct classifications.

10. Does the paper replicate the results of previous work? If yes, leave a summary of the findings (confirm/partially confirms/contradicts).

No

11. What success metrics are used?

precision/recall/FM

12. Write down any other comments/notes here.

-