DISCO-A Dataset of Discord Chat Conversations for Software Engineering Research.zip
README.md
7.7 kB
case_study
Inter_topic_distance maps
Python_HTMLSourcecode.txt
205.5 kB
Racket_HTMLSourcecode.txt
108.7 kB
clojurians_HTMLSourcecode.txt
96.6 kB
golang_HTMLSourcecode.txt
142.8 kB
ldavis_prepared_Racket1.html
108.7 kB
ldavis_prepared_Racket1.pickle
86.2 kB
ldavis_prepared_clojurians.html
96.6 kB
ldavis_prepared_clojurians.pickle
76.1 kB
ldavis_prepared_golang.html
142.8 kB
ldavis_prepared_golang.pickle
115.1 kB
ldavis_prepared_python.html
205.5 kB
ldavis_prepared_python.pickle
165.5 kB
Scripts
Clojurians.ipynb
133.6 kB
Golang.ipynb
183.8 kB
Python.ipynb
248.1 kB
Racket.ipynb
146.5 kB
data
clojurians
Aug2020-Oct2020
clojure_Aug2020-Oct2020.xml
71.6 kB
clojure_Aug2020-Oct2020.xml.out
77.4 kB
Feb2020-Apr2020
clojure_Feb2020-Apr2020.xml
83.5 kB
clojure_Feb2020-Apr2020.xml.out
90.8 kB
May2020-July2020
clojure_May2020-Jul2020.xml
72.3 kB
clojure_May2020-Jul2020.xml.out
78.4 kB
Nov2019-Jan2020
clojure_Nov2019-Jan2020.xml
70.9 kB
clojure_Nov2019-Jan2020.xml.out
76.7 kB
golang
Aug2020-Sep2020
golang_Aug2020-Sep2020.xml
9.4 MB
golang_Aug2020-Sep2020.xml.out
10.5 MB
Feb2020-Apr2020
golang_Feb2020-Apr2020.xml
11.2 MB
golang_Feb2020-Apr2020.xml.out
12.5 MB
May2020-July2020
golang_May2020-Jul2020.xml
11.7 MB
golang_May2020-Jul2020.xml.out
13.0 MB
Nov2019-Jan2020
golang_Nov2019-Jan2020.xml
6.3 MB
golang_Nov2019-Jan2020.xml.out
7.0 MB
pythongeneral
Apr2020
pythongeneralApr2020.xml
11.9 MB
pythongeneralApr2020.xml.out
13.2 MB
Aug2020
pythongeneralAug2020.xml
32.1 MB
pythongeneralAug2020.xml.out
35.8 MB
Dec2019
pythongeneralDec2019.xml
4.9 MB
pythongeneralDec2019.xml.out
5.4 MB
Feb2020
pythongeneralFeb2020.xml
6.0 MB
pythongeneralFeb2020.xml.out
6.7 MB
Jan2020
pythongeneralJan2020.xml
7.2 MB
pythongeneralJan2020.xml.out
8.0 MB
Jul2020
pythongeneralJul2020.xml
25.2 MB
pythongeneralJul2020.xml.out
28.1 MB
Jun2020
pythongeneralJun2020.xml
18.7 MB
pythongeneralJun2020.xml.out
20.8 MB
Mar2020
pythongeneralMar2020.xml
8.7 MB
pythongeneralMar2020.xml.out
9.7 MB
May2020
pythongeneralMay2020.xml
15.1 MB
pythongeneralMay2020.xml.out
16.8 MB
Nov2019
pythongeneralNov2019.xml
5.2 MB
pythongeneralNov2019.xml.out
5.8 MB
Oct2020
pythongeneralOct2020.xml
32.4 MB
pythongeneralOct2020.xml.out
36.0 MB
Sep2020
pythongeneralSep2020.xml
27.0 MB
pythongeneralSep2020.xml.out
30.0 MB
racketgeneral
Aug2020-Oct2020
Racket_general_Aug2020-Oct2020.xml
350.1 kB
Racket_general_Aug2020-Oct2020.xml.out
382.3 kB
Feb2020-Apr2020
Racket_general_Feb2020-Apr2020.xml
210.7 kB
Racket_general_Feb2020-Apr2020.xml.out
229.5 kB
May2020-July2020
Racket_general_May2020-Jul2020.xml
154.0 kB
Racket_general_May2020-Jul2020.xml.out
166.1 kB
Nov2019-Jan2020
racketgeneral_Nov2019-Jan2020.xml
202.9 kB
racketgeneral_Nov2019-Jan2020.xml.out
220.5 kB
scripts
COPYING
35.1 kB
discord_JSON_to_XML
Discord_JSON_to_XML_conversion.ipynb
14.0 kB
disentanglement
corpora
training.annot
403.7 kB
unigram.txt
29.7 kB
elsner-charniak-08-mod
IRC
dev
linux-dev-0X.annot
63.1 kB
linux-dev.txt
59.1 kB
linux-rest.txt
1.1 MB
linux.txt
1.3 MB
pilot
linux-pilot-0X.annot
29.0 kB
linux-pilot-1.annot
29.0 kB
linux-pilot-2.annot
29.0 kB
linux-pilot-3X.annot
28.8 kB
linux-pilot.txt
27.2 kB
test
linux-test-0.annot
59.3 kB
linux-test-1.annot
59.6 kB
linux-test-2.annot
59.3 kB
linux-test-3.annot
59.3 kB
linux-test-4.annot
59.3 kB
linux-test-5.annot
59.3 kB
linux-test-6X.annot
59.3 kB
linux-test.txt
55.4 kB
analysis
__init__.py
0 Bytes
bestBaseline.py
1.9 kB
chatStats.py
16.5 kB
describe.py
648 Bytes
distMat.py
3.9 kB
printDeltaT.py
318 Bytes
printTimes.py
146 Bytes
speakerStats.py
849 Bytes
data
linux-unigrams.dump
257.0 kB
names.txt
300.4 kB
techwords.dump
130.6 kB
megam_src.tgz
63.2 kB
model
OldclassifierTest.py
2.6 kB
analysis
__init__.py
0 Bytes
__init__.pyc
210 Bytes
bestBaseline.py
1.9 kB
chatStats.py
16.5 kB
chatStats.pyc
22.4 kB
describe.py
648 Bytes
distMat.py
3.9 kB
printDeltaT.py
318 Bytes
printTimes.py
146 Bytes
speakerStats.py
849 Bytes
cacheLinuxWords.py
1.3 kB
classifierPrecRec.py
1.5 kB
classifierTest.py
2.7 kB
conditionalFeatures.py
9.8 kB
conditionalFeatures.pyc
11.9 kB
greedy.py
1.8 kB
system.annot
59.3 kB
techTerm.py
1.8 kB
techTerm.pyc
2.8 kB
unigramStats.py
855 Bytes
preprocess
stripChat.py
2.6 kB
typescript
16.8 kB
utils
AIMA.py
23.0 kB
AIMA.pyc
39.8 kB
ClusterMetrics.py
10.3 kB
ClusterMetrics.pyc
14.9 kB
Probably.py
7.4 kB
Probably.pyc
9.6 kB
grouper.py
2.0 kB
grouper.pyc
3.2 kB
path.py
32.0 kB
path.pyc
38.0 kB
pyung.py
6.2 kB
waterworks
Dictionaries.py
1.5 kB
Files.py
10.2 kB
Processes.py
4.2 kB
Processes.pyc
5.1 kB
Sequences.py
3.7 kB
Streams.py
1.4 kB
Strings.py
2.8 kB
Tools.py
5.1 kB
Tools.pyc
9.0 kB
__init__.py
0 Bytes
__init__.pyc
212 Bytes
viewer
ChatPane.java
11.5 kB
ChatView.java
5.1 kB
Line.java
2.3 kB
ThreadWatcher.java
4.2 kB
intro.txt
4.3 kB
postprocessing
revert_preprocessing.py
1.5 kB
preprocessing
names.txt
300.4 kB
preprocessChat.py
5.1 kB
randomforest
doRandomForest.py
2.4 kB
sample_model
2.0 kB
run_disentanglement.sh
3.1 kB