wea_ondara/master
1
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

wip

Browse Source
This commit is contained in:
wea_ondara
2020-05-19 15:40:34 +02:00
parent 8f4cf7412f
commit 1f48374408
2 changed files with 11 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
text/3_method.tex
View File

@@ -48,7 +48,7 @@ ITS relies on linear regression and tries to fit a three-segment linear function
\begin{figure}
\centering\includegraphics[scale=0.7]{figures/itsexample}
\caption{An example that visualizes how ITS works. The change of the system occurs at month 0. The blue line shows the average sentiment of fictional answers grouped by month. The numbers attached to the blue line show the number of sentiment values for a given month. The yellow line represents the ITS analysis as a three-segment line.}
\caption{An example that visualizes how ITS works. The change of the system occurs at month 0. The blue line shows the average sentiment of fictional answers grouped by month. The numbers attached to the blue line show the number of sentiment values for a given month. The yellow line represents the ITS analysis as a three-segment line. This exmaple shows the expected behavior of the data sets in the following sections.}
\label{itsexample}
\end{figure}

14
text/6_discussion.tex
View File

@@ -4,7 +4,8 @@ The ITS analysis of the investigated communities show mixed results. Some commun
The other communities do not seem to profit from the change directly. ServerFault is an example where the change does not have a significant impact. The sentiment rises gradually prior to the change, jumps upward by a small value when the change ist introduced and the sentiment is falling slowly thereafter. The data does not inidicate a significant rise or fall in the average sentiment, so this community seem to be largly unaffected by the change. MathOverflow, math.stackexchange.com, and electronics.stackexchange.com show similar results. The average sentiment stay constant on MathOverflow and are falling for math.stackexchange.com and electronics.stackexchange.com. After the change these communities see a decrease in sentiment. These communities seem to not profit from the change. However math.stackexchange.com has group below average sentiment values at the end which could be a result from another unknown influence. Also the average sentiment on electronics.stackexchange.com seem to recover after about 12 months and future data is required to see if the rise in the end is a long term trend. SuperUser shows a really odd pattern. The average sentiment is stable prior to the change and decreased dramatically shortly afterward. However the sentiment recovers after 12 months. The ITS model chosen in this thesis is not able to capture the apparent pattern. Future data will be necessary to see if the sentiment recovers long term.
%so only community that shows a clear improvement when comapred to prior to change sentiment
% similarities in results and differences
% so: only community that shows a clear improvement when comapred to prior to change sentiment
% mse not really changing, downward trend before and after, probably to the low last 5 values, its does not say much
% mo: sentiments largely the same before and after, regression falling due to how its works, its does not say much
% au: show intresting zigzag pattern: falling then gradually rising
@@ -15,13 +16,18 @@ The other communities do not seem to profit from the change directly. ServerFaul
% tex: sentiments took up a bit after the change; change seems to works
% unix: sentiments falling prior but gainig after; change seems to work
By and large, the change introduced by the StackExchange team has a clear positive effect on the average sentiment of half of the investigated communities. Two of the communities have a delayed temporary decrease in sentiment which recovers after about 12 months. The selected ITS model is not designed to capture the sentiment pattern of these communities. For the other three communities the ITS analysis does not show a significant change in the sentiment trend.
% similarities in results and differences
% expectations from before the experiment and how they match with results
% interesting single results? maybe strong dip in maths sites
% did change from SE produce the desired results?
% as expected #answers per month vary greatly
Some investigated data sets show intresting patterns. StackOverflow shows the clearest results of all the investigated communities and closely resembles the example ITS shown in section 3. The result matches the expectations and shows that the change introduced by the StackExchange team works well for this community. The AskUbuntu community shows interesting zig-zag pattern where sentiment gradually rises over time and then falls apruptly.
% interesting single results?
The average sentiment of the StackOverflow community is the most stable in terms of deviation from the regression. This is expected as StackOverflow is the largest community by far and has the most questions created by new comers. On the other hand MathOverflow is the sparsed community and has the least amount questions from new contributors. The level of the average sentiment also varies greatly between communities. stats.stackexchange.com has the highest level of average sentiment compared to the other communities, whereas, tex.stackexchange.com has the lowest level average sentiment. Also, in every community the number of questions from new contributors slowly decreases over time. This may be a result of the filling of gaps in the knowledge repository over time.
% as expected #answers per month vary greatly -> mabye into data sets section
% some communties have a high average sentiment compared to others
% mathoverflow very sparse, stackoverflow densest obviously as biggets community 100x more users
% fewer questions by new users over time? + explaination