Collaboration and Conflict in Online Communities

Data science capstone domain of inquiry (DSC 180AB B04)

Developed by Keng-Chi Chang, Aaron Fraenkel, Molly Roberts


This domain will investigate collaboration and conflict in online communities. We will primarily be looking into behaviors on wikipedia; its open-source culture and heavy usage make it an ideal subject of study.


What constitutes successful collaboration on an online platform? Is it production of quality content by those of the community? How is it related to engagement with the platform? How are these concepts quantified?


What constitutes conflift on an online platform? Does it necessarily impede collaboration? How do certain conflicts interact with the power structures of the online community (and any surrounding communities)? How to conflicts play out among certain sub-populations? How are all these concepts quantified?

You will be strongly encouraged to pursue a Quarter-2 project that studies the same data source (Wikipedia data), as such data typically takes a lot of time to wrangle/understand.

Result replication (introduction to topic)

We will delve into this area via the following primary paper:

Here, we will follow the authors’ exploration into wikipedia edit wars, study their definition of a statistic that encodes conflict, and critically examine their claims. Beyond this specific paper, we will study an extension of this result and responses to these claims:

The latter-half of Quarter 1 will introduce you to other topics to inform possible avenues for further research:

  • possible applications of NLP to ask related questions in the area,
  • descriptions of other online platforms that could support similar questioning.

Section Participation

Participation in the weekly discussion section is mandatory. Each week, you are responsible for doing the reading/task assigned in the schedule. Come to section prepared to ask questions about and discuss the results of these tasks.

Each week, turn in answers to the weekly questions to Canvas. These questions are meant to focus your work for the week and help prepare you for discussion. If you have questions about your work, please ask them in section or office hours (I will rarely comment on your submission).

You are responsible for the entire weekly reading/task, even if portions are not covered in the weekly questions. The weekly tasks are the building blocks for the project proposals/assignments due at the end of the quarter.


Week Topic
1 Introduction
2 Wikipedia Edit Data
3 Measuring “Conflict” and “Collaboration”
4 EDA and the M-Statistic
5 Results and Shortcomings
6 “Even Good Bots Fight”
7 Ext #1
8 Ext #2
9 Ext #3
10 Present Proposals

Office Hours

Fridays 10-11AM