Jump to content

Grants:IdeaLab/Sentiment analyses (big data / AI)

From Meta, a Wikimedia project coordination wiki
Sentiment analyses (big data / AI)
Use established big data techniques to measure changes in community health metrics such as user happiness, anxiety levels and conflict intensity.
themesocial factors
contact email• feyd.huxtable@yahoo.co.uk
idea creator
this project needs...
project manager
created on17:39, 21 July 2018 (UTC)

Project idea[edit]

What Wikimedia project(s) and specific areas will you be evaluating?[edit]

Is this project measuring a specific space on a project (e.g. deletion discussions), or the project as a whole?
English Wikipedia. Could be narrowed to specific spaces or widened to other languages.

Describe your idea. How might it be implemented?[edit]

Provide details about the method or process of how you will evaluate your community or collect data. Does your idea involve private or personally identifying information? Take a look at the Privacy Policy for Wikimedia’s guidelines in this area.
1) Establish a partnership with a 3rd party who has the needed analytical skills. This could be a university (e.g. Warwick ) or maybe one of the big PR agencies. (This hasn't been widely reported, but the big agencies seem to have more developed skills for this sort of work than anyone in academia, they are charging huge fees to do similar analyses for large corporates. For Wikipedia they might be willing to enter a public partnership at a much reduced fee.) 2) Create the required data set along with a feed to keep it updated. It would include all talk & project page posts, together with timestamps, with authorship anonymised. 4.) Produce reports showing the trends in community health metrics like happiness, anxiety, collaborativeness , conflict intensity etc. 5.) Set up a dashboard so the foundation (and possibly regular editors) can set up custom reports, possibly even calibrating the analyses parameters.

Are there experienced Wikimedians who can help implement this project?[edit]

If applicable, please list groups or usernames of individuals who you can work with on this project, and what kind of work they will do.
This project might best be overseen by WMF staff and delivered primarily by the chosen partner.

How will you know if this project is successful? What are some outcomes that you can share after the project is completed?[edit]

Early outputs would be the reports tracking community health from 2001 to now.

How would your measurement idea help your community make better decisions?[edit]

After you are finished measuring or evaluating your Wikimedia project, how do you expect that information to be used to benefit the project?
Compared to currently available holistic metrics, the output of this project would provide a much greater degree of actionable intelligence and insight into the factors effecting community health. Over the last 10 years, the number of people with an internet connection has almost tripled, yet the number of active editors has fallen. But it's hard to infer causality from possible on wiki causes, like the sharp decline in admin promotions, along with the resulting concentration of power and inevitable increase in admin abuse. It’s hard to disentangle external influences like the pull on active editors from other platforms, like Facebook, Tencent etc. With the sentiment analyses the impact of both adverse and positive trends would be more visible. Also, there would be a more accurate real time measure of how short-term changes are received (e.g. like an improved UX). If you relay on feedback from users, there will be negativity and selection bias, which could be avoided with the sentiment analyses. Could be especially useful for example in evaluating the impact of a major UX change designed to promote collaboratives and attract diversity with well chosen aesthetics.

Do you think you can implement this idea? What support do you need?[edit]

Do you need people with specific skills to complete this idea? Are there any financial needs for this project? If you can’t implement this project, can you scale down your project so it is doable?
Yes, but may be better if WMF staff run the project. This is leading edge stuff, and any enterprise architect or programme manager should jump at the chance to run it.

Get Involved[edit]

About the idea creator[edit]

10 years English Wiki experience


  • Volunteer I'm not an expert, but I'm very interested in both arguments, community health and Big Data/AI, so if I can help somehow, here I am! I have experience as developer (almost J2EE), relational DB, some SPARQL queries and social media. Camelia (talk) 01:34, 28 July 2018 (UTC)


  • Yes, understand why we are loosing editors and why people don't approach Wikimedia projects is very important to measure the community health. I don't know how we can do this (involving universities is a good idea), but understanding the feelings (hapiness, anxiety, collaborativeness, conflict intensity etc) of wiki editors means understand something about where we need to act. Camelia (talk) 13:52, 22 July 2018 (UTC)
  • Very interesting project, but I imagine difficult to implement. I think it is fundamental to understand why there is a lot of dissatisfaction among users, especially among Wikipedia editors: it would be essential to understand the factors that lead to disaffection and abandonment of projects. Geoide (talk) 09:22, 25 July 2018 (UTC)

Expand your idea[edit]

Would a grant from the Wikimedia Foundation help make your idea happen? You can expand this idea into a grant proposal.

Expand into a Rapid Grant

No funding needed?[edit]

Does your idea not require funding, but you're not sure about what to do next? Not sure how to start a proposal on your local project that needs consensus? Contact Chris Schilling on-wiki at I JethroBT (WMF) (talk · contribs) or via e-mail at cschilling(_AT_)wikimedia.org for help!