Editing with machine learning: a case study on link recommendations
From Ewan McAndrew
- Kosta Harlan (WMF), software engineer for the Growth Team
- Martin Gerlach (WMF), research scientist for the Research Team
- Marshall Miller (WMF), product manager for the Growth Team
- Morten Warncke-Wang (WMF), staff data scientist for the Growth Team
- Rita Ho (WMF), principal user experience designer, Growth Team
Structured tasks are meant to break down editing tasks into step-by-step workflows that make sense for newcomers and make sense on mobile devices. The Growth team believes that introducing these new kinds of editing workflows will allow more new people to begin participating on Wikipedia, some of whom will learn to do more substantial edits and get involved with their communities. After discussing the idea of structured tasks with communities, we decided to build our first structured task: "add a link". In this talk, we will look at how the Link Recommendation Service was built as a first proof-of-concept to this approach, how its suggestions are incorporated into the editing experience, and how users are interacting with it.Session Outcomes
- Spark discussion around how machine learning can be effectively incorporated into Wikimedia projects.
- Brainstorm ideas for future tasks that would be a good fit for newcomers.