A Latent Space Analysis of Editor Lifecycles in Wikipedia
This addresses the challenge of sustaining collaborative communities like Wikipedia by providing insights into editor lifecycles, though it is incremental as it applies existing topic analysis methods to this domain.
The paper tackles the problem of high editor turnover in Wikipedia by analyzing editor activity patterns over time using a latent space representation, revealing that this representation can predict editor departure and showing that long-term editors gradually diversify their participation while short-term editors have more random and fluctuated behavior.
Collaborations such as Wikipedia are a key part of the value of the modern Internet. At the same time there is concern that these collaborations are threatened by high levels of member turnover. In this paper we borrow ideas from topic analysis to editor activity on Wikipedia over time into a latent space that offers an insight into the evolving patterns of editor behavior. This latent space representation reveals a number of different categories of editor (e.g. content experts, social networkers) and we show that it does provide a signal that predicts an editor's departure from the community. We also show that long term editors gradually diversify their participation by shifting edit preference from one or two namespaces to multiple namespaces and experience relatively soft evolution in their editor profiles, while short term editors generally distribute their contribution randomly among the namespaces and experience considerably fluctuated evolution in their editor profiles.