Wikipedia Vandal Early Detection: from User Behavior to User Embedding
This addresses the issue of maintaining Wikipedia's integrity by enabling early detection of vandals, though it is incremental as it builds on existing user behavior analysis methods.
The paper tackles the problem of detecting vandals on Wikipedia by using deep learning to model user edit histories, resulting in a method that dynamically updates user embeddings to predict vandalism with improved accuracy.
Wikipedia is the largest online encyclopedia that allows anyone to edit articles. In this paper, we propose the use of deep learning to detect vandals based on their edit history. In particular, we develop a multi-source long-short term memory network (M-LSTM) to model user behaviors by using a variety of user edit aspects as inputs, including the history of edit reversion information, edit page titles and categories. With M-LSTM, we can encode each user into a low dimensional real vector, called user embedding. Meanwhile, as a sequential model, M-LSTM updates the user embedding each time after the user commits a new edit. Thus, we can predict whether a user is benign or vandal dynamically based on the up-to-date user embedding. Furthermore, those user embeddings are crucial to discover collaborative vandals.