Wikipedia Vandal Early Detection: From User Behavior to User Embedding
Document Type
Conference Proceeding
Publication Date
2017
Keywords
Usual embedding, US edition, vandalism detection, benign users, state reverts
Abstract
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. Code and data related to this chapter are available at: https://bitbucket.org/bookcold/vandal_detection.
Citation
Yuan S., Zheng P., Wu X., Xiang Y. (2017) Wikipedia Vandal Early Detection: From User Behavior to User Embedding. In: Ceci M., Hollmén J., Todorovski L., Vens C., Džeroski S. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2017. Lecture Notes in Computer Science, vol 10534. doi: https://doi.org/10.1007/978-3-319-71249-9_50
Comments
Principal Investigator: Xintao Wu
Acknowledgements: The authors acknowledge the support from the 973 Program of China (2014CB340404), the National Natural Science Foundation of China (71571136), and the Research Projects of Science and Technology Commission of Shanghai Municipality (16JC1403000, 14511108002) to Shuhan Yuan and Yang Xiang, and from National Science Foundation (1564250) to Panpan Zheng and Xintao Wu. This research was conducted while Shuhan Yuan visited University of Arkansas.