Machine Learning
The complex dynamics of collaborative tagging
Proceedings of the 16th international conference on World Wide Web
Detecting splogs via temporal dynamics using self-similarity analysis
ACM Transactions on the Web (TWEB)
The recurrence dynamics of social tagging
Proceedings of the 18th international conference on World wide web
The singularity is not near: slowing growth of Wikipedia
Proceedings of the 5th International Symposium on Wikis and Open Collaboration
Hi-index | 0.00 |
This paper presents research relevant to predicting future editing by Wikipedia editors. We demonstrate the importance of each characteristic and attempt to clarify the characteristics that affect prediction. Clarifying this can help the Wikimedia Foundation (WMF) understand the editor's actions. This research adopted the increase in prediction errors as the means of evaluating the importance of a characteristic and thus computed the importance of each characteristic. We used random forest (RF) regression for calculating the importance. Characteristic evaluation in our experiment revealed that the past number of edits and the editing period increased predictive accuracy. Furthermore, information regarding earlier edit actions clearly contains factors that determine future edit actions.