I Wish I Didn't Say That! Analyzing and Predicting Deleted Messages in Twitter
This addresses the issue of understanding user behavior and content removal on social media platforms, which is incremental as it focuses on a previously unconsidered aspect of Twitter data.
The paper tackled the problem of predicting and analyzing deleted tweets on Twitter, showing that deletions can be automatically predicted ahead of time and identifying which tweets are likely to be deleted and how.
Twitter has become a major source of data for social media researchers. One important aspect of Twitter not previously considered are {\em deletions} -- removal of tweets from the stream. Deletions can be due to a multitude of reasons such as privacy concerns, rashness or attempts to undo public statements. We show how deletions can be automatically predicted ahead of time and analyse which tweets are likely to be deleted and how.