Rowe, Matthew, Sofia Angeletou, and Harith Alani. "Anticipating discussion activity on community forums." 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third International Conference on Social Computing. IEEE, 2011.

This paper addresses the challenge of predicting popular posts on the Social Web to help analysts focus on influential content. The study presents a two-step approach to anticipate discussions in community forums: identifying seed posts that generate discussions and predicting the length of these discussions. By exploring various features, including user and content features, the research finds that content features are better predictors for identifying seed posts, achieving an F1 value of 0.792. For predicting discussion activity, there is a positive correlation between user focus and discussion volumes, with an nDCG@1 value of 0.89 achieved using user features.