Abstract

Because of T witter's popularity and the viral nature of information dissemination on T witter, predicting which T witter topics will become popular in the near future becomes a task of considerable economic importance. Many T witter topics are annotated by hashtags. In this article, we propose methods to predict the popularity of new hashtags on T witter by formulating the problem as a classification task. We use five standard classification models (i.e., N aïve bayes, k ‐nearest neighbors, decision trees, support vector machines, and logistic regression) for prediction. The main challenge is the identification of effective features for describing new hashtags. We extract 7 content features from a hashtag string and the collection of tweets containing the hashtag and 11 contextual features from the social graph formed by users who have adopted the hashtag. We conducted experiments on a T witter data set consisting of 31 million tweets from 2 million S ingapore‐based users. The experimental results show that the standard classifiers using the extracted features significantly outperform the baseline methods that do not use these features. Among the five classifiers, the logistic regression model performs the best in terms of the M icro‐ F 1 measure. We also observe that contextual features are more effective than content features.