Meaning as collective use: predicting semantic hashtag categories on twitter

摘要: This paper sets out to explore whether data about the usage of hashtags on Twitter contains information their semantics. Towards that end, we perform initial statistical hypothesis tests quantify association between patterns and semantics hashtags. To assess utility pragmatic features - which describe how a hashtag is used over time for semantic analysis hashtags, conduct various stream classification experiments compare with lexical features. Our results indicate indeed contain valuable classifying into categories. Although do not outperform in our experiments, argue are important relevant settings textual might be sparse or absent (e.g., social video streams).