Detecting Social Roles in Twitter

Social roles are one particular demographic characteristic, which includes work, recreational, community and familial roles. We create a new annotated dataset for the task of detecting social roles from English Twitter profiles. The dataset includes approximately 1,000 Twitter profiles annotated with social roles. In addition, we release a set of word clusters obtained in an unsupervised manner from Twitter profiles. These clusters may be useful for other natural language processing tasks in social media.