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\nclusters obtained in an unsupervised manner from Twitter profiles. These clusters may be useful for other natural language processing tasks in social media.

社会角色是一种特定的人口统计学特征，涵盖职业、休闲、社区及家庭角色。我们构建了一个全新的标注数据集，用于从英文Twitter个人资料中检测社会角色的任务。该数据集包含约1000个标注有社会角色的Twitter个人资料。此外，我们还发布了一组从Twitter个人资料中通过无监督方式获得的词簇。这些词簇可能对社交媒体中的其他自然语言处理任务有所帮助。