Anger Management: Using Sentiment Analysis to Manage Online Communities

As online communities grow and user generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to encourage appropriate, socio-normative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments are a particularly strong boundary to participation. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows this task becomes more daunting. In this paper, we introduce an approach to automatic detection of inappropriate negative user contributions. We apply sentiment analysis techniques to the task of classifying short comments about news stories, a challenge due to the lack of context in the short comments. In combination with relevance detection techniques, this work will inform a hybrid community management system by automatically flagging off-topic and hostile comments.