Controversy Trend Detection in Social Media

Web Mining is the retrieval of useful information from web. The information exchanged in social network posts includes not only text but also images, URLs, and videos. This system focuses on mentions of users – links between users that are generated through replies, mentions, and re-tweets. The probability model is proposed to detect the emergence of a new topic from the anomalies measured through the model. The technique demonstrated on dataset which are gathered from twitter. Aggregating anomaly scores from hundreds of users, shows that detecting emerging topics only based on the reply/mention relationships in social network posts. The experiments show that the proposed mention-anomaly-based approaches can detect new topics at least as early as text-anomaly-based approaches.