Realizing Emergent Topics in Twitter by Detection of Abnormality Links

Abstract

In the present paper, we demonstrated the probability model which may capture the usual mentioning behavior of an end user consisting of both the number of mentions for every post and the frequency of users occurring in the mentions. Subsequently, to compute the anomaly of future user behavior this model is needed. While using the proposed probability model, we can quantitatively compute the originality or probable effect of a post resembled in the mentioned behavior of the end user. We aggregate all the anomaly scores obtained in this way above countless end users. The efficiency of the proposed method is demonstrated on four data sets we have obtained through Twitter. We demonstrated that the mention-anomaly-based method combined with the TFIDF method can detect the emergence of a new topic at least as quickly as text-anomaly-based counterparts.