A semantic enhanced approach for online hotspot forums detection

The user generated content on the web grows rapidly in this emergent information age. The evolutionary changes in technology make use of such information to capture only the user´s essence and finally the useful information are exposed to information seekers. In this paper we detect online hotspot forums by computing sentiment analysis for text data available in each forum. This approach analyzes the forum text data and computes sentiment score for each word or phrase of text. Then we propose two text mining approaches like K-means clustering and Support Vector Machine with Particle Swarm Optimization (PSO-SVM) classification algorithms that can be used to group into two forum clusters forming hotspot forums and non-hotspot forums within each time window. The text datasets that we use in our experimental research are collected from forums.digitalpoint.com and after data cleaning they are formatted to 37 different forums and 1616 threads. The experiment helps to identify that K-means and PSO-SVM together achieve highly consistent results.