Conversation Analysis on Social Networking Sites

With the explosion of Web 2.0, people are becoming more communicative through expansion of services and multi-platform applications such as micro blogs, forums and social networks which establishes social and collaborative backgrounds. These services can be seen as very large information repository containing millions of text messages usually organized into complex networks involving users interacting with each other at specific times. Several works focused only to retrieve separate tweets or those sharing same hash tags, but, it is not powerful enough if the goal of the search is to retrieve relevant tweets based on content. In addition, finding good results concerning the given subjects needs to consider the entire context. However, context can be derived from user interactions. In this work, we propose a new method to retrieval conversation on micro blogging sites. It's based on content analysis and content enrichment. The goal of our method is to present a more informative result compared to conventional search engine. To valid our method, we developed the TCOND system (Twitter Conversation Detector) which offers an alternative, results to keyword search on twitter and Google. We have evaluated our method on collected social network corpus related to specific subjects, and we obtained good results.