Probabilistic Community using Link and Content for Social Networks

Project Discription

Social media are platforms that allow common persons to create and publish contents. Two worldwide popular social media websites, Twitter and Facebook, demonstrate its explosive growth and profound influence. Both Twitter and Facebook are in the top 10 most-visited websites in the world according to Alexa ranking [1]. Facebook has more than 800 million active users [2], and by March 2011, on Twitter, there were about 140 million information pieces created and transferred daily [3]. There is other specialized social media that are focused on entertainment, sports, finance and politics.

Since there are many users sharing their opinions and experiences via social media, there is aggregation of personal wisdom and different viewpoints. Such aggregation has limitations as viewpoints are subject to change with time. In a sense the social media prediction problem is paralleled by prediction of financial time series based on past history, which has its uses in trading.

Whole work is divide into different modules base on the steps of calculation from the user to final output. First include clustering of social user dataset by using genetic algorithm. Then in second phase by utilizing the cluster center from the cluster identification of similar user in other social network was done.

Project Sample Image