Multi-dimensional Conversation Analysis across Online Social Networks

With the advance of the Internet, ordinary users have created multiple personal accounts on online social networks, and interactions among these social network users have recently been tagged with location information. In this work, we observe user interactions across two popular online social networks, Facebook and Twitter, and analyze which factors lead to retweet/like interactions for tweets/posts. In addition to the named entities, lexical errors and expressed sentiments in these data items, we also consider the impact of shared user locations on user interactions. In particular, we show that geolocations of users can greatly affect which social network post/tweet will be liked/ retweeted. We believe that the results of our analysis can help researchers to understand which social network content will have better visibility.