TweetPaper: Classification and Trend Detection in Twitter via Joint Complexity

In this paper we present TweetPaper, which is a visualization tool for classification and trend detection in real time. It is based on Joint Complexity, which gives a similarity measure between two texts or sequences. We analyze a sequence in subcomponents using Suffix Trees, which come with a simple, fast and low complexity method to store and recall them from memory, especially for short sequences, and it is significantly different than standard bag-of-words methods.