Extracting topics based on authors, recipients and content in microblogs

Abstract

Microblogs such as Twitter are important sources for spreading vital information at high speed. They also reflect the general people's reaction and opinion towards major events or stories. With information traveling so quickly, it is helpful to be able to apply unsupervised learning techniques to discover topics for information extraction and analysis. Although graphical models have been traditionally used for topic discovery in microblogs and text streams, previous work may not be as efficient because of the diverse and noisy nature of microblogs. In this paper, we demonstrate the application of the Author-Topic and the Author-Recipient-Topic model to microblogs. We extensively compare these models under different settings to an LDA baseline. Our results show that the Author-Recipient-Topic model extracts the most coherent topics establishing that joint modeling on author-recipient pairs and on the content of tweet leads to quantitatively better topic discovery. This paper also addresses the problem of topic modeling on short text by using clustering techniques. This technique helps in boosting the performance of our models. Our study reveals interesting traits about Twitter messages, users and their interactions.