Topic Models and their Applications in Social Media Analytics

This talk consists of two parts. In the first part, I will present the dynamic Joint Sentiment-Topic (dJST) model, which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. Three different ways of accounting for such dependency information have been studied. The effectiveness of our proposed model has been verified on the Mozilla add-on reviews crawled in a four-year time period.

In the second part of my talk, I will present our recently proposed Latent Event and Categorisation Model (LECM) which is an unsupervised Bayesian model for the extraction of structured representations of events from Twitter without the use of any labelled data. The extracted events are automatically clustered into coherence event type groups. The proposed framework has been evaluated on over 60 millions tweets and has achieved a precision of 70.49%, outperforming the state-of-the-art open event extraction system by nearly 6%. 

Yulan He is a Reader at Aston University, UK. She obtained her PhD degree in 2004 from the University of Cambridge, UK. Her early research focused on biomedical literature mining and microarray data analysis. Her current research interests lie in the integration of machine learning and natural language processing for social media analysis. Yulan has published over 100 papers in high impact journals and top conferences such as IEEE Transactions on Knowledge and Data Engineering, Information Processing & Management, IEEE Intelligent Systems, KDD, CIKM, ACL, etc. She served as an Area Chair in EMNLP 2015 and co-organised the European Conference in Information Retrieval 2010.