I passed my PhD examination in August, 2014.
 I joined IBM Research Australia in April, 2014. 
 This website will not be updated. Please go to my new homepage.

I obtained my PhD in the Department of Computing and Information System at the University of Melbourne, and I am also a NICTA-sponsored student in Victoria Lab. I am lucky to be advised by Tim Baldwin and Paul Cook. For more information, see my yearly updated resume.

A tweet-length summary of my research: 
U wanto undrstnd TWEETS lik dis? Make them readable like this; and if there are too many to read, select those from a region.

A summary of my research:
My PhD research topic is Improving the Utility of Social Media Data with Natural Language Processing. In particular, I worked on Twitter text normalisation and geolocation prediction. My research aims to practise a "divide and conquer" paradigm for the huge amount of Twitter data. On "conquer the noise", lexical normalisation converts various non-standard words to their canonical forms in social media, e.g., 4eva ("forever"). By doing so, the normalised data is expected to be more accessible to existing NLP tools and downstream application. As for "divide the data", geolocation prediction enables data partition by locations. It makes location-based applications feasible (e.g., local event detection, regional sentiment analysis) and avoids dealing with massive irrelevant data.




Locations of visitors to this page