Research Projects
Tweethood: Location Mining in Online Social Networks 
(Dec '09 - ongoing)
In my present research, we focus on mining both the city level location as well as the micro location of users on Online Social Networks. Apart from the traditional content based location extraction techniques used in blogs, web pages, etc., in social networks we can exploit the social graph of a user to determine his location (and other attributes such as age, ethnicity, language, etc.). We develop algorithms that make use of several crowd sourced gazetteers to understand the unstructured and raw social media text for pin pointing the location associated with a particular user. Please read my research statement for a detailed description of the work.
TWinner: Understanding News Queries with Geo-content using Twitter (Aug '09 - Dec '09)
We examined the application of social media in improving the quality of web search and predicting the news intent of the user. We go one step beyond the previous research by mining social media data, assigning weights to them and determining keywords that can be added to the search query to act as pointers to the existing search engine algorithms suggesting to it that the user is looking for news. We conducted a series of experiments to show the impact that TWinner has on the search results.
MapIt: Smarter Searches using Location Driven Knowledge Discovery and Mining (Jan '09 - Aug '09)
Developed a tool, called MapIt, which takes the Craigslist apartment listings and displays them on Google Maps. MapIt then integrates this functionality with the information collected from location based extraction of various web sources such as the city police blotter which makes apartment searching simpler and faster,helping the user to make a better decision. The research involved identification and disambiguation of location upto the street level in the raw and unstructured text. In addition to this we determine a confidence and accuracy value associated with each apartment.
