Hi வணக்கம் ! I am a PhD student at MIT Media lab where I work in the Laboratory of Social Machines group with Deb Roy.
I enjoy exploring novel approaches to tackle real-world problems through the lens of AI (deep learning, natural language processing & computer vision). I'm interested in developing and applying different learning methods to data (including multi-modal data) from different domains such as social media, news, personal and non-fictional narratives, movie dialogues, etc.
Recently, my research is focused on two broad themes: (a) uncovering latent semantic information from natural language for text understanding and generation, and (b) enabling AI systems to develop social intelligence i.e.
learning to empower AI systems to better model, understand and reason about human behaviour (persona modeling, mental state representation, common sense reasoning, theory of mind).
Projects
Lifelong Social Event Representation
Model Motives & Emotions from Personal Narratives
DAPPER: Domain-adapted Persona Representation
Generating Aversarial Examples for Text Classifiers
Learning Personas from Dialogue
Video SemNet: Memory-Augmented Network
Content Consistent Style Transfer
Tweet2vec: Learning Tweet Embeddings
Deep Multi-modal Multi-task Learning
DeepSpace: Mood-based Texture Generation
Auris:Creating Affective Virtual Spaces from Music
Identification of Representative Content on Twitter
Categorization of Election-related Tweets
TweetVista: AI Tool for Exploring conversations
Handwritten Tamil Recognition
Publications
Selected Press
- Washington Post: Twitter's political debate focuses on much different issues than Americans at large do
- Washington Post: How the Orlando attack showed the potential of an October Surprise
- Washington Post: Twitter users definitely see the Supreme Court vacancy as an election issue
- PRI: Just how uncivil is Election 2016? MIT's Media Lab has some charts you should see.
- New York Times: How to Escape Your Political Bubble for a Clearer View
- NPR: Tech Creates Our Political Echo Chambers. It Might Also Be A Solution
- Recode: This Chrome add-on lets you see Twitter through the eyes of other users
- Mashable: MIT-designed Chrome extension fixes your Twitter filter bubble
- The Outline: MIT released a tool that uses real people's Twitter feeds to show you the "other side"
Resume
MIT Media LabPhD Candidate: 2016-Now
Twitter Inc. Summer Intern: 2017
MIT Media LabMaster's Student: 2014-2016
Groupon India Pvt. Ltd.Software Development Engineer: 2013-2014
Media.net Software Development Engineer: 2012-2013
Anna University, India B.E. (Computer Science): 2008-2012
View Resume