Background

harvard

Postdoc, 2016-Present.

Supervisor: Dr. Guergana Savova

Computational Health Informatics Program (CHIP)

My work mainly focuses on developing machine learning models to extract clinically-valuable knowledge (e.g. medical concepts associated with different genres of data, or first-person alcohol drinking content and consumption level) from electronic health records and health-related forum posts.
Keywords: Biomedical Informatics, Machine Learning in Health, Language Modeling, Text Representation

umd

Postdoc, 2014-2016.

Supervisors: Drs. Philip Resnik and Hal Daumé III

Computational Linguistics and Information Processing (CLIP)

I worked on linguistically-aware machine learning models to better represent, predict, and enhance user generated content with applications to churn prediction and sentiment analysis.
Keywords: Representation Learning, Text Representation, Topic Modeling

nus

Ph.D., 2009-2013.

Advisor: Dr. Tat-Seng Chua

Lab for Media Search (LMS)

My PhD work at the National University of Singapore mainly focused on sentiment analysis and live event detection and tracking for organizations and businesses in social media. Several machine learning and optimization algorithms were developed to mine emerging and evolving themes / topics from social media and determine their sentiment.
Keywords: Social Media Analysis, Live Analytics, Event Detection and Tracking, and Sentiment Analysis.

ut

M.Eng., 2005-2008.

Advisors: Drs. Farhad Oroumchian, and Maseud Rahgozar

Database Research Group (DBRG)

My research at the University of Tehran mainly focused on result fusion and semantic retrieval problems in the context of distributed information retrieval systems. I also studied Persian text retrieval and Part-of-Speech tagging. For more info, please refer to Bijbakhan and Hamshahri portals. The Hamshahri collection was used as a benchmark in the Multilingual Textual Document Retrieval task at CLEF 2008 and 2009.
Keywords: Meta-Search, Distributed IR, Result Fusion, Persian Text, Multilingual Text Retrieval.