My name is Kavita Ganesan. I received my Ph.D from the University of Illinois at Urbana Champaign specializing in Text Mining, NLP, Machine Learning and Information Retrieval. Over the years, I have worked on a variety of text mining  and retrieval problems including sentiment analysis, text summarization, text clustering, document segmentation, entity retrieval, web crawling, topic extraction and recommendations engine. My expertise is in translating research or new conceptual ideas into practical systems as well as building out models/solutions that generalize and scale in production environments. Most of the systems I have developed have been from ground up, starting from actually sourcing data needed for analysis up to optimizing and parallelizing algorithms for scalability.

At present, I am working on Text Mining problems at GitHub. In my most recent project there, I developed the algorithm for auto-suggesting topics for millions of GitHub Repositories. I am also an active contributor for RxNLP where I developed some of the algorithms for sentence clustering and topics extraction. During my Ph.D years, I developed the FindiLike system and the algorithms behind it including several opinion summarizers (Opinosis - Graph Driven Text Summarizer, Micropinion Generation), opinion based entity retrieval (OpinRank) and algorithms for vertical crawling (OpinoFetch).

If you are interested in reading my publications you can find them on Google Scholar or my website

To get in touch with me, please use my I am also available on LinkedIn