S
Swapna Somasundaran
Researcher at Princeton University
Publications - 43
Citations - 2264
Swapna Somasundaran is an academic researcher from Princeton University. The author has contributed to research in topics: Narrative & Automatic summarization. The author has an hindex of 18, co-authored 42 publications receiving 2124 citations. Previous affiliations of Swapna Somasundaran include Siemens & Educational Testing Service.
Papers
More filters
Proceedings ArticleDOI
OpinionFinder: A System for Subjectivity Analysis
Theresa Wilson,Paul Hoffmann,Swapna Somasundaran,Jason S. Kessler,Janyce Wiebe,Yejin Choi,Claire Cardie,Ellen Riloff,Siddharth Patwardhan +8 more
TL;DR: OpinionFinder is a system that performs subjectivity analysis, automatically identifying when opinions, sentiments, speculations, and other private states are present in text.
Proceedings Article
Recognizing Stances in Ideological On-Line Debates
Swapna Somasundaran,Janyce Wiebe +1 more
TL;DR: This work constructs an arguing lexicon automatically from a manually annotated corpus and builds supervised systems employing sentiment and arguing opinions and their targets as features, which perform substantially better than a distribution-based baseline.
Proceedings ArticleDOI
Recognizing Stances in Online Debates
Swapna Somasundaran,Janyce Wiebe +1 more
TL;DR: This paper presents an unsupervised opinion analysis method for debate-side classification, i.e., recognizing which stance a person is taking in an online debate, and shows that this method is substantially better than challenging baseline methods.
Proceedings ArticleDOI
Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification
TL;DR: Two diverse global inference paradigms are used: a supervised collective classification framework and an unsupervised optimization framework, which perform substantially better than baseline approaches, establishing the efficacy of the methods and the underlying discourse scheme.
Proceedings Article
Detecting Arguing and Sentiment in Meetings
TL;DR: This paper analyzes opinion categories like Sentiment and Arguing in meetings using genre-specific lexicons and shows that classifiers using lexical and discourse knowledge have significant improvement over baseline.