RevRank: A Fully Unsupervised Algorithm for Selecting the Most Helpful Book Reviews

Authors

  • Oren Tsur The Hebrew University
  • Ari Rappoport The Hebrew University

Keywords:

review ranking, review helpfulness, content analysis, information systems applications

Abstract

We present an algorithm for automatically ranking user-generated book reviews according to review helpfulness. Given a collection of reviews, our RevRank algorithm identifies a lexicon of dominant terms that constitutes the core of a virtual optimal review. This lexicon defines a feature vector representation. Reviews are then converted to this representation and ranked according to their distance from a "virtual core" review vector. The algorithm is fully unsupervised and thus avoids costly and error-prone manual training annotations. Our experiments show that RevRank clearly outperforms a baseline imitating the Amazon user vote review ranking system.

Downloads

Published

2009-03-19

How to Cite

Tsur, O., & Rappoport, A. (2009). RevRank: A Fully Unsupervised Algorithm for Selecting the Most Helpful Book Reviews. Proceedings of the International AAAI Conference on Web and Social Media, 3(1), 154-161. Retrieved from https://ojs.aaai.org/index.php/ICWSM/article/view/13945