Multilingual Feature-Driven Opinion Extraction and Summarization from Customer Reviews

Authors:
Alexandra Balahur;Andrés Montoyo
Affiliations:
Department of Software and Computing Systems, University of Alicante, Spain;Department of Software and Computing Systems, University of Alicante, Spain
Venue:
NLDB '08 Proceedings of the 13th international conference on Natural Language and Information Systems: Applications of Natural Language to Information Systems
Year:
2008

Citing 0
Cited 3

Determining the Polarity and Source of Opinions Expressed in Political Debates

CICLing '09 Proceedings of the 10th International Conference on Computational Linguistics and Intelligent Text Processing
Text summarisation in progress: a literature review

Artificial Intelligence Review
Editorial: COMPENDIUM: A text summarization system for generating abstracts of research papers

Data & Knowledge Engineering

Quantified Score

Hi-index	0.04

Visualization

Abstract

This paper presents a feature-driven opinion summarization method for customer reviews on the web based on identifying general features (characteristics) describing any product, product specific features and feature attributes (adjectives grading the characteristics). Feature attributes are assigned a polarity using on the one hand a previously annotated corpus and on the other hand by applying Support Vector Machines Sequential Minimal Optimization[1] machine learning with the Normalized Google Distance[2]. Reviews are statistically summarized around product features using the polarity of the feature attributes they are described by.