Abstract

This paper presents Q-WordNet, a lexical resource consisting of WordNet senses automatically annotated by positive and negative polarity. Polarity classification amounts to decide whether a text (sense, sentence, etc.) may be associated to textit{positive} or textit{negative} connotations. Polarity classification is becoming important for applications such as Opinion Mining and Sentiment Analysis, which facilitates the extraction and analysis of opinions about commercial products, on companies reputation management, brand monitoring, or to track attitudes by mining online forums, blogs, etc. Inspired by work on classification of word senses by polarity (e.g., SentiWordNet), and taking WordNet as a starting point, we build Q-WordNet. Instead of applying external tools such as supervised classifiers to annotate WordNet synsets by polarity, we try to effectively maximize the linguistic information contained in WordNet, thereby taking advantage of the human effort undertaken by lexicographers and annotators. The resulting resource, Q-WordNet, is a subset of WordNet senses classified as positive and negative. In this approach, emph{neutral polarity} is seen as the absence of positive or negative polarity. The evaluation of Q-WordNet shows an improvement with respect to previous similar resources. We believe that Q-WordNet can be used as a starting point for data-driven approaches in Sentiment Analysis.

BIB_text

@Article {
author = {Rodrigo Agerri and Ana García-Serrano},
title = {Q-WordNet: Extracting Polarity from WordNet Senses},
pages = {2300-2305},
keywds = {
Lexical Resources, Sentiment Analysis, Computational Linguistics
}
abstract = {
This paper presents Q-WordNet, a lexical resource consisting of WordNet senses automatically annotated by positive and negative polarity. Polarity classification amounts to decide whether a text (sense, sentence, etc.) may be associated to textit{positive} or textit{negative} connotations. Polarity classification is becoming important for applications such as Opinion Mining and Sentiment Analysis, which facilitates the extraction and analysis of opinions about commercial products, on companies reputation management, brand monitoring, or to track attitudes by mining online forums, blogs, etc. Inspired by work on classification of word senses by polarity (e.g., SentiWordNet), and taking WordNet as a starting point, we build Q-WordNet. Instead of applying external tools such as supervised classifiers to annotate WordNet synsets by polarity, we try to effectively maximize the linguistic information contained in WordNet, thereby taking advantage of the human effort undertaken by lexicographers and annotators. The resulting resource, Q-WordNet, is a subset of WordNet senses classified as positive and negative. In this approach, emph{neutral polarity} is seen as the absence of positive or negative polarity. The evaluation of Q-WordNet shows an improvement with respect to previous similar resources. We believe that Q-WordNet can be used as a starting point for data-driven approaches in Sentiment Analysis.
}
isbn = {2-9517408-6-7},
date = {2010-05-19},
year = {2010},
}