webLyzard Publications

A Context-Dependent Supervised Learning Approach to Sentiment Detection in Large Textual Databases

Weichselbraun, Albert and Gindl, Stefan and Scharl, Arno (2010) A Context-Dependent Supervised Learning Approach to Sentiment Detection in Large Textual Databases. Journal of Information and Data Management, 1 (3). pp. 329-342. ISSN 2178-7107

[thumbnail of A Context-Dependent Supervised Learning Approach to Sentiment Detection in Large Textual Databases]
Preview
PDF (A Context-Dependent Supervised Learning Approach to Sentiment Detection in Large Textual Databases) - Published Version
797kB

Official URL: http://seer.lcc.ufmg.br/index.php/jidm

Abstract

Sentiment detection automatically identifies emotions in textual data. The increasing amount of emotive documents available in corporate databases and on the World Wide Web calls for automated methods to process this important source of knowledge. Sentiment detection draws attention from researchers and practitioners alike - to enrich business intelligence applications, for example, or to asure the impact of customer reviews on purchasing decisions. Most sentiment detection approaches do not consider language ambiguity, despite the fact that one and the same sentiment term might differ in polarity depending on the context, in which a statement is made. To address this shortcoming, this paper introduces a novel method that uses Naïve Bayes to identify ambiguous terms. A contextualized sentiment lexicon stores the polarity of these terms, together with a set of co-occurring context terms. A formal evaluation of the assigned polarities confirms that considering the usage context of ambiguous terms improves the accuracy of high-throughput sentiment detection methods. Such methods are a prerequisite for using sentiment as a metadata element in storage and distributed file-level intelligence applications, as well as in enterprise portals that provide a semantic repository of an organization's information assets.

Item Type:Article
Uncontrolled Keywords:annotation, document enrichment, machine learning, natural language processing, sentiment
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
ID Code:25
Deposited By: Dr Albert Weichselbraun
Deposited On:07 Oct 2010 11:16
Last Modified:07 Oct 2010 11:16

Repository Staff Only: item control page