DICTIONARY EXTENSION FOR IMPROVING AUTOMATED SENTIMENT DETECTION

Johannes Liegl, Stefan Gindl, Arno Scharl, Alexander Hubmann-Haidvogel

2010

Abstract

This paper investigates approaches to improve the accuracy of automated sentiment detection in textual knowledge repositories. Many high-throughput sentiment detection algorithms rely on sentiment dictionaries containing terms classified as either positive or negative. To obtain accurate and comprehensive sentiment dictionaries, we merge existing resources into a single dictionary and extend this dictionary by means of semisupervised learning algorithms such as Pointwise Mutual Information - Information Retrieval (PMI-IR) and Latent Semantic Analysis (LSA). The resulting extended dictionary is then evaluated on various datasets from different domains, which were annotated on both the document and sentence level.

Download


Paper Citation


in Harvard Style

Liegl J., Gindl S., Scharl A. and Hubmann-Haidvogel A. (2010). DICTIONARY EXTENSION FOR IMPROVING AUTOMATED SENTIMENT DETECTION . In Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2010) ISBN 978-989-8425-28-7, pages 404-407. DOI: 10.5220/0003070304040407

in Bibtex Style

@conference{kdir10,
author={Johannes Liegl and Stefan Gindl and Arno Scharl and Alexander Hubmann-Haidvogel},
title={DICTIONARY EXTENSION FOR IMPROVING AUTOMATED SENTIMENT DETECTION},
booktitle={Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2010)},
year={2010},
pages={404-407},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003070304040407},
isbn={978-989-8425-28-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval - Volume 1: KDIR, (IC3K 2010)
TI - DICTIONARY EXTENSION FOR IMPROVING AUTOMATED SENTIMENT DETECTION
SN - 978-989-8425-28-7
AU - Liegl J.
AU - Gindl S.
AU - Scharl A.
AU - Hubmann-Haidvogel A.
PY - 2010
SP - 404
EP - 407
DO - 10.5220/0003070304040407