SENTIMENT ANALYSIS RELOADED - A Comparative Study on Sentiment Polarity Identification Combining Machine Learning and Subjectivity Features

Ulli Waltinger

2010

Abstract

This paper presents an empirical study on machine learning-based sentiment analysis. Though polarity classification has been extensively studied at different document-structure levels (e.g. document, sentence, words), little work has been done investigating feature selection methods and subjectivity resources. We systematically analyze four different English subjectivity resources for the task of sentiment polarity identification. While the results show that the size of dictionaries clearly correlate to polarity-based feature coverage, this property does not correlate to classification accuracy. Using polarity-based feature selection, considering a minimum amount of prior polarity features, in combination with SVM-based machine learning methods exhibits the best performance (acc=84.1, f1=83.9), in comparison to the classical approaches on polarity identification. Based on the findings of the English-based experimental setup, a new German subjectivity resource is proposed for the task of German-based sentiment analysis. The results of the experiments show, with f1=85.9 its good adaptability to the new domain.

Paper Citation

in Harvard Style

Waltinger U. (2010). SENTIMENT ANALYSIS RELOADED - A Comparative Study on Sentiment Polarity Identification Combining Machine Learning and Subjectivity Features . In Proceedings of the 6th International Conference on Web Information Systems and Technology - Volume 1: WEBIST, ISBN 978-989-674-025-2, pages 203-210. DOI: 10.5220/0002772602030210

in Bibtex Style

@conference{webist10,
author={Ulli Waltinger},
title={SENTIMENT ANALYSIS RELOADED - A Comparative Study on Sentiment Polarity Identification Combining Machine Learning and Subjectivity Features},
booktitle={Proceedings of the 6th International Conference on Web Information Systems and Technology - Volume 1: WEBIST,},
year={2010},
pages={203-210},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002772602030210},
isbn={978-989-674-025-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Web Information Systems and Technology - Volume 1: WEBIST,
TI - SENTIMENT ANALYSIS RELOADED - A Comparative Study on Sentiment Polarity Identification Combining Machine Learning and Subjectivity Features
SN - 978-989-674-025-2
AU - Waltinger U.
PY - 2010
SP - 203
EP - 210
DO - 10.5220/0002772602030210