원문정보
보안공학연구지원센터(IJSEIA)
International Journal of Software Engineering and Its Applications
Vol.9 No.9
2015.09
pp.9-18
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
This paper addresses the problem of classifying news headlines into sentiment categories. Using a supervised approach, we train a classifier for classifying each news headline as positive, negative, or neutral. A news headline is considered positive if it is associated with good things, negative if it is associated with bad things, and neutral in the remaining cases. The experiments show an accuracy that ranges from 59.00% to 63.50% when syntactic features (argument1-verb-argument2 relations) are combined with other features. The accuracy ranges from 57.50% to 62.5% when these relations are not used.
목차
Abstract
1. Introduction
2. Related Work
2.1. Text and Sentiment Classification
2.2. Sentiment Classification of News Articles
3. Classifying News Headlines
3.1. Applied Approaches - Overview
3.2. Extracting Argument1-verb-argument2 Relations
4. Experiments and Results
4.1. Datasets
4.2. Sentiment Classification - Evaluation
4.3. Relation Extraction - Evaluation
5. Conclusions
Acknowledgements
References
1. Introduction
2. Related Work
2.1. Text and Sentiment Classification
2.2. Sentiment Classification of News Articles
3. Classifying News Headlines
3.1. Applied Approaches - Overview
3.2. Extracting Argument1-verb-argument2 Relations
4. Experiments and Results
4.1. Datasets
4.2. Sentiment Classification - Evaluation
4.3. Relation Extraction - Evaluation
5. Conclusions
Acknowledgements
References
저자정보
참고문헌
자료제공 : 네이버학술정보