Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics |
| Untertitel | Technical Papers |
| Herausgeber/-innen | Junichi Tsujii, Jan Hajic |
| Seiten | 553-564 |
| Seitenumfang | 12 |
| ISBN (elektronisch) | 9781941643266 |
| Publikationsstatus | Veröffentlicht - Aug. 2014 |
| Extern publiziert | Ja |
| Veranstaltung | 25th International Conference on Computational Linguistics - Dublin, Irland Dauer: 23 Aug. 2014 → 29 Aug. 2014 |
Abstract
Most text classification approaches model text at the lexical and syntactic level only, lacking domain robustness and explainability. In tasks like sentiment analysis, such approaches can result in limited effectiveness if the texts to be classified consist of a series of arguments. In this paper, we claim that even a shallow model of the argumentation of a text allows for an effective and more robust classification, while providing intuitive explanations of the classification results. Here, we apply this idea to the supervised prediction of sentiment scores for reviews. We combine existing approaches from sentiment analysis with novel features that compare the overall argumentation structure of the given review text to a learned set of common sentiment flow patterns. Our evaluation in two domains demonstrates the benefit of modeling argumentation for text classification in terms of effectiveness and robustness.
ASJC Scopus Sachgebiete
- Geisteswissenschaftliche Fächer (insg.)
- Sprache und Linguistik
- Sozialwissenschaften (insg.)
- Linguistik und Sprache
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. Hrsg. / Junichi Tsujii; Jan Hajic. 2014. S. 553-564.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Modeling Review Argumentation for Robust Sentiment Analysis
AU - Wachsmuth, Henning
AU - Trenkmann, Martin
AU - Stein, Benno
AU - Engels, Gregor
PY - 2014/8
Y1 - 2014/8
N2 - Most text classification approaches model text at the lexical and syntactic level only, lacking domain robustness and explainability. In tasks like sentiment analysis, such approaches can result in limited effectiveness if the texts to be classified consist of a series of arguments. In this paper, we claim that even a shallow model of the argumentation of a text allows for an effective and more robust classification, while providing intuitive explanations of the classification results. Here, we apply this idea to the supervised prediction of sentiment scores for reviews. We combine existing approaches from sentiment analysis with novel features that compare the overall argumentation structure of the given review text to a learned set of common sentiment flow patterns. Our evaluation in two domains demonstrates the benefit of modeling argumentation for text classification in terms of effectiveness and robustness.
AB - Most text classification approaches model text at the lexical and syntactic level only, lacking domain robustness and explainability. In tasks like sentiment analysis, such approaches can result in limited effectiveness if the texts to be classified consist of a series of arguments. In this paper, we claim that even a shallow model of the argumentation of a text allows for an effective and more robust classification, while providing intuitive explanations of the classification results. Here, we apply this idea to the supervised prediction of sentiment scores for reviews. We combine existing approaches from sentiment analysis with novel features that compare the overall argumentation structure of the given review text to a learned set of common sentiment flow patterns. Our evaluation in two domains demonstrates the benefit of modeling argumentation for text classification in terms of effectiveness and robustness.
UR - http://www.scopus.com/inward/record.url?scp=84938105825&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84938105825
SP - 553
EP - 564
BT - Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics
A2 - Tsujii, Junichi
A2 - Hajic, Jan
T2 - 25th International Conference on Computational Linguistics, COLING 2014
Y2 - 23 August 2014 through 29 August 2014
ER -