Loading [MathJax]/jax/output/HTML-CSS/config.js

Sentiment Flow – A General Model of Web Review Argumentation

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

External Research Organisations

  • Bauhaus-Universität Weimar
Plum Print visual indicator of research metrics
  • Citations
    • Citation Indexes: 28
  • Captures
    • Readers: 112
see details

Details

Original languageEnglish
Title of host publicationProceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Pages601-611
Number of pages11
ISBN (electronic)9781941643327
Publication statusPublished - Aug 2015
Externally publishedYes
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal
Duration: 17 Sept 201521 Sept 2015

Abstract

Web reviews have been intensively studied in argumentation-related tasks such as sentiment analysis. However, due to their focus on content-based features, many sentiment analysis approaches are effective only for reviews from those domains they have been specifically modeled for. This paper puts its focus on domain independence and asks whether a general model can be found for how people argue in web reviews. Our hypothesis is that people express their global sentiment on a topic with similar sequences of local sentiment independent of the domain. We model such sentiment flow robustly under uncertainty through abstraction. To test our hypothesis, we predict global sentiment based on sentiment flow. In systematic experiments, we improve over the domain independence of strong baselines. Our findings suggest that sentiment flow qualifies as a general model of web review argumentation.

ASJC Scopus subject areas

Cite this

Sentiment Flow – A General Model of Web Review Argumentation. / Wachsmuth, Henning; Kiesel, Johannes; Stein, Benno.
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015. p. 601-611.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Wachsmuth, H, Kiesel, J & Stein, B 2015, Sentiment Flow – A General Model of Web Review Argumentation. in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. pp. 601-611, Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, 17 Sept 2015. https://doi.org/10.18653/v1/d15-1072
Wachsmuth, H., Kiesel, J., & Stein, B. (2015). Sentiment Flow – A General Model of Web Review Argumentation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (pp. 601-611) https://doi.org/10.18653/v1/d15-1072
Wachsmuth H, Kiesel J, Stein B. Sentiment Flow – A General Model of Web Review Argumentation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015. p. 601-611 doi: 10.18653/v1/d15-1072
Wachsmuth, Henning ; Kiesel, Johannes ; Stein, Benno. / Sentiment Flow – A General Model of Web Review Argumentation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015. pp. 601-611
Download
@inproceedings{1e3e0ac450b3478c9543f2b458916b41,
title = "Sentiment Flow – A General Model of Web Review Argumentation",
abstract = "Web reviews have been intensively studied in argumentation-related tasks such as sentiment analysis. However, due to their focus on content-based features, many sentiment analysis approaches are effective only for reviews from those domains they have been specifically modeled for. This paper puts its focus on domain independence and asks whether a general model can be found for how people argue in web reviews. Our hypothesis is that people express their global sentiment on a topic with similar sequences of local sentiment independent of the domain. We model such sentiment flow robustly under uncertainty through abstraction. To test our hypothesis, we predict global sentiment based on sentiment flow. In systematic experiments, we improve over the domain independence of strong baselines. Our findings suggest that sentiment flow qualifies as a general model of web review argumentation.",
author = "Henning Wachsmuth and Johannes Kiesel and Benno Stein",
year = "2015",
month = aug,
doi = "10.18653/v1/d15-1072",
language = "English",
pages = "601--611",
booktitle = "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing",
note = "Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 ; Conference date: 17-09-2015 Through 21-09-2015",

}

Download

TY - GEN

T1 - Sentiment Flow – A General Model of Web Review Argumentation

AU - Wachsmuth, Henning

AU - Kiesel, Johannes

AU - Stein, Benno

PY - 2015/8

Y1 - 2015/8

N2 - Web reviews have been intensively studied in argumentation-related tasks such as sentiment analysis. However, due to their focus on content-based features, many sentiment analysis approaches are effective only for reviews from those domains they have been specifically modeled for. This paper puts its focus on domain independence and asks whether a general model can be found for how people argue in web reviews. Our hypothesis is that people express their global sentiment on a topic with similar sequences of local sentiment independent of the domain. We model such sentiment flow robustly under uncertainty through abstraction. To test our hypothesis, we predict global sentiment based on sentiment flow. In systematic experiments, we improve over the domain independence of strong baselines. Our findings suggest that sentiment flow qualifies as a general model of web review argumentation.

AB - Web reviews have been intensively studied in argumentation-related tasks such as sentiment analysis. However, due to their focus on content-based features, many sentiment analysis approaches are effective only for reviews from those domains they have been specifically modeled for. This paper puts its focus on domain independence and asks whether a general model can be found for how people argue in web reviews. Our hypothesis is that people express their global sentiment on a topic with similar sequences of local sentiment independent of the domain. We model such sentiment flow robustly under uncertainty through abstraction. To test our hypothesis, we predict global sentiment based on sentiment flow. In systematic experiments, we improve over the domain independence of strong baselines. Our findings suggest that sentiment flow qualifies as a general model of web review argumentation.

UR - http://www.scopus.com/inward/record.url?scp=84959883610&partnerID=8YFLogxK

U2 - 10.18653/v1/d15-1072

DO - 10.18653/v1/d15-1072

M3 - Conference contribution

AN - SCOPUS:84959883610

SP - 601

EP - 611

BT - Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015

Y2 - 17 September 2015 through 21 September 2015

ER -

By the same author(s)