Determining the semantic orientation of terms through gloss classification

Andrea Esuli, Fabrizio Sebastiani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

259 Citations (Scopus)

Abstract

Sentiment classification is a recent subdiscipline of text classification which is concerned not with the topic a document is about, but with the opinion it expresses. It has a rich set of applications, ranging from tracking users' opinions about products or about political candidates as expressed in online forums, to customer relationship management. Functional to the extraction of opinions from text is the determination of the orientation of "subjective" terms contained in text, i.e. the determination of whether a term that carries opinionated content has a positive or a negative connotation. In this paper we present a new method for determining the orientation of subjective terms. The method is based on the quantitative analysis of the glosses of such terms, i.e. the definitions that these terms are given in on-line dictionaries, and on the use of the resulting term representations for semi-supervised term classification. The method we present outperforms all known methods when tested on the recognized standard benchmarks for this task.

Original languageEnglish
Title of host publicationInternational Conference on Information and Knowledge Management, Proceedings
Pages617-624
Number of pages8
DOIs
Publication statusPublished - 2005
Externally publishedYes
EventCIKM'05 - Proceedings of the 14th ACM International Conference on Information and Knowledge Management - Bremen
Duration: 31 Oct 20055 Nov 2005

Other

OtherCIKM'05 - Proceedings of the 14th ACM International Conference on Information and Knowledge Management
CityBremen
Period31/10/055/11/05

Fingerprint

Customer relationship management
Text classification
Benchmark
Quantitative analysis
Sentiment classification

Keywords

  • Opinion Mining
  • Polarity Detection
  • Semantic Orientation
  • Sentiment Classification
  • Text Classification

ASJC Scopus subject areas

  • Business, Management and Accounting(all)

Cite this

Esuli, A., & Sebastiani, F. (2005). Determining the semantic orientation of terms through gloss classification. In International Conference on Information and Knowledge Management, Proceedings (pp. 617-624) https://doi.org/10.1145/1099554.1099713

Determining the semantic orientation of terms through gloss classification. / Esuli, Andrea; Sebastiani, Fabrizio.

International Conference on Information and Knowledge Management, Proceedings. 2005. p. 617-624.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Esuli, A & Sebastiani, F 2005, Determining the semantic orientation of terms through gloss classification. in International Conference on Information and Knowledge Management, Proceedings. pp. 617-624, CIKM'05 - Proceedings of the 14th ACM International Conference on Information and Knowledge Management, Bremen, 31/10/05. https://doi.org/10.1145/1099554.1099713
Esuli A, Sebastiani F. Determining the semantic orientation of terms through gloss classification. In International Conference on Information and Knowledge Management, Proceedings. 2005. p. 617-624 https://doi.org/10.1145/1099554.1099713
Esuli, Andrea ; Sebastiani, Fabrizio. / Determining the semantic orientation of terms through gloss classification. International Conference on Information and Knowledge Management, Proceedings. 2005. pp. 617-624
@inproceedings{6fbac74150e247d0bcda132ad9624bae,
title = "Determining the semantic orientation of terms through gloss classification",
abstract = "Sentiment classification is a recent subdiscipline of text classification which is concerned not with the topic a document is about, but with the opinion it expresses. It has a rich set of applications, ranging from tracking users' opinions about products or about political candidates as expressed in online forums, to customer relationship management. Functional to the extraction of opinions from text is the determination of the orientation of {"}subjective{"} terms contained in text, i.e. the determination of whether a term that carries opinionated content has a positive or a negative connotation. In this paper we present a new method for determining the orientation of subjective terms. The method is based on the quantitative analysis of the glosses of such terms, i.e. the definitions that these terms are given in on-line dictionaries, and on the use of the resulting term representations for semi-supervised term classification. The method we present outperforms all known methods when tested on the recognized standard benchmarks for this task.",
keywords = "Opinion Mining, Polarity Detection, Semantic Orientation, Sentiment Classification, Text Classification",
author = "Andrea Esuli and Fabrizio Sebastiani",
year = "2005",
doi = "10.1145/1099554.1099713",
language = "English",
isbn = "1595931406",
pages = "617--624",
booktitle = "International Conference on Information and Knowledge Management, Proceedings",

}

TY - GEN

T1 - Determining the semantic orientation of terms through gloss classification

AU - Esuli, Andrea

AU - Sebastiani, Fabrizio

PY - 2005

Y1 - 2005

N2 - Sentiment classification is a recent subdiscipline of text classification which is concerned not with the topic a document is about, but with the opinion it expresses. It has a rich set of applications, ranging from tracking users' opinions about products or about political candidates as expressed in online forums, to customer relationship management. Functional to the extraction of opinions from text is the determination of the orientation of "subjective" terms contained in text, i.e. the determination of whether a term that carries opinionated content has a positive or a negative connotation. In this paper we present a new method for determining the orientation of subjective terms. The method is based on the quantitative analysis of the glosses of such terms, i.e. the definitions that these terms are given in on-line dictionaries, and on the use of the resulting term representations for semi-supervised term classification. The method we present outperforms all known methods when tested on the recognized standard benchmarks for this task.

AB - Sentiment classification is a recent subdiscipline of text classification which is concerned not with the topic a document is about, but with the opinion it expresses. It has a rich set of applications, ranging from tracking users' opinions about products or about political candidates as expressed in online forums, to customer relationship management. Functional to the extraction of opinions from text is the determination of the orientation of "subjective" terms contained in text, i.e. the determination of whether a term that carries opinionated content has a positive or a negative connotation. In this paper we present a new method for determining the orientation of subjective terms. The method is based on the quantitative analysis of the glosses of such terms, i.e. the definitions that these terms are given in on-line dictionaries, and on the use of the resulting term representations for semi-supervised term classification. The method we present outperforms all known methods when tested on the recognized standard benchmarks for this task.

KW - Opinion Mining

KW - Polarity Detection

KW - Semantic Orientation

KW - Sentiment Classification

KW - Text Classification

UR - http://www.scopus.com/inward/record.url?scp=33646872279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646872279&partnerID=8YFLogxK

U2 - 10.1145/1099554.1099713

DO - 10.1145/1099554.1099713

M3 - Conference contribution

SN - 1595931406

SN - 9781595931405

SP - 617

EP - 624

BT - International Conference on Information and Knowledge Management, Proceedings

ER -