Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter

Hassan Saif, Yulan He, Miriam Fernández, Harith Alani

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

Abstract

Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior sentiment information of opinionated words in texts. However, words' sentiment orientations and strengths often change throughout various contexts in which the words appear. In this paper, we propose a lexicon adaptation approach that uses the contextual semantics of words to capture their contexts in tweet messages and update their prior sentiment orientations and/or strengths accordingly. We evaluate our approach on one state-of-the-art sentiment lexicon using three different Twitter datasets. Results show that the sentiment lexicons adapted by our approach outperform the original lexicon in accuracy and F-measure in two datasets, but give similar accuracy and slightly lower F-measure in one dataset.

Original languageEnglish
Title of host publicationSSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014
Subtitle of host publicationjoint proceedings of the 1st workshop on Semantic Sentiment Analysis (SSA2014), and the workshop on Social Media and Linked Data for Emergency Response (SMILE 2014) co-located with 11th European Semantic Web Conference (ESWC 2014)
EditorsAldo Gangemi, Harith Alani, Malvina Nissim, Erik Cambria, Diego Reforgiato Recupero
PublisherCEUR-WS.org
Pages5-12
Number of pages8
Publication statusPublished - 2014
Event1st workshop on Semantic Sentiment Analysis / workshop on Social Media and Linked Data for Emergency Response / co-located with 11th European Semantic Web Conference (ESWC 2014) - Crete, Greece
Duration: 25 May 201425 May 2014

Publication series

NameCEUR workshop proceedings
Volume1329
ISSN (Electronic)1613-0073

Workshop

Workshop1st workshop on Semantic Sentiment Analysis / workshop on Social Media and Linked Data for Emergency Response / co-located with 11th European Semantic Web Conference (ESWC 2014)
Abbreviated titleSSA-SMILE 2014 (ESWC 2014)
CountryGreece
CityCrete
Period25/05/1425/05/14

Fingerprint

Semantics

Bibliographical note

Saif, H; He, Y; Fernández, M; Alani, H 2014 'Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter', Proc. SSA-SMILE 2014, http://ceur-ws.org/Vol-1329/paper_2.pdf

Keywords

  • lexicon adaptation
  • semantics
  • sentiment analysis
  • Twitter

Cite this

Saif, H., He, Y., Fernández, M., & Alani, H. (2014). Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter. In A. Gangemi, H. Alani, M. Nissim, E. Cambria, & D. Reforgiato Recupero (Eds.), SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014: joint proceedings of the 1st workshop on Semantic Sentiment Analysis (SSA2014), and the workshop on Social Media and Linked Data for Emergency Response (SMILE 2014) co-located with 11th European Semantic Web Conference (ESWC 2014) (pp. 5-12). [2] (CEUR workshop proceedings; Vol. 1329). CEUR-WS.org.
Saif, Hassan ; He, Yulan ; Fernández, Miriam ; Alani, Harith. / Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter. SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014: joint proceedings of the 1st workshop on Semantic Sentiment Analysis (SSA2014), and the workshop on Social Media and Linked Data for Emergency Response (SMILE 2014) co-located with 11th European Semantic Web Conference (ESWC 2014). editor / Aldo Gangemi ; Harith Alani ; Malvina Nissim ; Erik Cambria ; Diego Reforgiato Recupero. CEUR-WS.org, 2014. pp. 5-12 (CEUR workshop proceedings).
@inproceedings{dfc41ac2940747ecb888e960f6926323,
title = "Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter",
abstract = "Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior sentiment information of opinionated words in texts. However, words' sentiment orientations and strengths often change throughout various contexts in which the words appear. In this paper, we propose a lexicon adaptation approach that uses the contextual semantics of words to capture their contexts in tweet messages and update their prior sentiment orientations and/or strengths accordingly. We evaluate our approach on one state-of-the-art sentiment lexicon using three different Twitter datasets. Results show that the sentiment lexicons adapted by our approach outperform the original lexicon in accuracy and F-measure in two datasets, but give similar accuracy and slightly lower F-measure in one dataset.",
keywords = "lexicon adaptation, semantics, sentiment analysis, Twitter",
author = "Hassan Saif and Yulan He and Miriam Fern{\'a}ndez and Harith Alani",
note = "Saif, H; He, Y; Fern{\'a}ndez, M; Alani, H 2014 'Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter', Proc. SSA-SMILE 2014, http://ceur-ws.org/Vol-1329/paper_2.pdf",
year = "2014",
language = "English",
series = "CEUR workshop proceedings",
publisher = "CEUR-WS.org",
pages = "5--12",
editor = "Aldo Gangemi and Harith Alani and Malvina Nissim and Erik Cambria and {Reforgiato Recupero}, Diego",
booktitle = "SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014",

}

Saif, H, He, Y, Fernández, M & Alani, H 2014, Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter. in A Gangemi, H Alani, M Nissim, E Cambria & D Reforgiato Recupero (eds), SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014: joint proceedings of the 1st workshop on Semantic Sentiment Analysis (SSA2014), and the workshop on Social Media and Linked Data for Emergency Response (SMILE 2014) co-located with 11th European Semantic Web Conference (ESWC 2014)., 2, CEUR workshop proceedings, vol. 1329, CEUR-WS.org, pp. 5-12, 1st workshop on Semantic Sentiment Analysis / workshop on Social Media and Linked Data for Emergency Response / co-located with 11th European Semantic Web Conference (ESWC 2014), Crete, Greece, 25/05/14.

Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter. / Saif, Hassan; He, Yulan; Fernández, Miriam; Alani, Harith.

SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014: joint proceedings of the 1st workshop on Semantic Sentiment Analysis (SSA2014), and the workshop on Social Media and Linked Data for Emergency Response (SMILE 2014) co-located with 11th European Semantic Web Conference (ESWC 2014). ed. / Aldo Gangemi; Harith Alani; Malvina Nissim; Erik Cambria; Diego Reforgiato Recupero. CEUR-WS.org, 2014. p. 5-12 2 (CEUR workshop proceedings; Vol. 1329).

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

TY - GEN

T1 - Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter

AU - Saif, Hassan

AU - He, Yulan

AU - Fernández, Miriam

AU - Alani, Harith

N1 - Saif, H; He, Y; Fernández, M; Alani, H 2014 'Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter', Proc. SSA-SMILE 2014, http://ceur-ws.org/Vol-1329/paper_2.pdf

PY - 2014

Y1 - 2014

N2 - Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior sentiment information of opinionated words in texts. However, words' sentiment orientations and strengths often change throughout various contexts in which the words appear. In this paper, we propose a lexicon adaptation approach that uses the contextual semantics of words to capture their contexts in tweet messages and update their prior sentiment orientations and/or strengths accordingly. We evaluate our approach on one state-of-the-art sentiment lexicon using three different Twitter datasets. Results show that the sentiment lexicons adapted by our approach outperform the original lexicon in accuracy and F-measure in two datasets, but give similar accuracy and slightly lower F-measure in one dataset.

AB - Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior sentiment information of opinionated words in texts. However, words' sentiment orientations and strengths often change throughout various contexts in which the words appear. In this paper, we propose a lexicon adaptation approach that uses the contextual semantics of words to capture their contexts in tweet messages and update their prior sentiment orientations and/or strengths accordingly. We evaluate our approach on one state-of-the-art sentiment lexicon using three different Twitter datasets. Results show that the sentiment lexicons adapted by our approach outperform the original lexicon in accuracy and F-measure in two datasets, but give similar accuracy and slightly lower F-measure in one dataset.

KW - lexicon adaptation

KW - semantics

KW - sentiment analysis

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84926328342&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84926328342

T3 - CEUR workshop proceedings

SP - 5

EP - 12

BT - SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014

A2 - Gangemi, Aldo

A2 - Alani, Harith

A2 - Nissim, Malvina

A2 - Cambria, Erik

A2 - Reforgiato Recupero, Diego

PB - CEUR-WS.org

ER -

Saif H, He Y, Fernández M, Alani H. Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter. In Gangemi A, Alani H, Nissim M, Cambria E, Reforgiato Recupero D, editors, SSA-SMILE 2014 : joint proceedings of SSA 2014 and SMILE 2014: joint proceedings of the 1st workshop on Semantic Sentiment Analysis (SSA2014), and the workshop on Social Media and Linked Data for Emergency Response (SMILE 2014) co-located with 11th European Semantic Web Conference (ESWC 2014). CEUR-WS.org. 2014. p. 5-12. 2. (CEUR workshop proceedings).