Adapting sentiment lexicons using contextual semantics for sentiment analysis of twitter

Hassan Saif*, Yulan He, Miriam Fernández, Harith Alani

*Corresponding author for this work

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 publicationThe semantic web : ESWC 2014 satellite events
Subtitle of host publicationESWC 2014 satellite events, Anissaras, Crete, Greece, May 25-29, 2014, revised selected papers
Place of PublicationChem (CH)
PublisherSpringer
Pages54-63
Number of pages10
ISBN (Electronic)978-3-319-11955-7
ISBN (Print)978-3-319-11954-0
DOIs
Publication statusPublished - 16 Oct 2014
Event11th international Conference on Semantic Web: trends and challenges - Anissaras, Crete, Greece
Duration: 25 May 201429 May 2014

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume8798
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference11th international Conference on Semantic Web: trends and challenges
Abbreviated titleESWC 2014
CountryGreece
CityAnissaras, Crete
Period25/05/1429/05/14

Fingerprint

Sentiment Analysis
Semantics
Update
Evaluate
Context
Text

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 The semantic web : ESWC 2014 satellite events: ESWC 2014 satellite events, Anissaras, Crete, Greece, May 25-29, 2014, revised selected papers (pp. 54-63). (Lecture notes in computer science; Vol. 8798). Chem (CH): Springer. https://doi.org/10.1007/978-3-319-11955-7_5
Saif, Hassan ; He, Yulan ; Fernández, Miriam ; Alani, Harith. / Adapting sentiment lexicons using contextual semantics for sentiment analysis of twitter. The semantic web : ESWC 2014 satellite events: ESWC 2014 satellite events, Anissaras, Crete, Greece, May 25-29, 2014, revised selected papers. Chem (CH) : Springer, 2014. pp. 54-63 (Lecture notes in computer science).
@inproceedings{2cf5179c37a34b1f989367531bc1e94e,
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",
year = "2014",
month = "10",
day = "16",
doi = "10.1007/978-3-319-11955-7_5",
language = "English",
isbn = "978-3-319-11954-0",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "54--63",
booktitle = "The semantic web : ESWC 2014 satellite events",
address = "Germany",

}

Saif, H, He, Y, Fernández, M & Alani, H 2014, Adapting sentiment lexicons using contextual semantics for sentiment analysis of twitter. in The semantic web : ESWC 2014 satellite events: ESWC 2014 satellite events, Anissaras, Crete, Greece, May 25-29, 2014, revised selected papers. Lecture notes in computer science, vol. 8798, Springer, Chem (CH), pp. 54-63, 11th international Conference on Semantic Web: trends and challenges, Anissaras, Crete, Greece, 25/05/14. https://doi.org/10.1007/978-3-319-11955-7_5

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

The semantic web : ESWC 2014 satellite events: ESWC 2014 satellite events, Anissaras, Crete, Greece, May 25-29, 2014, revised selected papers. Chem (CH) : Springer, 2014. p. 54-63 (Lecture notes in computer science; Vol. 8798).

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

PY - 2014/10/16

Y1 - 2014/10/16

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=84908667095&partnerID=8YFLogxK

UR - http://link.springer.com/chapter/10.1007%2F978-3-319-11955-7_5

U2 - 10.1007/978-3-319-11955-7_5

DO - 10.1007/978-3-319-11955-7_5

M3 - Conference contribution

AN - SCOPUS:84908667095

SN - 978-3-319-11954-0

T3 - Lecture notes in computer science

SP - 54

EP - 63

BT - The semantic web : ESWC 2014 satellite events

PB - Springer

CY - Chem (CH)

ER -

Saif H, He Y, Fernández M, Alani H. Adapting sentiment lexicons using contextual semantics for sentiment analysis of twitter. In The semantic web : ESWC 2014 satellite events: ESWC 2014 satellite events, Anissaras, Crete, Greece, May 25-29, 2014, revised selected papers. Chem (CH): Springer. 2014. p. 54-63. (Lecture notes in computer science). https://doi.org/10.1007/978-3-319-11955-7_5