SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter

Hassan Saif; Miriam Fernández; Yulan He; Harith Alani

doi:10.1007/978-3-319-07443-6_7

SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter

Hassan Saif, Miriam Fernández, Yulan He, Harith Alani

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Lexicon-based approaches to Twitter sentiment analysis are gaining much popularity due to their simplicity, domain independence, and relatively good performance. These approaches rely on sentiment lexicons, where a collection of words are marked with fixed sentiment polarities. However, words' sentiment orientation (positive, neural, negative) and/or sentiment strengths could change depending on context and targeted entities. In this paper we present SentiCircle; a novel lexicon-based approach that takes into account the contextual and conceptual semantics of words when calculating their sentiment orientation and strength in Twitter. We evaluate our approach on three Twitter datasets using three different sentiment lexicons. Results show that our approach significantly outperforms two lexicon baselines. Results are competitive but inconclusive when comparing to state-of-art SentiStrength, and vary from one dataset to another. SentiCircle outperforms SentiStrength in accuracy on average, but falls marginally behind in F-measure.

Original language	English
Title of host publication	The semantic web: trends and challenges
Subtitle of host publication	11th international conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, proceedings
Editors	Valentina Presutti, Claudia d’Amato, Fabien Gandon, Mathieu d’Aquin, et al
Place of Publication	Chem (CH)
Publisher	Springer
Pages	83-98
Number of pages	16
ISBN (Electronic)	978-3-319-07443-6
ISBN (Print)	978-3-319-07442-9
DOIs	https://doi.org/10.1007/978-3-319-07443-6_7
Publication status	Published - 31 Dec 2014
Event	11th international Conference on Semantic Web: trends and challenges - Anissaras, Crete, Greece Duration: 25 May 2014 → 29 May 2014

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	8465
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	11th international Conference on Semantic Web: trends and challenges
Abbreviated title	ESWC 2014
Country/Territory	Greece
City	Anissaras, Crete
Period	25/05/14 → 29/05/14

Keywords

semantics
sentiment analysis
Twitter

Access to Document

10.1007/978-3-319-07443-6_7

Cite this

Saif, H., Fernández, M., He, Y., & Alani, H. (2014). SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter. In V. Presutti, C. d’Amato, F. Gandon, M. d’Aquin, & et al (Eds.), The semantic web: trends and challenges: 11th international conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, proceedings (pp. 83-98). (Lecture notes in computer science; Vol. 8465). Springer. https://doi.org/10.1007/978-3-319-07443-6_7

Saif, Hassan ; Fernández, Miriam ; He, Yulan et al. / SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter. The semantic web: trends and challenges: 11th international conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, proceedings. editor / Valentina Presutti ; Claudia d’Amato ; Fabien Gandon ; Mathieu d’Aquin ; et al. Chem (CH) : Springer, 2014. pp. 83-98 (Lecture notes in computer science).

@inproceedings{f306a4d52a404968af7561d27f2e4277,

title = "SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter",

abstract = "Lexicon-based approaches to Twitter sentiment analysis are gaining much popularity due to their simplicity, domain independence, and relatively good performance. These approaches rely on sentiment lexicons, where a collection of words are marked with fixed sentiment polarities. However, words' sentiment orientation (positive, neural, negative) and/or sentiment strengths could change depending on context and targeted entities. In this paper we present SentiCircle; a novel lexicon-based approach that takes into account the contextual and conceptual semantics of words when calculating their sentiment orientation and strength in Twitter. We evaluate our approach on three Twitter datasets using three different sentiment lexicons. Results show that our approach significantly outperforms two lexicon baselines. Results are competitive but inconclusive when comparing to state-of-art SentiStrength, and vary from one dataset to another. SentiCircle outperforms SentiStrength in accuracy on average, but falls marginally behind in F-measure.",

keywords = "semantics, sentiment analysis, Twitter",

author = "Hassan Saif and Miriam Fern{\'a}ndez and Yulan He and Harith Alani",

year = "2014",

month = dec,

day = "31",

doi = "10.1007/978-3-319-07443-6_7",

language = "English",

isbn = "978-3-319-07442-9",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "83--98",

editor = "Valentina Presutti and Claudia d{\textquoteright}Amato and Fabien Gandon and Mathieu d{\textquoteright}Aquin and {et al}",

booktitle = "The semantic web: trends and challenges",

address = "Germany",

note = "11th international Conference on Semantic Web: trends and challenges, ESWC 2014 ; Conference date: 25-05-2014 Through 29-05-2014",

}

Saif, H, Fernández, M, He, Y & Alani, H 2014, SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter. in V Presutti, C d’Amato, F Gandon, M d’Aquin & et al (eds), The semantic web: trends and challenges: 11th international conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, proceedings. Lecture notes in computer science, vol. 8465, Springer, Chem (CH), pp. 83-98, 11th international Conference on Semantic Web: trends and challenges, Anissaras, Crete, Greece, 25/05/14. https://doi.org/10.1007/978-3-319-07443-6_7

SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter. / Saif, Hassan; Fernández, Miriam; He, Yulan et al.
The semantic web: trends and challenges: 11th international conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, proceedings. ed. / Valentina Presutti; Claudia d’Amato; Fabien Gandon; Mathieu d’Aquin; et al. Chem (CH): Springer, 2014. p. 83-98 (Lecture notes in computer science; Vol. 8465).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter

AU - Saif, Hassan

AU - Fernández, Miriam

AU - He, Yulan

AU - Alani, Harith

PY - 2014/12/31

Y1 - 2014/12/31

N2 - Lexicon-based approaches to Twitter sentiment analysis are gaining much popularity due to their simplicity, domain independence, and relatively good performance. These approaches rely on sentiment lexicons, where a collection of words are marked with fixed sentiment polarities. However, words' sentiment orientation (positive, neural, negative) and/or sentiment strengths could change depending on context and targeted entities. In this paper we present SentiCircle; a novel lexicon-based approach that takes into account the contextual and conceptual semantics of words when calculating their sentiment orientation and strength in Twitter. We evaluate our approach on three Twitter datasets using three different sentiment lexicons. Results show that our approach significantly outperforms two lexicon baselines. Results are competitive but inconclusive when comparing to state-of-art SentiStrength, and vary from one dataset to another. SentiCircle outperforms SentiStrength in accuracy on average, but falls marginally behind in F-measure.

AB - Lexicon-based approaches to Twitter sentiment analysis are gaining much popularity due to their simplicity, domain independence, and relatively good performance. These approaches rely on sentiment lexicons, where a collection of words are marked with fixed sentiment polarities. However, words' sentiment orientation (positive, neural, negative) and/or sentiment strengths could change depending on context and targeted entities. In this paper we present SentiCircle; a novel lexicon-based approach that takes into account the contextual and conceptual semantics of words when calculating their sentiment orientation and strength in Twitter. We evaluate our approach on three Twitter datasets using three different sentiment lexicons. Results show that our approach significantly outperforms two lexicon baselines. Results are competitive but inconclusive when comparing to state-of-art SentiStrength, and vary from one dataset to another. SentiCircle outperforms SentiStrength in accuracy on average, but falls marginally behind in F-measure.

KW - semantics

KW - sentiment analysis

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84902578900&partnerID=8YFLogxK

UR - http://link.springer.com/chapter/10.1007%2F978-3-319-07443-6_7

U2 - 10.1007/978-3-319-07443-6_7

DO - 10.1007/978-3-319-07443-6_7

M3 - Conference publication

AN - SCOPUS:84902578900

SN - 978-3-319-07442-9

T3 - Lecture notes in computer science

SP - 83

EP - 98

BT - The semantic web: trends and challenges

A2 - Presutti, Valentina

A2 - d’Amato, Claudia

A2 - Gandon, Fabien

A2 - d’Aquin, Mathieu

A2 - et al,

PB - Springer

CY - Chem (CH)

T2 - 11th international Conference on Semantic Web: trends and challenges

Y2 - 25 May 2014 through 29 May 2014

ER -

Saif H, Fernández M, He Y, Alani H. SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter. In Presutti V, d’Amato C, Gandon F, d’Aquin M, et al, editors, The semantic web: trends and challenges: 11th international conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, proceedings. Chem (CH): Springer. 2014. p. 83-98. (Lecture notes in computer science). doi: 10.1007/978-3-319-07443-6_7

SentiCircles for contextual and conceptual semantic sentiment analysis of Twitter

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Adapting sentiment lexicons using contextual semantics for sentiment analysis of twitter

Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter

Cite this