Semantic sentiment analysis of Twitter

Hassan Saif, Yulan He, Harith Alani

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

Abstract

Sentiment analysis over Twitter offer organisations a fast and effective way to monitor the publics' feelings towards their brand, business, directors, etc. A wide range of features and methods for training sentiment classifiers for Twitter datasets have been researched in recent years with varying results. In this paper, we introduce a novel approach of adding semantics as additional features into the training set for sentiment analysis. For each extracted entity (e.g. iPhone) from tweets, we add its semantic concept (e.g. Apple product) as an additional feature, and measure the correlation of the representative concept with negative/positive sentiment. We apply this approach to predict sentiment for three different Twitter datasets. Our results show an average increase of F harmonic accuracy score for identifying both negative and positive sentiment of around 6.5% and 4.8% over the baselines of unigrams and part-of-speech features respectively. We also compare against an approach based on sentiment-bearing topic analysis, and find that semantic features produce better Recall and F score when classifying negative sentiment, and better Precision with lower Recall and F score in positive sentiment classification.
Original languageEnglish
Title of host publicationThe semantic web – ISWC 2012
Subtitle of host publication11th international semantic web conference, Boston, MA, USA, November 11-15, 2012, proceedings, part 1
EditorsPhilippe Cudré-Mauroux, Jeff Heflin, Evren Sirin, et al.
Place of PublicationHeildelberg (DE)
PublisherSpringer
Pages508-524
Number of pages17
Volume7649
ISBN (Electronic)978-3-642-35176-1
ISBN (Print)978-3-642-35175-4
DOIs
Publication statusPublished - 2012
Event11th international semantic web conference - Boston, MA, United States
Duration: 11 Nov 201215 Nov 2012

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume7649
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference11th international semantic web conference
CountryUnited States
CityBoston, MA
Period11/11/1215/11/12

Fingerprint

Semantics
Bearings (structural)
Classifiers
Industry

Keywords

  • sentiment analysis
  • semantic concepts
  • feature interpolation

Cite this

Saif, H., He, Y., & Alani, H. (2012). Semantic sentiment analysis of Twitter. In P. Cudré-Mauroux, J. Heflin, E. Sirin, & E. A. (Eds.), The semantic web – ISWC 2012: 11th international semantic web conference, Boston, MA, USA, November 11-15, 2012, proceedings, part 1 (Vol. 7649, pp. 508-524). (Lecture notes in computer science; Vol. 7649). Heildelberg (DE): Springer. https://doi.org/10.1007/978-3-642-35176-1-32
Saif, Hassan ; He, Yulan ; Alani, Harith. / Semantic sentiment analysis of Twitter. The semantic web – ISWC 2012: 11th international semantic web conference, Boston, MA, USA, November 11-15, 2012, proceedings, part 1. editor / Philippe Cudré-Mauroux ; Jeff Heflin ; Evren Sirin ; et al. Vol. 7649 Heildelberg (DE) : Springer, 2012. pp. 508-524 (Lecture notes in computer science).
@inproceedings{784b6b943d3e44099b946018b0de8974,
title = "Semantic sentiment analysis of Twitter",
abstract = "Sentiment analysis over Twitter offer organisations a fast and effective way to monitor the publics' feelings towards their brand, business, directors, etc. A wide range of features and methods for training sentiment classifiers for Twitter datasets have been researched in recent years with varying results. In this paper, we introduce a novel approach of adding semantics as additional features into the training set for sentiment analysis. For each extracted entity (e.g. iPhone) from tweets, we add its semantic concept (e.g. Apple product) as an additional feature, and measure the correlation of the representative concept with negative/positive sentiment. We apply this approach to predict sentiment for three different Twitter datasets. Our results show an average increase of F harmonic accuracy score for identifying both negative and positive sentiment of around 6.5{\%} and 4.8{\%} over the baselines of unigrams and part-of-speech features respectively. We also compare against an approach based on sentiment-bearing topic analysis, and find that semantic features produce better Recall and F score when classifying negative sentiment, and better Precision with lower Recall and F score in positive sentiment classification.",
keywords = "sentiment analysis, semantic concepts, feature interpolation",
author = "Hassan Saif and Yulan He and Harith Alani",
year = "2012",
doi = "10.1007/978-3-642-35176-1-32",
language = "English",
isbn = "978-3-642-35175-4",
volume = "7649",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "508--524",
editor = "Philippe Cudr{\'e}-Mauroux and Jeff Heflin and Evren Sirin and {et al.}",
booktitle = "The semantic web – ISWC 2012",
address = "Germany",

}

Saif, H, He, Y & Alani, H 2012, Semantic sentiment analysis of Twitter. in P Cudré-Mauroux, J Heflin, E Sirin & EA (eds), The semantic web – ISWC 2012: 11th international semantic web conference, Boston, MA, USA, November 11-15, 2012, proceedings, part 1. vol. 7649, Lecture notes in computer science, vol. 7649, Springer, Heildelberg (DE), pp. 508-524, 11th international semantic web conference, Boston, MA, United States, 11/11/12. https://doi.org/10.1007/978-3-642-35176-1-32

Semantic sentiment analysis of Twitter. / Saif, Hassan; He, Yulan; Alani, Harith.

The semantic web – ISWC 2012: 11th international semantic web conference, Boston, MA, USA, November 11-15, 2012, proceedings, part 1. ed. / Philippe Cudré-Mauroux; Jeff Heflin; Evren Sirin; et al. Vol. 7649 Heildelberg (DE) : Springer, 2012. p. 508-524 (Lecture notes in computer science; Vol. 7649).

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

TY - GEN

T1 - Semantic sentiment analysis of Twitter

AU - Saif, Hassan

AU - He, Yulan

AU - Alani, Harith

PY - 2012

Y1 - 2012

N2 - Sentiment analysis over Twitter offer organisations a fast and effective way to monitor the publics' feelings towards their brand, business, directors, etc. A wide range of features and methods for training sentiment classifiers for Twitter datasets have been researched in recent years with varying results. In this paper, we introduce a novel approach of adding semantics as additional features into the training set for sentiment analysis. For each extracted entity (e.g. iPhone) from tweets, we add its semantic concept (e.g. Apple product) as an additional feature, and measure the correlation of the representative concept with negative/positive sentiment. We apply this approach to predict sentiment for three different Twitter datasets. Our results show an average increase of F harmonic accuracy score for identifying both negative and positive sentiment of around 6.5% and 4.8% over the baselines of unigrams and part-of-speech features respectively. We also compare against an approach based on sentiment-bearing topic analysis, and find that semantic features produce better Recall and F score when classifying negative sentiment, and better Precision with lower Recall and F score in positive sentiment classification.

AB - Sentiment analysis over Twitter offer organisations a fast and effective way to monitor the publics' feelings towards their brand, business, directors, etc. A wide range of features and methods for training sentiment classifiers for Twitter datasets have been researched in recent years with varying results. In this paper, we introduce a novel approach of adding semantics as additional features into the training set for sentiment analysis. For each extracted entity (e.g. iPhone) from tweets, we add its semantic concept (e.g. Apple product) as an additional feature, and measure the correlation of the representative concept with negative/positive sentiment. We apply this approach to predict sentiment for three different Twitter datasets. Our results show an average increase of F harmonic accuracy score for identifying both negative and positive sentiment of around 6.5% and 4.8% over the baselines of unigrams and part-of-speech features respectively. We also compare against an approach based on sentiment-bearing topic analysis, and find that semantic features produce better Recall and F score when classifying negative sentiment, and better Precision with lower Recall and F score in positive sentiment classification.

KW - sentiment analysis

KW - semantic concepts

KW - feature interpolation

UR - http://www.scopus.com/inward/record.url?scp=84868588570&partnerID=8YFLogxK

UR - http://www.springerlink.com/content/r863wj5871q17671/

U2 - 10.1007/978-3-642-35176-1-32

DO - 10.1007/978-3-642-35176-1-32

M3 - Conference contribution

AN - SCOPUS:84868588570

SN - 978-3-642-35175-4

VL - 7649

T3 - Lecture notes in computer science

SP - 508

EP - 524

BT - The semantic web – ISWC 2012

A2 - Cudré-Mauroux, Philippe

A2 - Heflin, Jeff

A2 - Sirin, Evren

A2 - , et al.

PB - Springer

CY - Heildelberg (DE)

ER -

Saif H, He Y, Alani H. Semantic sentiment analysis of Twitter. In Cudré-Mauroux P, Heflin J, Sirin E, EA, editors, The semantic web – ISWC 2012: 11th international semantic web conference, Boston, MA, USA, November 11-15, 2012, proceedings, part 1. Vol. 7649. Heildelberg (DE): Springer. 2012. p. 508-524. (Lecture notes in computer science). https://doi.org/10.1007/978-3-642-35176-1-32