Sentiment analysis techniques in recent works

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

13 Citations (Scopus)

Abstract

Sentiment Analysis (SA) task is to label people's opinions as different categories such as positive and negative from a given piece of text. Another task is to decide whether a given text is subjective, expressing the writer's opinions, or objective, expressing. These tasks were performed at different levels of analysis ranging from the document level, to the sentence and phrase level. Another task is aspect extraction which originated from aspect-based sentiment analysis in phrase level. All these tasks are under the umbrella of SA. In recent years a large number of methods, techniques and enhancements have been proposed for the problem of SA in different tasks at different levels. This survey aims to categorize SA techniques in general, without focusing on specific level or task. And also to review the main research problems in recent articles presented in this field. We found that machine learning-based techniques including supervised learning, unsupervised learning and semi-supervised learning techniques, Lexicon-based techniques and hybrid techniques are the most frequent techniques used. The open problems are that recent techniques are still unable to work well in different domain; sentiment classification based on insufficient labeled data is still a challenging problem; there is lack of SA research in languages other than English; and existing techniques are still unable to deal with complex sentences that requires more than sentiment words and simple parsing.

Original languageEnglish
Title of host publicationProceedings of the 2015 Science and Information Conference, SAI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages288-291
Number of pages4
ISBN (Print)9781479985470
DOIs
Publication statusPublished - 2 Sep 2015
EventScience and Information Conference, SAI 2015 - London, United Kingdom
Duration: 28 Jul 201530 Jul 2015

Other

OtherScience and Information Conference, SAI 2015
CountryUnited Kingdom
CityLondon
Period28/7/1530/7/15

Fingerprint

Supervised learning
Learning
Unsupervised learning
Research
Learning systems
Labels
Language
learning
writer
lack
language
Supervised Machine Learning
Surveys and Questionnaires
Machine Learning

Keywords

  • Lexicon-based approaches
  • machine learning approaches
  • sentiment analysis

ASJC Scopus subject areas

  • Health Informatics
  • Social Sciences (miscellaneous)
  • Computer Science Applications
  • Human-Computer Interaction
  • Computer Networks and Communications
  • Information Systems
  • Software

Cite this

Madhoushi, Z., Hamdan, A. R., & Zainudin, S. (2015). Sentiment analysis techniques in recent works. In Proceedings of the 2015 Science and Information Conference, SAI 2015 (pp. 288-291). [7237157] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SAI.2015.7237157

Sentiment analysis techniques in recent works. / Madhoushi, Zohreh; Hamdan, Abdul Razak; Zainudin, Suhaila.

Proceedings of the 2015 Science and Information Conference, SAI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 288-291 7237157.

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

Madhoushi, Z, Hamdan, AR & Zainudin, S 2015, Sentiment analysis techniques in recent works. in Proceedings of the 2015 Science and Information Conference, SAI 2015., 7237157, Institute of Electrical and Electronics Engineers Inc., pp. 288-291, Science and Information Conference, SAI 2015, London, United Kingdom, 28/7/15. https://doi.org/10.1109/SAI.2015.7237157
Madhoushi Z, Hamdan AR, Zainudin S. Sentiment analysis techniques in recent works. In Proceedings of the 2015 Science and Information Conference, SAI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 288-291. 7237157 https://doi.org/10.1109/SAI.2015.7237157
Madhoushi, Zohreh ; Hamdan, Abdul Razak ; Zainudin, Suhaila. / Sentiment analysis techniques in recent works. Proceedings of the 2015 Science and Information Conference, SAI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 288-291
@inproceedings{6745f54c240e4b7d9a25fa5619472c79,
title = "Sentiment analysis techniques in recent works",
abstract = "Sentiment Analysis (SA) task is to label people's opinions as different categories such as positive and negative from a given piece of text. Another task is to decide whether a given text is subjective, expressing the writer's opinions, or objective, expressing. These tasks were performed at different levels of analysis ranging from the document level, to the sentence and phrase level. Another task is aspect extraction which originated from aspect-based sentiment analysis in phrase level. All these tasks are under the umbrella of SA. In recent years a large number of methods, techniques and enhancements have been proposed for the problem of SA in different tasks at different levels. This survey aims to categorize SA techniques in general, without focusing on specific level or task. And also to review the main research problems in recent articles presented in this field. We found that machine learning-based techniques including supervised learning, unsupervised learning and semi-supervised learning techniques, Lexicon-based techniques and hybrid techniques are the most frequent techniques used. The open problems are that recent techniques are still unable to work well in different domain; sentiment classification based on insufficient labeled data is still a challenging problem; there is lack of SA research in languages other than English; and existing techniques are still unable to deal with complex sentences that requires more than sentiment words and simple parsing.",
keywords = "Lexicon-based approaches, machine learning approaches, sentiment analysis",
author = "Zohreh Madhoushi and Hamdan, {Abdul Razak} and Suhaila Zainudin",
year = "2015",
month = "9",
day = "2",
doi = "10.1109/SAI.2015.7237157",
language = "English",
isbn = "9781479985470",
pages = "288--291",
booktitle = "Proceedings of the 2015 Science and Information Conference, SAI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Sentiment analysis techniques in recent works

AU - Madhoushi, Zohreh

AU - Hamdan, Abdul Razak

AU - Zainudin, Suhaila

PY - 2015/9/2

Y1 - 2015/9/2

N2 - Sentiment Analysis (SA) task is to label people's opinions as different categories such as positive and negative from a given piece of text. Another task is to decide whether a given text is subjective, expressing the writer's opinions, or objective, expressing. These tasks were performed at different levels of analysis ranging from the document level, to the sentence and phrase level. Another task is aspect extraction which originated from aspect-based sentiment analysis in phrase level. All these tasks are under the umbrella of SA. In recent years a large number of methods, techniques and enhancements have been proposed for the problem of SA in different tasks at different levels. This survey aims to categorize SA techniques in general, without focusing on specific level or task. And also to review the main research problems in recent articles presented in this field. We found that machine learning-based techniques including supervised learning, unsupervised learning and semi-supervised learning techniques, Lexicon-based techniques and hybrid techniques are the most frequent techniques used. The open problems are that recent techniques are still unable to work well in different domain; sentiment classification based on insufficient labeled data is still a challenging problem; there is lack of SA research in languages other than English; and existing techniques are still unable to deal with complex sentences that requires more than sentiment words and simple parsing.

AB - Sentiment Analysis (SA) task is to label people's opinions as different categories such as positive and negative from a given piece of text. Another task is to decide whether a given text is subjective, expressing the writer's opinions, or objective, expressing. These tasks were performed at different levels of analysis ranging from the document level, to the sentence and phrase level. Another task is aspect extraction which originated from aspect-based sentiment analysis in phrase level. All these tasks are under the umbrella of SA. In recent years a large number of methods, techniques and enhancements have been proposed for the problem of SA in different tasks at different levels. This survey aims to categorize SA techniques in general, without focusing on specific level or task. And also to review the main research problems in recent articles presented in this field. We found that machine learning-based techniques including supervised learning, unsupervised learning and semi-supervised learning techniques, Lexicon-based techniques and hybrid techniques are the most frequent techniques used. The open problems are that recent techniques are still unable to work well in different domain; sentiment classification based on insufficient labeled data is still a challenging problem; there is lack of SA research in languages other than English; and existing techniques are still unable to deal with complex sentences that requires more than sentiment words and simple parsing.

KW - Lexicon-based approaches

KW - machine learning approaches

KW - sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=84957824424&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957824424&partnerID=8YFLogxK

U2 - 10.1109/SAI.2015.7237157

DO - 10.1109/SAI.2015.7237157

M3 - Conference contribution

SN - 9781479985470

SP - 288

EP - 291

BT - Proceedings of the 2015 Science and Information Conference, SAI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -