Sentiment analysis in Turkish at different granularity levels

RAHIM DEHKHARGHANI, BERRIN YANIKOGLU, YUCEL SAYGIN, KEMAL OFLAZER

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Sentiment analysis has attracted a lot of research interest in recent years, especially in the context of social media. While most of this research has focused on English, there is ample data and interest in the topic for many other languages, as well. In this article, we propose a comprehensive sentiment analysis system for Turkish. We cover different levels of sentiment analysis such as aspect, sentence, and document levels as well as some linguistic issues such as conjunction and intensification in Turkish sentiment analysis. Our system is evaluated on Turkish movie reviews and the obtained accuracies range from sixty per cent to seventy-nine per cent in ternary and binary classification tasks at different levels of analysis.

Original languageEnglish
Pages (from-to)1-25
Number of pages25
JournalNatural Language Engineering
DOIs
Publication statusAccepted/In press - 21 Oct 2016
Externally publishedYes

Fingerprint

Linguistics
research interest
systems analysis
movies
social media
linguistics
Sentiment
Granularity
language
Social Media
Language
Levels of Analysis
Movies
Sixties

ASJC Scopus subject areas

  • Software
  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence

Cite this

DEHKHARGHANI, RAHIM., YANIKOGLU, BERRIN., SAYGIN, YUCEL., & OFLAZER, KEMAL. (Accepted/In press). Sentiment analysis in Turkish at different granularity levels. Natural Language Engineering, 1-25. https://doi.org/10.1017/S1351324916000309

Sentiment analysis in Turkish at different granularity levels. / DEHKHARGHANI, RAHIM; YANIKOGLU, BERRIN; SAYGIN, YUCEL; OFLAZER, KEMAL.

In: Natural Language Engineering, 21.10.2016, p. 1-25.

Research output: Contribution to journalArticle

DEHKHARGHANI, RAHIM, YANIKOGLU, BERRIN, SAYGIN, YUCEL & OFLAZER, KEMAL 2016, 'Sentiment analysis in Turkish at different granularity levels', Natural Language Engineering, pp. 1-25. https://doi.org/10.1017/S1351324916000309
DEHKHARGHANI RAHIM, YANIKOGLU BERRIN, SAYGIN YUCEL, OFLAZER KEMAL. Sentiment analysis in Turkish at different granularity levels. Natural Language Engineering. 2016 Oct 21;1-25. https://doi.org/10.1017/S1351324916000309
DEHKHARGHANI, RAHIM ; YANIKOGLU, BERRIN ; SAYGIN, YUCEL ; OFLAZER, KEMAL. / Sentiment analysis in Turkish at different granularity levels. In: Natural Language Engineering. 2016 ; pp. 1-25.
@article{dc031e2204cb4d428606057692af6a14,
title = "Sentiment analysis in Turkish at different granularity levels",
abstract = "Sentiment analysis has attracted a lot of research interest in recent years, especially in the context of social media. While most of this research has focused on English, there is ample data and interest in the topic for many other languages, as well. In this article, we propose a comprehensive sentiment analysis system for Turkish. We cover different levels of sentiment analysis such as aspect, sentence, and document levels as well as some linguistic issues such as conjunction and intensification in Turkish sentiment analysis. Our system is evaluated on Turkish movie reviews and the obtained accuracies range from sixty per cent to seventy-nine per cent in ternary and binary classification tasks at different levels of analysis.",
author = "RAHIM DEHKHARGHANI and BERRIN YANIKOGLU and YUCEL SAYGIN and KEMAL OFLAZER",
year = "2016",
month = "10",
day = "21",
doi = "10.1017/S1351324916000309",
language = "English",
pages = "1--25",
journal = "Natural Language Engineering",
issn = "1351-3249",
publisher = "Cambridge University Press",

}

TY - JOUR

T1 - Sentiment analysis in Turkish at different granularity levels

AU - DEHKHARGHANI, RAHIM

AU - YANIKOGLU, BERRIN

AU - SAYGIN, YUCEL

AU - OFLAZER, KEMAL

PY - 2016/10/21

Y1 - 2016/10/21

N2 - Sentiment analysis has attracted a lot of research interest in recent years, especially in the context of social media. While most of this research has focused on English, there is ample data and interest in the topic for many other languages, as well. In this article, we propose a comprehensive sentiment analysis system for Turkish. We cover different levels of sentiment analysis such as aspect, sentence, and document levels as well as some linguistic issues such as conjunction and intensification in Turkish sentiment analysis. Our system is evaluated on Turkish movie reviews and the obtained accuracies range from sixty per cent to seventy-nine per cent in ternary and binary classification tasks at different levels of analysis.

AB - Sentiment analysis has attracted a lot of research interest in recent years, especially in the context of social media. While most of this research has focused on English, there is ample data and interest in the topic for many other languages, as well. In this article, we propose a comprehensive sentiment analysis system for Turkish. We cover different levels of sentiment analysis such as aspect, sentence, and document levels as well as some linguistic issues such as conjunction and intensification in Turkish sentiment analysis. Our system is evaluated on Turkish movie reviews and the obtained accuracies range from sixty per cent to seventy-nine per cent in ternary and binary classification tasks at different levels of analysis.

UR - http://www.scopus.com/inward/record.url?scp=84992144103&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992144103&partnerID=8YFLogxK

U2 - 10.1017/S1351324916000309

DO - 10.1017/S1351324916000309

M3 - Article

SP - 1

EP - 25

JO - Natural Language Engineering

JF - Natural Language Engineering

SN - 1351-3249

ER -