Sentiment analysis in Turkish at different granularity levels

Warning The system is temporarily closed to updates for reporting purpose.

Dehkharghani, Rahim and Yanıkoğlu, Berrin and Saygın, Yücel and Oflazer, Kemal (2016) Sentiment analysis in Turkish at different granularity levels. Natural Language Engineering . ISSN 1351-3249 (Print) 1469-8110 (Online) Published Online First http://dx.doi.org/10.1017/S1351324916000309

[thumbnail of SA_in_Turkish_8.11.pdf] PDF
SA_in_Turkish_8.11.pdf
Restricted to Registered users only

Download (689kB) | Request a copy

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.
Item Type: Article
Subjects: Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Computer Science & Eng.
Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 12 Nov 2016 16:34
Last Modified: 12 Nov 2016 16:34
URI: https://research.sabanciuniv.edu/id/eprint/30626

Actions (login required)

View Item
View Item