Title :
Sentiment Analysis of Turkish Political News
Author :
Kaya, M. ; Fidan, G. ; Toroslu, I. Hakki
Author_Institution :
Dept. of Comput. Eng., Middle East Tech. Univ., Ankara, Turkey
Abstract :
In this paper, sentiment classification techniques are incorporated into the domain of political news from columns in different Turkish news sites. We compared four supervised machine learning algorithms of Naïve Bayes, Maximum Entropy, SVM and the character based N-Gram Language Model for sentiment classification of Turkish political columns. We also discussed in detail the problem of sentiment classification in the political news domain. We observe from empirical findings that the Maximum Entropy and N-Gram Language Model outperformed the SVM and Naïve Bayes. Using different features, all the approaches reached accuracies of 65% to 77%.
Keywords :
Bayes methods; Web sites; learning (artificial intelligence); maximum entropy methods; pattern classification; politics; support vector machines; SVM; Turkish news sites; Turkish political columns; Turkish political news; character based n-gram language model; maximum entropy; naïve Bayes; sentiment analysis; sentiment classification techniques; supervised machine learning algorithms; Machine Learning; NLP; News Domain; Sentiment Analysis; Turkish;
Conference_Titel :
Web Intelligence and Intelligent Agent Technology (WI-IAT), 2012 IEEE/WIC/ACM International Conferences on
Conference_Location :
Macau
Print_ISBN :
978-1-4673-6057-9
DOI :
10.1109/WI-IAT.2012.115