Sentiment Analysis of Turkish Political News

被引：63

作者：

Kaya, Mesut ^{[1
,2
]}

Fidan, Guven ^{[2
]}

Toroslu, Ismail H. ^{[1
]}

机构：

[1] Middle East Tech Univ, Dept Comp Engn, Ankara, Turkey

[2] AGMLab, R&D Dept, Ankara, Turkey

来源：

2012 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON WEB INTELLIGENCE AND INTELLIGENT AGENT TECHNOLOGY (WI-IAT 2012), VOL 1 | 2012年

关键词：

Sentiment Analysis; Turkish; Machine Learning; News Domain; NLP;

D O I：

10.1109/WI-IAT.2012.115

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 Naive 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 Naive Bayes. Using different features, all the approaches reached accuracies of 65% to 77%.

引用

页码：174 / 180

页数：7

共 24 条

[1] [Anonymous], 2002, Technical Report EGB-1094
[2] [Anonymous], 2007, ICWSM 2007 INT C WEB
[3] [Anonymous], P KDD
[4] [Anonymous], P WWW 2003
[5] [Anonymous], P 8 AS PAC FIN ASS A
[6] [Anonymous], 2009, Proceedings of the 1st Workshop on Opinion Mining and Sentiment Analysis WOMSA
[7] BALAHUR A, 2010, 7 C INT LANG RES EV
[8] Blaz Fortuna, 2009, DETECTING BIAS MEDIA
[9] A machine learning approach to sentiment analysis in multilingual Web texts
Boiy, Erik
Moens, Marie-Francine
[J]. INFORMATION RETRIEVAL, 2009, 12 (05): : 526 - 558
[10] Carpenter B., 2005, P 2005 ASS COMPUTATI, P1

← 1 2 3 →