M. Kaya, G. Fidan, и I. Toroslu. Web Intelligence and Intelligent Agent Technology (WI-IAT), 2012 IEEE/WIC/ACM International Conferences on, 1, стр. 174-180. (декабря 2012)
DOI: 10.1109/WI-IAT.2012.115
Аннотация
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%.
%0 Conference Paper
%1 6511881
%A Kaya, M.
%A Fidan, G.
%A Toroslu, I.H.
%B Web Intelligence and Intelligent Agent Technology (WI-IAT), 2012 IEEE/WIC/ACM International Conferences on
%D 2012
%K analysis ht2015 sentiment
%P 174-180
%R 10.1109/WI-IAT.2012.115
%T Sentiment Analysis of Turkish Political News
%U http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6511881
%V 1
%X 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%.
@inproceedings{6511881,
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%.},
added-at = {2015-04-01T21:15:39.000+0200},
author = {Kaya, M. and Fidan, G. and Toroslu, I.H.},
biburl = {https://www.bibsonomy.org/bibtex/219856e541d731832121def67351aea90/dallmann},
booktitle = {Web Intelligence and Intelligent Agent Technology (WI-IAT), 2012 IEEE/WIC/ACM International Conferences on},
doi = {10.1109/WI-IAT.2012.115},
interhash = {1aa869d1ee391712f18cac949a76c499},
intrahash = {19856e541d731832121def67351aea90},
keywords = {analysis ht2015 sentiment},
month = dec,
pages = {174-180},
timestamp = {2015-04-01T21:15:39.000+0200},
title = {Sentiment Analysis of Turkish Political News},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6511881},
volume = 1,
year = 2012
}