Suchergebnisse

In this paper, we aim to determine the overall sentiment classification of Turkish political columns. That is, our goal is to determine whether the whole document has positive or negative opinion regardless of its subject. In order to enhance the performance of the classification, transfer learning is applied from unlabeled Twitter data to labeled political columns. A variation of self-taught learning has been proposed, and implemented for the classification. Different machine learning techniques, including support vector machine, maximum entropy classification, and Naive-Bayes has been used for the supervised learning phase. In our experiments we have obtained up to 26 % increase in the accuracy of the classification with the inclusion of the Twitter data into the sentiment classification of Turkish political columns using transfer learning.

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%.