Polarity detection of Turkish comments on technology companies

Author

Isguder-Sahin, Gozde Gul ; Zafer, Harun Resit ; Adah, Esref

Author_Institution

Dept. of Comput. Eng., Istanbul Tech. Univ., Istanbul, Turkey

fYear

2014

fDate

20-22 Oct. 2014

Firstpage

136

Lastpage

139

Abstract

In this study, comments about technology brands are collected from a popular Turkish website, eksisözlük, and classified as positive or negative. Turkish text is preprocessed with different kinds of filters and then modeled with 1-gram, 2-grams and 3-grams language models. Naive Bayes (NB), Support Vector Machines (SVM) and K nearest neighbor (KNN) classifiers are applied on different configurations of preprocessing techniques, language models and linguistic attributes for comparison. We measured best F-measure as 0,696 on our test dataset.

Keywords

Bayes methods; Web sites; information filters; natural language processing; pattern classification; support vector machines; text analysis; 1-gram language model; 2-grams language model; 3-grams language model; F-measure; K nearest neighbor classifiers; KNN classifiers; NB; SVM; Turkish Website; Turkish comments polarity detection; Turkish text preprocessing; filters; linguistic attributes; naive Bayes; support vector machines; technology brands; technology companies; Companies; Computers; Educational institutions; Sentiment analysis; Support vector machines; Training; Vocabulary; Preprocessing; Turkish; polarity detection; sentiment analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Asian Language Processing (IALP), 2014 International Conference on

Conference_Location

Kuching

Type

conf

DOI

10.1109/IALP.2014.6973514

Filename

6973514