|
AUTHOR(S): Krunoslav Zubrinic, Tomo Sjekavica, Mario Milicevic, Ines Obradovic
|
TITLE A Comparison of Machine Learning Algorithms in Opinion Polarity Classification of Customer Reviews |
 PDF |
ABSTRACT In this paper we analyze reviews written by customers of an online shop, by employing opinion polarity classification on document level using five machine learning algorithms: Na¨ive Bayes, Support Vector Machine, Neural networks, C4.5 algorithm and classifier based on maximum entropy. We achieved the best results using Support Vector Machine algorithm (accuracy=0.845) and maximum entropy classifier (accuracy=0.84). Although those results are not as good as results that can be achieved in topic-based categorization, compared to similar researches in opinion polarity classification, they indicate a relatively good predictive performance of classical machine learning algorithms. |
KEYWORDS opinion polarity classification, sentiment analysis, natural language processing |
|
Cite this paper Krunoslav Zubrinic, Tomo Sjekavica, Mario Milicevic, Ines Obradovic. (2018) A Comparison of Machine Learning Algorithms in Opinion Polarity Classification of Customer Reviews. International Journal of Computers, 3, 159-163 |
|
