Measuring the customer satisfaction is one of the most important aspects for every successful enterprise trying to improve its service quality, so accumulating reviews is highly encouraged. However, as the number of reviews expand it is crucial to develop effective sentiment analysis systems capable of classifying the comments to accomplish further analysis. This is one of the rare studies analyzing health service contentment, especially in Turkish. Positive and negative comments collected from patients were used to train and test a classification system by using machine learning methods such as Naïve Bayes, Support Vector Machine (SMO) and J48 tree algorithms, resulting in instantaneous and high average prediction rates varying between 90.4% to 95.8%.
CITATION STYLE
Ceyhan, M., Orhan, Z., & Domnori, E. (2017). Health service quality measurement from patient reviews in Turkish by opinion mining. In IFMBE Proceedings (Vol. 62, pp. 649–653). Springer Verlag. https://doi.org/10.1007/978-981-10-4166-2_97
Mendeley helps you to discover research relevant for your work.