A comparative study of Persian sentiment analysis based on different feature combinations

Dashtipour, K.; Gogate, M.; Adeel, A.; Hussain, A.; Alqarafi, A.; Durrani, T.

Abstract

In recent years, the use of internet and correspondingly the number of online reviews, comments and opinions have increased significantly. It is indeed very difficult for humans to read these opinions and classify them accurately. Consequently, there is a need for an automated system to process this big data. In this paper, a novel sentiment analysis framework for Persian language has been proposed. The proposed framework comprises three basic steps: pre-processing, feature extraction, and support vector machine (SVM) based classification. The performance of the proposed framework has been evaluated taking into account different features combinations. The simulation results have revealed that the best performance could be achieved by integrating unigram, bigram, and trigram features.

Citation

Dashtipour, K., Gogate, M., Adeel, A., Hussain, A., Alqarafi, A., & Durrani, T. (2017, July). A comparative study of Persian sentiment analysis based on different feature combinations. Presented at International Conference in Communications, Signal Processing, and Systems, Harbin, China

• Presentation Conference Type: Conference Paper (published)
• Conference Name: International Conference in Communications, Signal Processing, and Systems
• Start Date: Jul 14, 2017
• End Date: Jul 16, 2017
• Online Publication Date: Jun 7, 2018
• Publication Date: 2019
• Deposit Date: Jul 19, 2019
• Journal: Lecture Notes in Electrical Engineering
• Publisher: Springer
• Pages: 2288-2294
• Series Title: Lecture Notes in Electrical Engineering
• Series Number: 463
• ISBN: 978-981-10-6570-5
• DOI: https://doi.org/10.1007/978-981-10-6571-2_279
• Keywords: Sentiment analysis, Persian, Feature selection, N-gram
• Public URL: http://researchrepository.napier.ac.uk/Output/1792069
• Related Public URLs: https://www.storre.stir.ac.uk/handle/1893/27774