Comparative analysis of machine learning methods to classify opinions about the peruvian restaurant service on Facebook
DOI:
https://doi.org/10.26439/ciis2021.5578Keywords:
sentiment analysis, natural language processin, machine learning, vector support machine, Naive Bayes, Ramdom Forest, restaurant serviceAbstract
Customer opinions on social media services are vital for companies because they can improve and enhance business opportunities if the comments can be analyzed in time. The purpose of this work is to determine the best performing machine learning methods to apply sentiment analysis and classify positive and negative comments about the Peruvian restaurant service on Facebook. As the first contribution to this project, two datasets of comments from Peruvian restaurant chain posts on Facebook were created. The second contribution is the proposed methodology divided into two stages: in the first stage, Natural Language techniques were applied for the pre-processing of comments; In the second stage, the performance of the Naive Bayes, Random Forest, and SVM algorithms with RBF and Linear cores was analyzed to classify the opinions in the datasets. The experimental results demonstrated that the SVM classifier obtained the best performance in both the training and testing stages with 91.44% and 94% accuracy for the primary and secondary datasets, respectively, proving the viability of the proposed methodology.
Downloads
References
He, W., Zha, S., y Li, L. (2016). Social Media Competitive Analysis and Text Mining: A Case Study in the Pizza Industry. International Journal of Information Management, 33(3), 464-472. https://doi.org/10.1016/j.ijinfomgt.2013.01.001
Hossain, F. M. T., Hossain, M. I., y Nawshin, S. (2017). Machine Learning Based Class Level Prediction of Restaurant Reviews. 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), 420-423. https://doi.org/10.1109/R10-HTC.2017.8288989
Ibrahim, N. F., y Wang, X. (2019). A Text Analytics Approach for Online Retailing Service Improvement: Evidence from Twitter. Decision Support Systems, 121, 37-50. https://doi.org/10.1016/j.dss.2019.03.002
Islam, M., Jubayer, F., y Ahmed, S. (2017). A Support Vector Machine Mixed with TFIDF Algorithm to Categorize Bengali Document. 2017 International Conference on Electrical, Computer and Communication Engineering (ECCE), 191-196. https://doi.org/10.1109/ecace.2017.7912904
Khan, A. H., y Zubair, M. (2020). Classification of Multi-Lingual Tweets, into Multi-Class Model Using Naïve Bayes and Semi-Supervised Learning. Multimedia Tools and Applications, 79(43-44), 32749-32767. https://doi.org/10.1007/s11042-020-09512-2
Krishna, A., Akhilesh, V., Aich, A., y Hegde, C. (2019). Sentiment Analysis of Restaurant Reviews Using Machine Learning Techniques. En V. Sridhar, M. Padma y K. Rao (Eds.), Emerging Research in Electronics, Computer Science and Technology (pp. 687-696). Springer. https://doi.org/10.1007/978-981-13-5802-9_60
Madasu, A., y Elango, S. (2020). Efficient Feature Selection Techniques for Sentiment Analysis. Multimedia Tools and Applications, 79(9-10), 6313-6335. https://doi.org/10.1007/s11042-019-08409-z
Poornima, A., y Priya, K. S. (2020). A Comparative Sentiment Analysis of Sentence Embedding Using Machine Learning Techniques. En 2020 6th International Conference on Advanced Computing and Communication Systems, ICACCS, 493-496. https://doi.org/10.1109/ICACCS48705.2020.9074312
Yulianto, M., Girsang, A. S., y Rumagit, R. Y. (2018). Business Intelligence for Social Media Interaction in the Travel Industry in Indonesia. Journal of Intelligence Studies in Business, 8(2), 77-84. https://doi.org/10.37380/JISIB.V8I2.323
Zahoor, K., Bawany, N. Z., y Hamid, S. (2020). Sentiment Analysis and Classification of Restaurant Reviews Using Machine Learning. 2020 21st International Arab Conference on Information Technology (ACIT). https://doi.org/10.1109/ACIT50332.2020.9300098
