PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

The gaming industry is becoming more and more popular as the number of players increases. Game recommendations allow players to quickly decide if it is worth playing. This article explores how reviews of players who have played the game can be used to decide whether the game should be recommended. Nevertheless, genre-oriented models have not been incorporated in the recommendation. Since different genres have different characteristics that attract different groups of players, generalized recommendation models may not be effective enough in dealing with specific genres of games. This article proposes a genre-based recommendation model using a supervised machine learning model. All game datasets will be divided into six genres (Action, RPG, Adventure, FPS, Horror, and Strategy). Each game genre is trained separately with three feature selection methods (Bag of Words, N-Gram and Part of Speech) and three classification algorithms (Naive Bayes, Support Vector Machine and Decision Tree). The experiment results found that genre-based models mostly outperform the general model (without differentiating by genre). The best feature selection and combination of classification algorithms is also obtained for each genre, with Bag of Words and Naive Bayes topping most genres. For example, the accuracy achieved by the FPS model is 0.854 compared to the general (all genres) model with an accuracy of 0.828.

• Abualigah, L., Elaziz, M. A., Sumari, P., Geem, Z. W., & Gandomi, A. H. (2022). Reptile Search Algorithm (RSA): A nature-inspired meta-heuristic optimizer. Expert Systems with Applications, 191, Article 116158. https://doi.org/10.1016/j.eswa.2021.116158
  
  Asudani, D. S., Nagwani, N. K., & Singh, P. (2023). Impact of word embedding models on text analytics in deep learning environment: A review. Artificial Intelligence Review, 56(9), 10345-10425. https://doi.org/10.1007/s10462-023-10419-1
  
  Bais, R., Odek, P., & Ou, S. (2017). Sentiment Classification on Steam Reviews. Semantic Sholar.
  
  Biradar, G. R., Raagini, J., Varier, A., & Sudhir, M. (2019, June 29-30). Classification of book genres using book cover and title. [Paper presentation]. IEEE International Conference on Intelligent Systems and Green Technology (ICISGT), Visakhapatnam, India. https://doi.org/10.1109/ICISGT44072.2019.00031
  
  Britto, L. F., & Pacifico, L. (2020, November 7-10). Evaluating video game acceptance in game reviews using sentiment analysis techniques. [Paper presentation]. Proceedings of SBGames, Recife, Brazil.
  
  Cavnar, W. B., & Trenkle, J. M. (1994, April 11-13). N-gram-based text categorization. [Paper presentation].Proceedings of SDAIR-94, 3rd Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, U.S.A.
  
  Chakraborty, P., Nawar, F., & Chowdhury, H. A. (2021). A ternary sentiment classification of Bangla text data using support vector machine and random forest classifier. In J. K. Mandal, P. Hsiung & R. S. Dhar (Eds.), Topical Drifts in Intelligent Computing (pp. 69-77). Springer.
  
  Gaspar, P., Carbonell, J., & Oliveira, J. L. (2012). On the parameter optimization of support vector machines for binary classification. Journal of Integrative Bioinformatics, 9(3), 33–43. https://doi.org/10.1515/jib-2012-201
  
  Chu, W. T., & Guo, H. J. (2017, October). Movie genre classification based on poster images with deep neural networks. In proceedings of the workshop on multimodal understanding of social, affective and subjective attributes (pp. 39-45). ACM Publishing. https://doi.org/10.1145/3132515.3132516
  
  Deniz, A., Angin, M., & Angin, P. (2021). Evolutionary multiobjective feature selection for sentiment analysis. IEEE Access, 9, 142982–142996. https://doi.org/10.1109/ACCESS.2021.3118961
  
  Hadwan, M., Al-Sarem, M., Saeed, F., & Al-Hagery, M. A. (2022). An improved sentiment classification approach for measuring user satisfaction toward governmental services’ mobile apps using machine learning methods with feature engineering and SMOTE technique. Applied Sciences, 12(11), Article 5547. https://doi.org/10.3390/app12115547
  
  Jiang, Y., & Zheng, L. (2020). Deep learning for video game genre classification. Multimedia Tools and Applications, 82(14), 21085-21099. https://doi.org/10.1007/s11042-023-14560-5
  
  Patel, H. H., & Prajapati, P. (2018). Study and analysis of decision tree based classification algorithms. International Journal of Computer Sciences and Engineering, 6(10), 74–78.
  
  Puppala, L. K., Muvva, S. S. R., Chinige, S. R., & Rajendran, P. S. (2021, July 8-10). A novel music genre classification using convolutional neural network. [Paper presentation]. 6th International Conference on Communication and Electronics Systems (ICCES), Coimbatre, India. https://doi.org/10.1109/ICCES51350.2021.9489022
  
  Raschka, S. (2014). Naive bayes and text classification i-introduction and theory. ArXiv Preprint. https://doi.org/10.48550/arXiv.1410.5329
  
  Shahzad, A., Zafar, B., Ali, N., Jamil, U., Alghadhban, A. J., Assam, M., Ghamry, N. A., & Eldin, E. T. (2022). COVID-19 vaccines related user’s response categorization using machine learning techniques. Computation, 10(8), Article 141. https://doi.org/10.3390/computation10080141
  
  Simoes, G. S., Wehrmann, J., Barros, R. C., & Ruiz, D. D. (2016, July 24-29). Movie genre classification with convolutional neural networks. [Paper presentation]. International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada. https://doi.org/10.1109/IJCNN.2016.7727207
  
  Viggiato, M., Lin, D., Hindle, A., & Bezemer, C. P. (2021). What causes wrong sentiment classifications of game reviews? IEEE Transactions on Games, 14(3), 350–363. https://doi.org/10.1109/TG.2021.3072545
  
  Zuo, Z. (2018). Sentiment analysis of steam review datasets using naive bayes and decision tree classifier. Ideals.