A Step-by-Step Approach for User Acceptance Evaluation in Games Based on Sentiment Analysis and Machine Learning
Resumo
User opinion analysis is an important tool to guide the decision-making process of independent game developers and game studios, once such activity leads to better product development towards the user satisfaction. Sentiment Analysis (SA) techniques have been widely used by companies to discover what customers are saying about their products, and the game industry could also benefit from such research field, once user feelings about a video game may have a relevant impact in retention and revenues. In this work, a thorough analysis on user acceptance in video games is performed by means of Natural Language Processing and SA approaches, where game reviews are exploited to understand what are the most relevant topics users are taking into consideration when they evaluate a game. A Sentiment Classification approach is performed, and the proposed methodology is discussed step-by-step, seeking out to motivate further researches in the field. Also, a new data set is proposed, composed by game reviews written in Brazilian Portuguese, given the relevance of Brazilian market in game industry.
Referências
Demšar, J. Statistical comparisons of classiers over multiple data sets. The Journal of Machine Learning Research vol. 7, pp. 130, 2006.
HaCohen-Kerner, Y., Miller, D., and Yigal, Y. The inuence of preprocessing on text classication using a bag-of-words representation. PLOS ONE 15 (5): 122, 05, 2020.
Kaur, J. and Buttar, P. K. A systematic review on stopword removal algorithms. Int. J. Futur. Revolut. Comput. Sci. Commun. Eng 4 (4), 2018.
Kowsari, K., Meimandi, K. J., Heidarysafa, M., Mendu, S., Barnes, L. E., and Brown, D. E. Text classication algorithms: A survey. CoRR vol. abs/1904.08067, 2019.
Livingston, I., Nacke, L., and Mandryk, R. The impact of negative game reviews and user comments on player experience. In Proceedings of the 2011 ACM SIGGRAPH Symposium on Video Games. ACM, pp. 25-29, 2011.
Martineau, J. and Finin, T. Delta tdf: An improved feature space for sentiment analysis. In Proceedings of the International AAAI Conference on Web and Social Media. Vol. 3. pp. 14, 2009.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research vol. 12, pp. 2825-2830, 2011.
Strååt, B. and Verhagen, H. Using user created game reviews for sentiment analysis: A method for researching user attitudes. In GHITALY17: 1st Workshop on Games-Human Interaction. ACM, pp. 16, 2017.
Urriza, I. M. and Clarino, M. A. A. Aspect-based sentiment analysis of user created game reviews. In 2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA). pp. 76-81, 2021.
Vieira, A. C. and Brandão, W. C. GA-Eval: a neural network based approach to evaluate video games acceptance. In Proceedings of the 18th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames 2019). SBC, pp. 595-598, 2019.
Wang, X. and Goh, D. Video game acceptance: A meta-analysis of the extended technology acceptance model. Cyberpsychology, Behavior, and Social Networking vol. 20, pp. 662-671, 11, 2017.
Yang, L. and Shami, A. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing vol. 415, pp. 295-316, 2020.
