The Frontiers of Society, Science and Technology, 2020, 2(12); doi: 10.25236/FSST.2020.021212.
Jihao Zhang1, Hongzhi Zhao2, Zhicheng Chen3, Zihan Song4
1 Department of Foreign Language, Huazhong University of Science and Technology, Wuhan 430074, China
2 Department of Computer Science and Technology, North China Electric Power University, Beijing 102206, China
3 Department of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
4 Department of Mathematics and Statistics, South Central University for Nationalities, Wuhan 430074, China
Considered the influence of COVID-19 epidemic on video game markets, this paper proposes using Python to find the best model of predicting the most popular game tags on Steam game platform. Four of the models of predicting the best-selling games on Steam are based on Lasso linear regression, support vector machine, decision tree and random forest. Then people can predict the most popular tags by sum the tags of these games. Another one of the models of predicting the most popular game tags directly are based on natural language processing and random forest. This research succeeds to provide a game tags predicting model combining the catastrophic events and machine learning for the first time.
Machine learning, Linear regression, Svm, Natural language processing
Jihao Zhang, Hongzhi Zhao, Zhicheng Chen, Zihan Song. Prediction of the Most Popular Game Tags on Steam under the Influence of Covid-19 Based on Machine Learning and Natural Language Processing. The Frontiers of Society, Science and Technology (2020) Vol. 2 Issue 12: 70-80. https://doi.org/10.25236/FSST.2020.021212.
[1] Miloš Milošević, Nenad Živić, Igor Andjelkovića (2017). Early churn prediction with personalized targeting in mobile social games, Expert Systems with Applications, no.83, pp.326-332.
[2] Suchacka, Grażyna, Sławomir Stemplewski (2017). Application of neural network to predict purchases in online store, Information Systems Architecture and Technology: Proceedings of 37th International Conference on Information Systems Architecture and Technology–ISAT 2016–Part IV, pp.221-231.
[3] Borbora, Zoheb H, Jaideep Srivastava (2012). User behavior modelling approach for churn prediction in online games, IEEE International Conference on Privacy, Security, Risk and Trust and IEEE International Confernece on Social Computing, Amsterdam, Netherland, pp.51-60
[4] Croda, Rosa María Cantón, Damián Emilio Gibaja Romero (2019). Sales prediction through neural networks for a small dataset, IJIMAI, vol.5, no.4, pp.35-41.
[5] Marcoux, Julie, and Sid-Ahmed Selouani (2009). A hybrid subspace-connectionist data mining approach for sales forecasting in the video game industry, IEEE WRI World Congress on Computer Science and Information Engineering, the United States, no.5, pp.666-670.
[6] Thomopoulos, Nick T (2015). Demand forecasting for inventory control, Demand Forecasting for Inventory Control, pp.1-10.
[7] Dannenberg, and Jeff (2010). Internet based prediction market, U.S. Patent Application 12/331,782, filed June 10.
[8] H. Rodriguez, V. Puig, J. J. Flores, and R. Lopez (2016). Combined holt-winters and GA trained ANN approach for sensor validation and reconstruction: Application to water demand flowmeters, 3rd Conference on Control and Fault-Tolerant Systems, Barcelona, Spain, pp.202-207.
[9] Ioannis Krasonikolakis, Adam Vrechopoulos, and Athanasia Pouloudi (2014). Store selection criteria and sales prediction in virtual worlds, Information & Management, vol.51, no.6, pp.641-652.
[10] Geva, Tomer, Gal Oestreicher-Singer, Niv Efron, et al (2015). Using forum and search data for sales prediction of high-involvement products, MIS Quarterly, Forthcoming.
[11] Rephael Sweary, Michael Eden, and Yaron Golan, Multi-Stage Future Events Outcome Prediction Game, US Patent App. 12/223, 612, 2009
[12] Zhou, Longjun, Shanshan Wu, Ming Zhou (2020). 'School’s Out, But Class’ On', The Largest Online Education in the World Today: Taking China’s Practical Exploration During The COVID-19 Epidemic Prevention and Control As an Example, But Class’ On', The Largest Online Education in the World Today: Taking China’s Practical Exploration During The COVID-19 Epidemic Prevention and Control As an Example.
[13] Cantin, Guillaume, Nathalie Verdiére, Valentina Lanza, et al (2016). Mathematical modeling of human behaviors during catastrophic events: stability and bifurcations, International Journal of Bifurcation and Chaos, vol.26, no.10, pp.1630025
[14] Verdière, Nathalie, Valentina Lanza, Rodolphe Charrier, et al (2014). Mathematical modeling of human behaviors during catastrophic events.
[15] Ahn, Sangho, Juyoung Kang, Sangun Park (2017). WHAT MAKES THE DIFFERENCE BETWEEN POPULAR GAMES AND UNPOPULAR GAMES? ANALYSIS OF ONLINE GAME REVIEWS FROM STEAM PLATFORM USING WORD2VEC AND BASS MODEL.
[16] Cheuque, Germán, José Guzmán, Denis Parra (2019).Recommender systems for Online video game platforms: The case of STEAM, In Companion Proceedings of The 2019 World Wide Web Conference, San Francisco, the United States, pp.763-771.
[17] Lin, Dayi, Cor-Paul Bezemer, Ying Zou, et al (2009). Hassan, An empirical study of game reviews on the Steam platform, Empirical Software Engineering, vol.24, no.1, pp.170-207.