Document Type : Technical Paper
Authors
1 Electrical and Computer Engineering Department, Semnan University, Semnan, Iran.
2 Semnan University
Abstract
Research in recommender systems has largely relied on standardized datasets such as MovieLens, Amazon Reviews, and Last.fm. However, these datasets are unsuitable for in-game recommendations, particularly in Multiplayer Online Battle Arenas (MOBAs), due to the sequential, team-based, and adversarial nature of gameplay. To identify essential characteristics for in-game recommendation datasets, we perform a cross-domain analysis of widely used recommendation datasets, evaluating their structural and distributional properties, including interaction space, matrix shape, sparsity, and Gini-based feature–shape diversity. Building on these insights, we curate DOTA-Draft, a research-ready dataset from raw professional Dota 2 matches, encoding sequential pick/ban states, patch versions, and match outcomes. Using this dataset, we conduct top-k drafting recommendation tasks and provide baseline results with Bayesian Personalized Ranking (BPR) and GRU4Rec. To facilitate adoption, DOTA-Draft is packaged in a RecBole-compatible format. This work establishes principled benchmarks for in-game recommendation, demonstrates the inadequacy of traditional user–item paradigms in dynamic, adversarial environments, and provides a foundation for developing models that account for sequential, multi-agent decision-making.
Keywords
- In-game recommendation systems
- Multiplayer Online Battle Arenas (MOBA)
- Dota 2 Interaction Dataset
- Session-based recommendation models
- Benchmarking with RecBole framework
Main Subjects
[1] F. M. Harper and J. A. Konstan, "The movielens datasets: History and context, " Acm Trans. Interact. Intell. Syst., vol. 5, no. 4, pp. 1–19, 2015, doi: 10.1145/2827872.
[2] Y. Hou, J. Li, Z. He, A. Yan, X. Chen, and J. McAuley, "Bridging Language and Items for Retrieval and Recommendation, " no. 1, 2024, [Online]. Available: http://arxiv.org/abs/2403.03952
[3] I. Stewart, "Cups and downs, " Coll. Math. J., vol. 43, no. 1, pp. 15–19, 2012, doi: 10.4169/college.math.j.43.1.015.
[4] J. Ni, J. Li, and J. McAuley, "Justifying recommendations using distantly-labeled reviews and fine-grained aspects, " in Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), 2019, pp. 188–197.
[5] E. Gibson, M. D. Griffiths, F. Calado, and A. Harris, "The relationship between videogame micro-transactions and problem gaming and gambling: A systematic review, " Comput. Human Behav., vol. 131, p. 107219, 2022.
[6] S. Kühn, D. T. Kugler, K. Schmalen, M. Weichenberger, C. Witt, and J. Gallinat, "Does playing violent video games cause aggression? A longitudinal intervention study, " Mol. Psychiatry, vol. 24, no. 8, pp. 1220–1234, 2019.
[7] I. Granic, A. Lobel, and R. C. M. E. Engels, "The benefits of playing video games, " Am. Psychol., vol. 69, no. 1, pp. 66–78, 2014, doi: 10.1037/a0034857.
[8] M. Quwaider, A. Alabed, and R. Duwairi, "The impact of video games on the players behaviors: A survey, " in Procedia Computer Science, Elsevier, 2019, pp. 575–582. doi: 10.1016/j.procs.2019.04.077.
[9] D. Forni, "Horizon Zero Dawn: The Educational Influence of Video Games in Counteracting Gender Stereotypes, " Trans. Digit. Games Res. Assoc., vol. 5, no. 1, 2020, doi: 10.26503/todigra.v5i1.111.
[10] D. Madden, X. Liu, H. Yu, M. F. Sonbudak, G. M. Troiano, and C. Harteveld, "Why are you playing games? you are a girl!: Exploring gender biases in esports, " in Conference on Human Factors in Computing Systems - Proceedings, 2021, pp. 1–15. doi: 10.1145/3411764.3445248.
[11] L. Pascarella, F. Palomba, M. Di Penta, and A. Bacchelli, "How is video game development different from software development in open source?, " in Proceedings - International Conference on Software Engineering, 2018, pp. 392–402. doi: 10.1145/3196398.3196418.
[12] V. Nardone, B. Muse, M. Abidi, F. Khomh, and M. Di Penta, "Video Game Bad Smells: What They Are and How Developers Perceive Them, " ACM Trans. Softw. Eng. Methodol., vol. 32, no. 4, pp. 1–35, 2023, doi: 10.1145/3563214.
[13] R. Ardianto, T. Rivanie, Y. Alkhalifi, F. S. Nugraha, and W. Gata, "SENTIMENT ANALYSIS ON E-SPORTS FOR EDUCATION CURRICULUM USING NAIVE BAYES AND SUPPORT VECTOR MACHINE, " J. Ilmu Komput. dan Inf., vol. 13, no. 2, pp. 109–122, 2020, doi: 10.21609/jiki.v13i2.885.
[14] J. J. Thompson, B. H. Leung, M. R. Blair, and M. Taboada, "Sentiment analysis of player chat messaging in the video game StarCraft 2: Extending a lexicon-based model, " Knowledge-Based Syst., vol. 137, pp. 149–162, 2017, doi: 10.1016/j.knosys.2017.09.022.
[15] A. Bucchiarone, K. M. L. Cooper, D. Lin, E. F. Melcer, and K. Sung, "Games and Software Engineering, " ACM SIGSOFT Softw. Eng. Notes, vol. 48, no. 1, pp. 85–89, 2023, doi: 10.1145/3573074.3573096.
[16] A. D’Angelo, C. Di Sipio, C. Politowski, and R. Rubei, PlayMyData: a curated dataset of multi-platform video games, vol. 1, no. 1. Association for Computing Machinery, 2024. doi: 10.1145/3643991.3644869.
[17] V. Araujo, H. Salinas, A. Labarca, A. Villa, and D. Parra, "Hierarchical Transformers for Group-Aware Sequential Recommendation: Application in MOBA Games, " UMAP2022 - Adjun. Proc. 30th ACM Conf. User Model. Adapt. Pers., pp. 293–301, 2022, doi: 10.1145/3511047.3537667.
[18] L. Hanke and L. Chaimowicz, "A recommender system for hero line-ups in MOBA games, " Proc. 13th AAAI Conf. Artif. Intell. Interact. Digit. Entertain. AIIDE 2017, pp. 43–49, 2017, doi: 10.1609/aiide.v13i1.12938.
[19] M. Viggiato and C. P. Bezemer, "Trouncing in dota 2: An investigation of blowout matches, " Proc. 16th AAAI Conf. Artif. Intell. Interact. Digit. Entertain. AIIDE 2020, pp. 294–300, 2020, doi: 10.1609/aiide.v16i1.7444.
[20] J. M. Wang-Cheng Kang, "Self-Attentive Sequential Recommendation, " IEEE Int. Conf. Data Min., vol. 2018-Novem, pp. 197–206, 2018.
[21] M. Wan and J. McAuley, "Item recommendation on monotonic behavior chains, " RecSys 2018 - 12th ACM Conf. Recomm. Syst., pp. 86–94, 2018, doi: 10.1145/3240323.3240369.
[22] A. Pathak, K. Gupta, and J. McAuley, "Generating and personalizing bundle recommendations on steam, " SIGIR 2017 - Proc. 40th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr., pp. 1073–1076, 2017, doi: 10.1145/3077136.3080724.
[23] BwandoWando, "Dota 2 Pro League Matches 2016-2025. " Accessed: Apr. 20, 2026. [Online]. Available: https://www.kaggle.com/datasets/bwandowando/dota-2-pro-league-matches-2023/
[24] K. Akhmedov and A. H. Phan, "Machine learning models for DOTA 2 outcomes prediction, " arXiv Prepr. arXiv2106.01782, 2021.
[25] K. Conley and D. Perry, "How Does He Saw Me? A Recommendation Engine for Picking Heroes in Dota 2, " CS229 Previous Proj., vol. 7, 2013, [Online]. Available: https://cs229.stanford.edu/proj2013/PerryConley-HowDoesHeSawMeARecommendationEngineForPickingHeroesInDota2.pdf
[26] A. Drachen, M. Yancey, J. Maguire, D. Chu, I. Y. Wang, T. Mahlmann, M. Schubert, and D. Klabajan, "Skill-based differences in spatio-Temporal team behaviour in defence of the Ancients 2 (DotA 2), " in Conference Proceedings - 2014 IEEE Games, Media, Entertainment Conference, IEEE GEM 2014, 2015, pp. 1–8. doi: 10.1109/GEM.2014.7048109.
[27] T. E. Batsford, "Calculating Optimal Jungling Routes in DOTA2 Using Neural Networks and Genetic Algorithms, " Game Behav., vol. 1, no. 1, 2014.
[28] T. Flint, "Creating a Hero Recommender System for Newer Player in Dota 2, " 2022.
[29] H. Lee, D. Hwang, H. Kim, B. Lee, and J. Choo, “DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games, " in WWW 2022 - Proceedings of the ACM Web Conference 2022, Association for Computing Machinery, 2022, pp. 3428–3439. doi: 10.1145/3485447.3512278.
[30] A. Summerville, M. Cook, and B. Steenhuisen, "Draft-Analysis of the ancients: Predicting draft picks in DotA 2 using machine learning, " AAAI Work. - Tech. Rep., vol. WS-16-21-WS-16-23, no. Godec, pp. 100–106, 2016.
[31] Z. Chen, T.-H. D. Nguyen, Y. Xu, C. Amato, S. Cooper, Y. Sun, and M. S. El-Nasr, "The Art of Drafting: A Team-Oriented Hero Recommendation System for Multiplayer Online Battle Arena Games, " 2018, [Online]. Available: http://arxiv.org/abs/1806.10130
[32] W. X. Zhao, S. Mu, Y. Hou, Z. Lin, Y. Chen, X. Pan, K. Li, Y. Lu, H. Wang, C. Tian, Y. Min, Z. Feng, X. Fan, X. Chen, P. Wang, W. Ji, Y. Li, X. Wang, and J. R. Wen, "RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms, " Int. Conf. Inf. Knowl. Manag. Proc., pp. 4653–4664, 2021, doi: 10.1145/3459637.3482016.
[33] W. X. Zhao, Y. Hou, X. Pan, C. Yang, Z. Zhang, Z. Lin, J. Zhang, S. Bian, J. Tang, W. Sun, Y. Chen, L. Xu, G. Zhang, Z. Tian, C. Tian, S. Mu, X. Fan, X. Chen, and J. R. Wen, RecBole 2.0: Towards a More Up-to-Date Recommendation Library, vol. 1, no. 1. Association for Computing Machinery, 2022. doi: 10.1145/3511808.3557680.
[34] S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme, "BPR: Bayesian personalized ranking from implicit feedback, " Proc. 25th Conf. Uncertain. Artif. Intell. UAI 2009, pp. 452–461, 2009.
[35] F. A. N. Ge, C. Zhang, K. Wang, L. I. Yingjie, J. Chen, and X. U. Zenglin, "CUPID: Improving Battle Fairness and Position Satisfaction in Online MOBA Games with a Re-matchmaking System, " Proc. ACM Human-Computer Interact., vol. 8, no. CSCW2, 2024, doi: 10.1145/3686978.
[36] K. W. Błaszczyk and D. Szajerman, "Champion Recommendation in League of Legends Using Machine Learning, " Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 14076 LNCS, pp. 155–170, 2023, doi: 10.1007/978-3-031-36027-5_12.
[37] C. Chen, F. Mo, X. Fan, C. Bai, and H. Yamana, "Mobarec-gcnfp: Champion recommendation for multi-player online battle arena games using graph convolution network with fewer parameters, " in 2023 IEEE 8th International Conference on Big Data Analytics (ICBDA), 2023, pp. 147–153.
[38] J. Y. Chin, Y. Chen, and G. Cong, "The datasets dilemma: How much DoWe really know about recommendation datasets?, " WSDM 2022 - Proc. 15th ACM Int. Conf. Web Search Data Min., no. 3, pp. 141–149, 2022, doi: 10.1145/3488560.3498519.
[39] B. Becker and R. Kohavi, "Adult, " 1996, doi: 10.24432/C5XW20.
[40] J.-B. Tien, joycenv, and O. Chapelle, "Display Advertising Challenge. " Accessed: Apr. 21, 2026. [Online]. Available: https://kaggle.com/competitions/criteo-display-ad-challenge.
[41] S. Wang and W. Cukierski, "Click-Through Rate Prediction. " Accessed: Apr. 21, 2026. [Online]. Available: https://kaggle.com/competitions/avazu-ctr-prediction
[42] W. Zhang, S. Yuan, J. Wang, and X. Shen, "Real-Time Bidding Benchmarking with iPinYou Dataset, " 2014, [Online]. Available: http://arxiv.org/abs/1407.7073
[43] J. McAuley and J. Leskovec, "From amateurs to connoisseurs: Modeling the evolution of user expertise through online reviews, " WWW 2013 - Proc. 22nd Int. Conf. World Wide Web, pp. 897–907, 2013.
[44] E. Cho, S. A. Myers, and J. Leskovec, "Friendship and mobility: user movement in location-based social networks, " in Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, 2011, pp. 1082–1090.
[45] R. Misra, M. Wan, and J. McAuley, "Decomposing fit semantics for product size recommendation in metric spaces, " RecSys 2018 - 12th ACM Conf. Recomm. Syst., pp. 422–426, 2018, doi: 10.1145/3240323.3240398.
[46] J. Ni, L. Muhlstein, and J. McAuley, "Modeling heart rate and activity data for personalized fitness recommendation, " Web Conf. 2019 - Proc. World Wide Web Conf. WWW 2019, vol. 2, pp. 1343–1353, 2019, doi: 10.1145/3308558.3313643.
[47] J. Stamper, A. Niculescu-Mizil, S. Ritter, G. J. Gordon, and K. R. Koedinger, "Algebra I 2008-2009: Challenge data set from KDD Cup 2010 Educational Data Mining Challenge, " 2010. [Online]. Available: http://pslcdatashop.web.cmu.edu/KDDCup/downloads.jsp
[48] B. P. Majumder, S. Li, J. Ni, and J. McAuley, "Generating personalized recipes from historical user preferences, " EMNLP-IJCNLP 2019 - 2019 Conf. Empir. Methods Nat. Lang. Process. 9th Int. Jt. Conf. Nat. Lang. Process. Proc. Conf., pp. 5976–5982, 2019, doi: 10.18653/v1/d19-1613.
[49] F. Zhu, Y. Wang, C. Chen, G. Liu, and X. Zheng, "A graphical and attentional framework for dual-target cross-domain recommendation, " IJCAI Int. Jt. Conf. Artif. Intell., vol. 2021-Janua, pp. 3001–3008, 2020, doi: 10.24963/ijcai.2020/415.
[50] J. Rappaz, J. McAuley, and K. Aberer, "Recommendation on live-streaming platforms: Dynamic availability and repeat consumption, " in RecSys 2021 - 15th ACM Conference on Recommender Systems, New York, NY, USA: ACM, Sep. 2021, pp. 390–399. doi: 10.1145/3460231.3474267.
[51] S. Oramas, V. C. Ostuni, T. Di Noia, X. Serra, and E. Di Sciascio, "Sound and music recommendation with knowledge graphs, " ACM Trans. Intell. Syst. Technol., vol. 8, no. 2, pp. 21:1--21:21, 2016, doi: 10.1145/2926718.
[52] I. Cantador, P. Brusilovsky, and T. Kuflik, "Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011), " in Proceedings of the fifth ACM conference on Recommender systems, in RecSys 2011. New York, NY, USA: ACM, Oct. 2011, pp. 387–388. doi: 10.1145/2043932.2044016.
[53] M. Schedl, "The LFM-1b Dataset for Music Retrieval and Recommendation, " in Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, New York, NY, USA: ACM, Jun. 2016, pp. 103–110. doi: 10.1145/2911996.2912004.
[54] M. Moscati, E. Parada-Cabaleiro, Y. Deldjoo, E. Zangerle, and M. Schedl, "Music4All-Onion - A Large-Scale Multi-faceted Content-Centric Music Recommendation Dataset, " in International Conference on Information and Knowledge Management, Proceedings, M. Al Hasan and L. Xiong, Eds., New York, NY, USA: ACM, Oct. 2022, pp. 4339–4343. doi: 10.1145/3511808.3557656.
[55] F. Wu, Y. Qiao, J.-H. Chen, C. Wu, T. Qi, J. Lian, D. Liu, X. Xie, J. Gao, W. Wu, and M. Zhou, "MIND: A Large-scale Dataset for News Recommendation, " in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Stroudsburg, PA, USA: Association for Computational Linguistics, 2020, pp. 3597–3606. doi: 10.18653/v1/2020.acl-main.331.
[56] X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T.-S. Chua, "Neural Collaborative Filtering, " in Proceedings of the 26th International Conference on World Wide Web, Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee, Apr. 2017, pp. 173–182. doi: 10.1145/3038912.3052569.
[57] D. P. KOHEN, K. N. OLNESS, S. O. COLWELL, and A. HEIMEL, "The Use of Relaxation-Mental Imagery (Self-Hypnosis) in the Management of 505 Pediatric Behavioral Encounters, " J. Dev. Behav. Pediatr., vol. 5, no. 1, p. 21???25, Feb. 1984, doi: 10.1097/00004703-198402000-00005.
[58] Y. Zhang, M. Zhang, Y. Liu, S. Ma, and S. Feng, "Localized matrix factorization for recommendation based on matrix block diagonal forms, " in Proceedings of the 22nd international conference on World Wide Web, New York, NY, USA: ACM, May 2013, pp. 1511–1520. doi: 10.1145/2488388.2488520.
[59] R. Zykov, N. Artem, and A. Alexander, "RetailRocket Recommender System Dataset, " Kaggle. Accessed: Apr. 21, 2026. [Online]. Available: https://www.kaggle.com/datasets/retailrocket/ecommerce-dataset
[60] R. Mohammad and L. McCluskey, "Phishing Websites, " UCI Machine Learning Repository. Accessed: Apr. 21, 2026. [Online]. Available: https://archive.ics.uci.edu/dataset/327/phishing+websites
[61] R. He, C. Fang, Z. Wang, and J. McAuley, "Vista: A visually, socially, and temporally-aware model for artistic recommendation, " in RecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems, 2016, pp. 309–316. doi: 10.1145/2959100.2959152.
[62] J. Hamidzadeh and M. Moradi, "Online recommender system considering changes in user’s preference, " J. AI Data Min., vol. 9, no. 2, pp. 203–212, 2021, doi: 10.22044/jadm.2020.9518.2085.
[63] S. Saffari, M. Dorrigiv and F. Yaghmaee, "Harnessing Machine Learning for Procedural Content Generation in Gaming: A Comprehensive Review, " J. AI Data Min., vol. 12, no. 4, pp. 583–597, 2024, doi: 10.22044/jadm.2025.15016.2603.
)