Recommending Teammates with Deep Neural Networks

The effects of team collaboration on performance have been explored in a variety of settings. Online games enable people with significantly different skills to cooperate and compete within a shared context. Players can affect teammates' performance either via direct communication or by influencing teammates' actions. Understanding such effects can help us provide insights into human behavior as well as make team recommendations. In this work, we aim at recommending teammates to each individual player for maximal skill growth. We study the effect of collaboration in online games using a large dataset from Dota 2, a popular Multiplayer Online Battle Arena game. To this aim, we construct an online co-play teammate network of players, whose links are weighted based on the gain in skill achieved due to team collaboration. We then use the performance network to devise a recommendation system based on a modified deep neural network autoencoder method.

[1]  Ryan A. Rossi,et al.  A Framework for Generalizing Graph-based Representation Learning Methods , 2017, ArXiv.

[2]  Marc Herrlich,et al.  Classification of Player Roles in the Team-Based Multi-player Game Dota 2 , 2015, ICEC.

[3]  Wenwu Zhu,et al.  Structural Deep Network Embedding , 2016, KDD.

[4]  Palash Goyal,et al.  Graph Embedding Techniques, Applications, and Performance: A Survey , 2017, Knowl. Based Syst..

[5]  Brian Keegan,et al.  Ping to Win?: Non-Verbal Communication and Team Performance in Competitive Online Multiplayer Games , 2016, CHI.

[6]  Tom Minka,et al.  TrueSkillTM: A Bayesian Skill Rating System , 2006, NIPS.

[7]  Wei Lu,et al.  Deep Neural Networks for Learning Graph Representations , 2016, AAAI.

[8]  Hannes Werthner,et al.  Ranking factors of team success , 2013, WWW.

[9]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[10]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[11]  Thomas Hofmann,et al.  TrueSkill™: A Bayesian Skill Rating System , 2007 .

[12]  Brent E. Harrison,et al.  Identifying patterns in combat that are predictive of success in MOBA games , 2014, FDG.

[13]  Tim Urdan,et al.  Classroom effects on student motivation: Goal structures, social relationships, and competence beliefs , 2006 .

[14]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[15]  Emilio Ferrara,et al.  Non-negative Tensor Factorization for Human Behavioral Pattern Mining in Online Games , 2017, Inf..

[16]  Diego Klabjan,et al.  Skill-based differences in spatio-temporal team behaviour in defence of the Ancients 2 (DotA 2) , 2014, 2014 IEEE Games Media Entertainment.

[17]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[18]  J. Pearce.  Toward an Organizational Behavior of Contract Laborers: Their Psychological Involvement and Effects on Employee Co-Workers. , 1993 .

[19]  Alexandru Iosup,et al.  Analyzing Implicit Social Networks in Multiplayer Online Games , 2014, IEEE Internet Computing.

[20]  Kyung-Joong Kim,et al.  Social Network Analysis of High-Level Players in Multiplayer Online Battle Arena Game , 2014, SocInfo Workshops.

[21]  James S. Jackson,et al.  Teammates On and Off the Field? Contact With Black Teammates and the Racial Attitudes of White Student Athletes , 2003 .

[22]  Jure Leskovec,et al.  Supervised random walks: predicting and recommending links in social networks , 2010, WSDM '11.

[23]  Jian Pei,et al.  Asymmetric Transitivity Preserving Graph Embedding , 2016, KDD.

[24]  Max Welling,et al.  Variational Graph Auto-Encoders , 2016, ArXiv.

[25]  Alexander J. Smola,et al.  Distributed large-scale natural graph factorization , 2013, WWW.