TeamSkill: Modeling Team Chemistry in Online Multi-player Games

DeLong, Colin; Pathak, Nishith; Erickson, Kendrick; Perrino, Eric; Shim, Kyong Jin; Srivastava, Jaideep

doi:10.1007/978-3-642-20847-8_43

Cited by 16 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With MLG tournaments often featuring 250+ Halo teams vying for top placings, heavy emphasis is placed on teamwork, resulting in an ideal dataset for observing interaction effects among teammates. The results bore out the utility of accounting for these effects, with the highest-performing algorithm from our most recent work [9], TeamSkill-EVMixed, improving on the previous "best in class" approach, TeamSkill-EV [8], by conditionally including game-specific data in the prediction task based on whether or not teams were considered closelymatched, ultimately outperforming all other approaches in over 90% of the test cases, and often by a significant margin. It performed particularly well in cases of limited game history and in "close" games where teams are almost evenly-matched, up to 40% better in such situations.…”

Section: Introductionmentioning

confidence: 85%

“…In our previous work [8], we introduced four approaches which employed varying methods of explicitly modeling group-level interaction effects during the skill assessment process -TeamSkill-K, TeamSkill-AllK, TeamSkill-AllK-EV, and TeamSkill-AllK-LS. Each had in common the idea that ratings need not be limited to individual players, but subsets of teams as well.…”

Section: A An Overview Of Teamskillmentioning

confidence: 99%

“…The best results in [8] were seen from TeamSkill-AllK-EV (or "EV"), which outperformed the baseline versions of Glicko/TrueSkill and the other TeamSkill approaches in the majority of cases. Similar to TeamSkill-AllK, EV uses all available player subgroup information, but instead sums together the aggregate skill ratings corresponding to each set of k-sized subgroup ratings, omitting the use of default subgroup ratings for subgroups with no prior playing history and weighting each k-level aggregate rating uniformly.…”

Section: Teamskill-allk-evmentioning

confidence: 99%

“…Our previous work [8], [9] took on this challenge, introducing a number of skill assessment approaches (collectively known as TeamSkill) which assigned ratings to groups of players in addition to individual players, employing several different sets of assumptions/methods to aggregate these ratings into an overall skill rating for each team. Evaluation was conducted using a curated dataset consisting of tournament and scrimmage games between professional and semi-professional Halo 3 teams over the course of 2 years.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

TeamSkill and the NBA

DeLong

Terveen

Srivastava

2013

Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining

Self Cite

View full text Add to dashboard Cite

In this paper, we build on our previous work by evaluating several approaches for assessing the skill of players and teams on the basis of both individual performance and group cohesion, or "team chemistry", using game data from the National Basketball Association (NBA). Previously developed for skill assessment in team-based multi-player video games (e.g., Halo 3), we find that group cohesion is a predictive feature in virtual and real-world team-based games, and that methods utilizing such features can often outperform the baseline in both contexts. Additionally, we observe a strong positive correlation between the predictive accuracy of our group cohesion-based approaches and the duration of playing time between a particular configuration of players on a team and their opponents, or "match-up" length.

show abstract

Section: Introductionmentioning

confidence: 85%

Section: A An Overview Of Teamskillmentioning

confidence: 99%

Section: Teamskill-allk-evmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

TeamSkill and the NBA

DeLong

Terveen

Srivastava

2013

Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this regard, Silva et al (2013) have noted that it is the ability to perceive "collective affordances"or the dynamic relationships among teammates, their opponents, and environmental pressuresthat allows teammates to establish coordination in interactive team tasks. Also noteworthy, within this dynamic systems view, there are scholars who compare TC to "chemical reactions" or "team chemistry" (see DeLong et al, 2011;Gershgoren et al, 2016), thus adding further nomological confusion to research on group dynamics in applied psychology (see Filho, 2015).…”

Section: Conceptual Framework Of Coordination In Teamsmentioning

confidence: 99%

Team coordination in high-risk circus acrobatics

Filho¹,

Rettig

2018

View full text Add to dashboard Cite

To advance understanding of the mechanisms allowing for team coordination (TC) in complex motor actions, we conducted a qualitative study with eight elite hand-to-hand circus acrobats. Data collection consisted of field observations, an open-ended interview with the participants’ head coach, and focus group interviews with all acrobats. Data analysis yielded three higher order themes: TC, collective efficacy (CE), and TC-CE linkage. Teammates’ shared and complementary mental models, as well as implicit and explicit communication dynamics, emerged as formative sub-themes of TC; self-efficacy and other’s-efficacy emerged as reflective sub-themes of CE. Our findings also suggest that TC is likely inter-related to CE in a systemic fashion. Practitioners should encourage the development of both shared and complementary models of thinking, while promoting verbal and non-verbal communication skills. Finally, increasing teammates’ confidence in themselves and in their teammates can help in the development of CE as well as the enhancement of TC.

show abstract

The Evaluation of Rating Systems in Online Free-for-All Games

Dehpanah

Ghori

Gemmell

et al. 2021

Transactions on Computational Science and Computational Intelligence

View full text Add to dashboard Cite

Online competitive games have become increasingly popular. To ensure an exciting and competitive environment, these games routinely attempt to match players with similar skill levels. Matching players is often accomplished through a rating system. There has been an increasing amount of research on developing such rating systems. However, less attention has been given to the evaluation metrics of these systems. In this paper, we present an exhaustive analysis of six metrics for evaluating rating systems in online competitive games. We compare traditional metrics such as accuracy. We then introduce other metrics adapted from the field of information retrieval. We evaluate these metrics against several well-known rating systems on a large real-world dataset of over 100,000 free-for-all matches. Our results show stark differences in their utility. Some metrics do not consider deviations between two ranks. Others are inordinately impacted by new players. Many do not capture the importance of distinguishing between errors in higher ranks and lower ranks. Among all metrics studied, we recommend Normalized Discounted Cumulative Gain (NDCG) because not only does it resolve the issues faced by other metrics, but it also offers flexibility to adjust the evaluations based on the goals of the system.

show abstract

TeamSkill: Modeling Team Chemistry in Online Multi-player Games

Cited by 16 publications

References 5 publications

TeamSkill and the NBA

TeamSkill and the NBA

Team coordination in high-risk circus acrobatics

The Evaluation of Rating Systems in Online Free-for-All Games

Contact Info

Product

Resources

About