AUTHOR=Even Cindy , Bosser Anne-Gwenn , Buche Cédric 

TITLE=Assessing the Believability of Computer Players in Video Games: A New Protocol and Computer Tool

JOURNAL=Frontiers in Computer Science

VOLUME=Volume 3 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2021.774763

DOI=10.3389/fcomp.2021.774763

ISSN=2624-9898

ABSTRACT=In this paper, we address the challenge of believability  in multiplayer video games. Your contribution is a system for assessing the believability of virtual players. The state of the art examines existing methods and identifies seven distinguishing features that differ considerably from one assessment to the next. Our investigation reveals that assessment procedures typically alter gameplay, posing a considerable danger of bias. This is a major flaw since virtual players are evaluated in a specific context rather than in the context of the game as it should be played, potentially skewing the findings of the evaluation. As a result, we begin on a trial-and-error process, with each new proposal building on the achievements of the previous one while removing the flaws. We created a computer system that partially automates the execution of the assessment procedure to make these trials easier to implement. This technology is adaptable and has been used in a variety of combinations to demonstrate its versatility. Finally, we provide an unique approach that allows gamers to assess the believability of virtual players indirectly by employing the same reporting mechanisms that are used to detect cheating, abuse, and harassment in online video games. Our solution is to provide alternatives in reporting forms that would alert users to the presence of bots. We believe that the more a bot is reported, the less credible it becomes. We ran an experiment to test our proposal, which yielded extremely encouraging results.