基于多模态Twitch流数据的电子竞技人才挖掘
E-Sports Talent Scouting Based on Multimodal Twitch Stream Data
摘要:
我们提出并研究了一种新的任务的可行性,该任务包括使用多模式Twitch聊天和视频流数据来寻找电子竞技人才。在这方面,我们专注于预测在Twitch上播放游戏的《反恐精英:全球攻势》(CS:GO)玩家的排名。在2019年1月至2019年4月期间,我们建立了两个Twitch流媒体集合:一个用于425名公开排名的CS:GO玩家,另一个用于9,928名未排名的CS:GO玩家。我们从视频、音频和文本聊天数据中提取神经特征,并估计玩家在数据汇集时间范围内排名靠前的特定模式概率。然后,使用分层贝叶斯模型来汇集各种模式的证据,并为每个玩家生成内在技能的估计。我们的模型通过将内在技能预测与2019年5月公开描述的玩家排名相关联来验证。
英文摘要:
We propose and investigate feasibility of a novel task that consists in finding e-sports talent using multimodal Twitch chat and video stream data. In that, we focus on predicting the ranks of Counter-Strike: Global Offensive (CS:GO) gamers who broadcast their games on Twitch. During January 2019-April 2019, we have built two Twitch stream collections: One for 425 publicly ranked CS:GO gamers and one for 9,928 unranked CS:GO gamers. We extract neural features from video, audio and text chat data and estimate modality-specific probabilities for a gamer to be top-ranked during the data collection time-frame. A hierarchical Bayesian model is then used to pool the evidence across modalities and generate estimates of intrinsic skill for each gamer. Our modeling is validated through correlating the intrinsic skill predictions with May 2019 ranks of the publicly profiled gamers.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。