Entertainment Computing最新文献_第4页

Optimizing transmedia storytelling strategies across platforms for Maximum audience engagement 优化跨平台跨媒体叙事策略，最大化用户粘性

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-11-19 DOI: 10.1016/j.entcom.2025.101061

Hamed Nozari

In the present era, transmedia narratives have gained an important place in marketing, education, and entertainment as a new tool for conveying messages in various media platforms. The main challenge in utilizing this approach is how to optimally allocate content to different platforms while considering conflicting goals such as maximizing audience engagement and minimizing distribution cost. By designing a multi-objective optimization model, this study provides an intelligent framework for making decisions about the content distribution mix in various media. The proposed model considers constraints such as media capacity, technical compatibility, total budget, and minimum level of engagement. To solve the model, genetic algorithms and particle swarm optimization algorithms are used and their performance is compared with the exact solution of the model in the GAMS environment. The results show that in different scenarios, the model has been able to reduce distribution cost by 23% and increase audience engagement by 19%. Also, the optimal content mix has been significantly consistent with changes in input parameters. This framework is a decision-making tool for transmedia campaign designers and has the ability to be generalized to real projects.

在当今时代，跨媒体叙事作为各种媒体平台传递信息的新工具，在营销、教育、娱乐等领域占有重要地位。使用这种方法的主要挑战是，如何在考虑最大化用户粘性和最小化发行成本等相互冲突的目标的同时，将内容最佳地分配给不同的平台。通过设计一个多目标优化模型，本研究为各种媒体的内容分发组合决策提供了一个智能框架。建议的模型考虑了诸如媒体容量、技术兼容性、总预算和最低参与水平等限制因素。采用遗传算法和粒子群优化算法求解该模型，并与GAMS环境下模型的精确解进行了性能比较。结果表明，在不同的场景下，该模型能够降低23%的发行成本，提高19%的受众参与度。此外，最优的内容组合与输入参数的变化显著一致。这个框架是跨媒体活动设计师的决策工具，可以推广到实际项目中。

{"title":"Optimizing transmedia storytelling strategies across platforms for Maximum audience engagement","authors":"Hamed Nozari","doi":"10.1016/j.entcom.2025.101061","DOIUrl":"10.1016/j.entcom.2025.101061","url":null,"abstract":"<div><div>In the present era, transmedia narratives have gained an important place in marketing, education, and entertainment as a new tool for conveying messages in various media platforms. The main challenge in utilizing this approach is how to optimally allocate content to different platforms while considering conflicting goals such as maximizing audience engagement and minimizing distribution cost. By designing a multi-objective optimization model, this study provides an intelligent framework for making decisions about the content distribution mix in various media. The proposed model considers constraints such as media capacity, technical compatibility, total budget, and minimum level of engagement. To solve the model, genetic algorithms and particle swarm optimization algorithms are used and their performance is compared with the exact solution of the model in the GAMS environment. The results show that in different scenarios, the model has been able to reduce distribution cost by 23% and increase audience engagement by 19%. Also, the optimal content mix has been significantly consistent with changes in input parameters. This framework is a decision-making tool for transmedia campaign designers and has the ability to be generalized to real projects.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101061"},"PeriodicalIF":2.4,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparing game enjoyment, competitive anxiety and performance of sit-up exercise via a team competition app 通过团队竞赛应用程序比较游戏乐趣、竞争焦虑和仰卧起坐锻炼的表现

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-11-18 DOI: 10.1016/j.entcom.2025.101059

Wei-Chen Hung , Jon-Chao Hong , Yu-Feng Wu

Exergames are used to achieve some types of outcomes in addition to offering entertainment. To examine the practice effect of exergaming, this study had 6th grade students compete collaboratively in a sit-up competition using the Fit-Fun exergame app. Each participant performed sit-ups for 1 min, and five participants’ sit-ups were accumulated to calculate the group’s score. Applying achievement emotion theory, this study examined the change in the students’ game enjoyment, competition anxiety, and exercise performance over six trials. A single-group quasi-experimental design was conducted, and students were encouraged to take part via the purposive sampling method. Questionnaires were completed at the end of each of the six trials. A total of 208 valid samples were collected for statistical analysis. Results showed a noteworthy improvement in exergaming performance, but a decrease in game enjoyment, while game competition anxiety stayed relatively stable. The findings contribute to the literature by applying achievement emotion theory to a collaborative exergaming context, and showing how constant competitive gameplay can increase performance while potentially weakening enjoyment. The findings may be a future exergame and physical education design reference.

除了提供娱乐外，游戏还用于实现某些类型的结果。为了检验练习游戏的练习效果，本研究让六年级的学生使用Fit-Fun练习游戏应用程序进行仰卧起坐比赛。每个参与者做1分钟的仰卧起坐，并累积五名参与者的仰卧起坐来计算小组的分数。本研究运用成就情绪理论，通过六次实验，考察了学生在游戏享受、竞争焦虑和运动表现方面的变化。采用单组准实验设计，采用目的抽样法鼓励学生参与。在六次试验的每一次结束时都要完成问卷调查。共收集有效样本208份进行统计分析。结果显示，游戏成绩显著提高，但游戏乐趣下降，而游戏竞争焦虑保持相对稳定。通过将成就情感理论应用于合作游戏情境，并展示持续的竞争性游戏玩法如何在潜在削弱乐趣的同时提高玩家表现，这些发现为相关文献做出了贡献。本研究结果可为未来体育游戏设计提供参考。

{"title":"Comparing game enjoyment, competitive anxiety and performance of sit-up exercise via a team competition app","authors":"Wei-Chen Hung , Jon-Chao Hong , Yu-Feng Wu","doi":"10.1016/j.entcom.2025.101059","DOIUrl":"10.1016/j.entcom.2025.101059","url":null,"abstract":"<div><div>Exergames are used to achieve some types of outcomes in addition to offering entertainment. To examine the practice effect of exergaming, this study had 6th grade students compete collaboratively in a sit-up competition using the Fit-Fun exergame app. Each participant performed sit-ups for 1 min, and five participants’ sit-ups were accumulated to calculate the group’s score. Applying achievement emotion theory, this study examined the change in the students’ game enjoyment, competition anxiety, and exercise performance over six trials. A single-group quasi-experimental design was conducted, and students were encouraged to take part via the purposive sampling method. Questionnaires were completed at the end of each of the six trials. A total of 208 valid samples were collected for statistical analysis. Results showed a noteworthy improvement in exergaming performance, but a decrease in game enjoyment, while game competition anxiety stayed relatively stable. The findings contribute to the literature by applying achievement emotion theory to a collaborative exergaming context, and showing how constant competitive gameplay can increase performance while potentially weakening enjoyment. The findings may be a future exergame and physical education design reference.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101059"},"PeriodicalIF":2.4,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145618298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the psychological mechanisms of metaverse game experiences: Identity construction and emotional impact 探索虚拟世界游戏体验的心理机制：身份建构和情感影响

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-11-17 DOI: 10.1016/j.entcom.2025.101058

HanXi Li , YuanXiong Liu , Younghwan Pan

Metaverse games offer immersive environments where users construct and engage with idealized virtual identities. However, limited research has explored the psychological mechanisms of virtual self-identity formation and its emotional impact. This study integrates Experience Economy Theory (EET), Self-Identity Theory, and Self-Discrepancy Theory to examine how metaverse gaming experiences influence users’ psychological states. Using survey data from 383 metaverse games users and PLS-SEM analysis, results confirm that all four EET dimensions positively impact virtual self-identity, with entertainment experience having the strongest effect and escapist experience the weakest. Virtual self-identity exhibits dual effects, increasing anxiety while lowering self-esteem, with self-estrangement playing a key mediating role in amplifying these negative psychological outcomes. This study extends EET to metaverse gaming, empirically validates the self-identity and self-discrepancy processes in virtual environments, and highlights the psychological risks and benefits of virtual self-identity. Findings offer insights for game designers, users, and policymakers to balance engagement with well-being.

虚拟世界游戏提供了沉浸式的环境，用户可以在其中构建和参与理想化的虚拟身份。然而，关于虚拟自我同一性形成的心理机制及其情感影响的研究有限。本研究结合体验经济理论（EET）、自我同一性理论（Self-Identity Theory）和自我差异理论（Self-Discrepancy Theory），探讨虚拟世界游戏体验对用户心理状态的影响。通过对383名虚拟世界游戏用户的调查数据和PLS-SEM分析，结果证实，所有四个EET维度都对虚拟自我认同产生积极影响，其中娱乐体验的影响最大，逃避体验的影响最弱。虚拟自我认同具有双重效应，既增加焦虑又降低自尊，而自我隔阂在放大这些负面心理结果中起着关键的中介作用。本研究将EET扩展到虚拟游戏中，实证验证了虚拟环境中的自我认同和自我差异过程，并强调了虚拟自我认同的心理风险和收益。研究结果为游戏设计师、用户和政策制定者平衡用户粘性和幸福感提供了见解。

{"title":"Exploring the psychological mechanisms of metaverse game experiences: Identity construction and emotional impact","authors":"HanXi Li , YuanXiong Liu , Younghwan Pan","doi":"10.1016/j.entcom.2025.101058","DOIUrl":"10.1016/j.entcom.2025.101058","url":null,"abstract":"<div><div>Metaverse games offer immersive environments where users construct and engage with idealized virtual identities. However, limited research has explored the psychological mechanisms of virtual self-identity formation and its emotional impact. This study integrates Experience Economy Theory (EET), Self-Identity Theory, and Self-Discrepancy Theory to examine how metaverse gaming experiences influence users’ psychological states. Using survey data from 383 metaverse games users and PLS-SEM analysis, results confirm that all four EET dimensions positively impact virtual self-identity, with entertainment experience having the strongest effect and escapist experience the weakest. Virtual self-identity exhibits dual effects, increasing anxiety while lowering self-esteem, with self-estrangement playing a key mediating role in amplifying these negative psychological outcomes. This study extends EET to metaverse gaming, empirically validates the self-identity and self-discrepancy processes in virtual environments, and highlights the psychological risks and benefits of virtual self-identity. Findings offer insights for game designers, users, and policymakers to balance engagement with well-being.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101058"},"PeriodicalIF":2.4,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145580013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Examining the influence of target–distractor similarity on difficulty in a working memory game 研究目标-干扰物相似性对工作记忆游戏难度的影响

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-11-15 DOI: 10.1016/j.entcom.2025.101060

Madeleine Frister , Fiona McNab , Maximilian Croissant , Paul Cairns

Video games often feature complex game environments, with many elements irrelevant to the current task, which may distract from goal-relevant information. From a game design perspective, this increased difficulty factor may either be desired or lead to unwanted consequences and accessibility concerns. Evidence from cognitive science suggests that information processing is more susceptible to distracting items similar to the target. The current study therefore investigated the effects of target–distractor similarity on difficulty in a Working Memory (WM) game that requires participants to memorise a target path on a grid. Distractors with varying similarity to the path were presented either simultaneously with the path (encoding period), or after the path has disappeared (delay period). Results revealed that distractors generally led to poorer performance, and further that performance gradually declined with increasing target–distractor similarity during memory encoding. Exploratory analyses between performance and player experience suggest that higher success rates may be related to higher ratings of enjoyment. The present findings highlight the importance of considering the visual design of goal-relevant and task-irrelevant surrounding elements to provide an optimal challenge level and ensure positive player experiences in video games that place demand on WM capabilities.

电子游戏通常以复杂的游戏环境为特色，包含许多与当前任务无关的元素，这可能会分散与目标相关的信息。从游戏设计的角度来看，这种增加的难度因素可能是理想的，也可能导致不必要的结果和易用性问题。来自认知科学的证据表明，信息处理更容易受到与目标相似的分散注意力的物品的影响。因此，目前的研究调查了目标-干扰物相似性对工作记忆（WM）游戏难度的影响，该游戏要求参与者记住网格上的目标路径。与路径相似度不同的干扰物可以与路径同时呈现（编码周期），也可以在路径消失后呈现（延迟周期）。结果表明，在记忆编码过程中，随着目标-分心物相似性的增加，目标-分心物的表现逐渐下降。性能和玩家体验之间的探索性分析表明，更高的成功率可能与更高的乐趣评级有关。目前的研究结果强调了考虑目标相关和任务无关周围元素的视觉设计的重要性，以提供最佳的挑战水平，并确保对WM能力有要求的电子游戏中的积极玩家体验。

{"title":"Examining the influence of target–distractor similarity on difficulty in a working memory game","authors":"Madeleine Frister , Fiona McNab , Maximilian Croissant , Paul Cairns","doi":"10.1016/j.entcom.2025.101060","DOIUrl":"10.1016/j.entcom.2025.101060","url":null,"abstract":"<div><div>Video games often feature complex game environments, with many elements irrelevant to the current task, which may distract from goal-relevant information. From a game design perspective, this increased difficulty factor may either be desired or lead to unwanted consequences and accessibility concerns. Evidence from cognitive science suggests that information processing is more susceptible to distracting items similar to the target. The current study therefore investigated the effects of target–distractor similarity on difficulty in a Working Memory (WM) game that requires participants to memorise a target path on a grid. Distractors with varying similarity to the path were presented either simultaneously with the path (encoding period), or after the path has disappeared (delay period). Results revealed that distractors generally led to poorer performance, and further that performance gradually declined with increasing target–distractor similarity during memory encoding. Exploratory analyses between performance and player experience suggest that higher success rates may be related to higher ratings of enjoyment. The present findings highlight the importance of considering the visual design of goal-relevant and task-irrelevant surrounding elements to provide an optimal challenge level and ensure positive player experiences in video games that place demand on WM capabilities.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101060"},"PeriodicalIF":2.4,"publicationDate":"2025-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Becoming someone in Esports: Identity, aspiration, and psychological commitment in a digital entertainment ecosystem 成为电子竞技中的佼佼者：数字娱乐生态系统中的身份、抱负和心理承诺

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-11-11 DOI: 10.1016/j.entcom.2025.101054

Arianna Boldi, Domenico Sanseverino

The classification of esports participants remains conceptually fragmented and empirically inconsistent, particularly in informal ecosystems lacking standardized professional criteria. This study examines how individuals involved in the Italian esports scene define their roles, occupational identities, and career aspirations within the precarious and loosely regulated esports market. Drawing on survey data from 297 gamers, including casual gamers and esports participants, we explore differences in gaming practices, digital skills, employment status, and career orientation. Informed by theories of aspirational labor and boundaryless careers, we propose a role-based taxonomy that recognizes functional roles such as administrators, content creators, and hybrid professionals. Esports participants differ from casual gamers in gaming intensity, platform preferences, and digital collaboration skills, but not in employment status or career values. Crucially, perceived professional commitment is more closely tied to functional roles than to gaming frequency. Most esports participants do not consider their engagement economically viable, underscoring the aspirational and precarious nature of esports labor. By situating player self-perceptions within broader dynamics of gaming platforms and digital entertainment, this study advances a context-sensitive model of esports engagement and contributes to comparative research and policy debates on esports and digital entertainment.

电子竞技参与者的分类在概念上仍然是碎片化的，在经验上也是不一致的，特别是在缺乏标准化专业标准的非正式生态系统中。本研究考察了意大利电子竞技领域的个人如何在不稳定且监管松散的电子竞技市场中定义自己的角色、职业身份和职业抱负。通过对297名游戏玩家（包括休闲游戏玩家和电子竞技参与者）的调查数据，我们探讨了游戏实践、数字技能、就业状况和职业方向的差异。根据有抱负的劳动和无边界职业理论，我们提出了一种基于角色的分类法，可以识别功能角色，如管理员、内容创作者和混合专业人员。电子竞技参与者与休闲玩家在游戏强度、平台偏好和数字协作技能方面存在差异，但在就业状况或职业价值观方面则没有差异。最重要的是，感知到的职业承诺与功能性角色的关系比与游戏频率的关系更紧密。大多数电竞参与者不认为他们的参与在经济上是可行的，这突显了电竞劳动力的抱负和不稳定性。通过将玩家的自我认知置于更广泛的游戏平台和数字娱乐动态中，本研究提出了一种情境敏感的电子竞技参与模型，并有助于电子竞技和数字娱乐的比较研究和政策辩论。

{"title":"Becoming someone in Esports: Identity, aspiration, and psychological commitment in a digital entertainment ecosystem","authors":"Arianna Boldi, Domenico Sanseverino","doi":"10.1016/j.entcom.2025.101054","DOIUrl":"10.1016/j.entcom.2025.101054","url":null,"abstract":"<div><div>The classification of esports participants remains conceptually fragmented and empirically inconsistent, particularly in informal ecosystems lacking standardized professional criteria. This study examines how individuals involved in the Italian esports scene define their roles, occupational identities, and career aspirations within the precarious and loosely regulated esports market. Drawing on survey data from 297 gamers, including casual gamers and esports participants, we explore differences in gaming practices, digital skills, employment status, and career orientation. Informed by theories of aspirational labor and boundaryless careers, we propose a role-based taxonomy that recognizes functional roles such as administrators, content creators, and hybrid professionals. Esports participants differ from casual gamers in gaming intensity, platform preferences, and digital collaboration skills, but not in employment status or career values. Crucially, perceived professional commitment is more closely tied to functional roles than to gaming frequency. Most esports participants do not consider their engagement economically viable, underscoring the aspirational and precarious nature of esports labor. By situating player self-perceptions within broader dynamics of gaming platforms and digital entertainment, this study advances a context-sensitive model of esports engagement and contributes to comparative research and policy debates on esports and digital entertainment.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101054"},"PeriodicalIF":2.4,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145533012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning transferable collaborative behaviors for multiple agents in the game environment 博弈环境中多主体可转移协作行为的学习

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-11-10 DOI: 10.1016/j.entcom.2025.101051

Wei Li , Jiali Lv , Xu Zhang , Kaizhu Huang , Aiguo Song

Cooperative Multi-Agent Reinforcement Learning (CMARL) enables multiple agents to learn collaborative policies for accomplishing complex tasks in virtual game environments. However, most CMARL algorithms have difficulties in learning effective collaborative policies in single one scenario and transfer them across scenarios. To address these challenges around the multi-agent systems, we propose a novel method, named Collaborative Policy Learning and Transfer (CPLT). CPLT comprises two key components: the Control Action Generation (CAG) module, which learns the effective and transferable policies from the local observations of agents, and the Collaborative Control Optimization (CCO) module, which precisely evaluates the agent contributions to improve the teamwork. We evaluate CPLT on StarCraft Multi-Agent Challenge (SMAC), a benchmark platform of the real-time strategy game StarCraft II, and Multi-Agent Particle Environment (MPE), a two-dimensional platform for the cooperative and competitive tasks. Experimental results demonstrate that CPLT can effectively improve the agent performances in both within-scenario and cross-scenario collaborative tasks. Moreover, the CAG and CCO modules show strong compatibility with the related CMARL methods for enhancing their gaming performances.

协作式多智能体强化学习（Cooperative Multi-Agent Reinforcement Learning， CMARL）使多个智能体能够学习协同策略，以完成虚拟游戏环境中的复杂任务。然而，大多数CMARL算法难以在单一场景中学习有效的协同策略并将其跨场景迁移。为了解决这些围绕多智能体系统的挑战，我们提出了一种新的方法，称为协同策略学习和迁移（CPLT）。CPLT由两个关键部分组成：控制动作生成（CAG）模块和协同控制优化（CCO）模块，CAG模块从智能体的局部观察中学习有效和可转移的策略，CCO模块精确评估智能体的贡献以提高团队合作能力。我们在实时战略游戏《星际争霸II》的基准平台《星际争霸多代理挑战》（SMAC）和用于合作和竞争任务的二维平台《多代理粒子环境》（MPE）上对CPLT进行了评估。实验结果表明，CPLT可以有效地提高智能体在场景内和跨场景协同任务中的性能。此外，CAG和CCO模块与相关的CMARL方法具有较强的兼容性，从而提高了它们的游戏性能。

{"title":"Learning transferable collaborative behaviors for multiple agents in the game environment","authors":"Wei Li , Jiali Lv , Xu Zhang , Kaizhu Huang , Aiguo Song","doi":"10.1016/j.entcom.2025.101051","DOIUrl":"10.1016/j.entcom.2025.101051","url":null,"abstract":"<div><div>Cooperative Multi-Agent Reinforcement Learning (CMARL) enables multiple agents to learn collaborative policies for accomplishing complex tasks in virtual game environments. However, most CMARL algorithms have difficulties in learning effective collaborative policies in single one scenario and transfer them across scenarios. To address these challenges around the multi-agent systems, we propose a novel method, named Collaborative Policy Learning and Transfer (CPLT). CPLT comprises two key components: the Control Action Generation (CAG) module, which learns the effective and transferable policies from the local observations of agents, and the Collaborative Control Optimization (CCO) module, which precisely evaluates the agent contributions to improve the teamwork. We evaluate CPLT on StarCraft Multi-Agent Challenge (SMAC), a benchmark platform of the real-time strategy game StarCraft II, and Multi-Agent Particle Environment (MPE), a two-dimensional platform for the cooperative and competitive tasks. Experimental results demonstrate that CPLT can effectively improve the agent performances in both within-scenario and cross-scenario collaborative tasks. Moreover, the CAG and CCO modules show strong compatibility with the related CMARL methods for enhancing their gaming performances.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101051"},"PeriodicalIF":2.4,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145618299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identifying fighting, balanced, and territorial go player styles with deep learning 通过深度学习识别战斗、平衡和领土类型的围棋玩家

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-10-17 DOI: 10.1016/j.entcom.2025.101036

Tejal R. Shirsat, Shi-Jim Yen

The game of Go, renowned for its strategic depth, has been a central focus in both competitive gaming and artificial intelligence (AI) research. This paper explores the application of deep learning techniques to recognize the playstyles of human Go players, a task that offers valuable insights into complex human decision-making. The study employs a neural network architecture, leveraging convolutional layers, residual connections, and attention mechanisms, to categorize player styles into three specific groups: Fighting, Balanced, and Territorial. Trained on a dataset of 70,000 original Go game records, which was expanded through data augmentation to 483,712 samples, the model achieved a high testing accuracy of 82.6 % on a separate, unseen dataset of 10,000 game records. These results demonstrate the model’s effectiveness in accurately distinguishing between these playstyles and its strong generalization capability, with a final validation accuracy of 81.03 %. The model successfully identifies players preferred playing styles, revealing consistent preferences aligned with Go literature. This work contributes to the field of behavioral stylometry by showcasing how deep learning can be applied to complex strategic behaviors, with potential implications for player modeling and AI-human collaboration in various strategic contexts.

围棋以其战略深度而闻名，一直是竞技游戏和人工智能（AI）研究的焦点。本文探讨了深度学习技术的应用，以识别人类围棋棋手的游戏风格，这一任务为复杂的人类决策提供了有价值的见解。该研究采用神经网络架构，利用卷积层、剩余连接和注意力机制，将玩家风格分为三类：战斗、平衡和领土。该模型在包含70,000个原始围棋游戏记录的数据集上进行训练，并通过数据增强扩展到483,712个样本，在包含10,000个游戏记录的独立未见数据集上实现了82.6%的高测试准确率。这些结果证明了该模型在准确区分这些游戏风格方面的有效性及其强大的泛化能力，最终验证准确率为81.03%。该模型成功地识别了玩家偏好的下棋风格，揭示了与围棋文献一致的偏好。这项工作通过展示深度学习如何应用于复杂的战略行为，以及在各种战略背景下对玩家建模和人工智能-人类协作的潜在影响，为行为文体学领域做出了贡献。

{"title":"Identifying fighting, balanced, and territorial go player styles with deep learning","authors":"Tejal R. Shirsat, Shi-Jim Yen","doi":"10.1016/j.entcom.2025.101036","DOIUrl":"10.1016/j.entcom.2025.101036","url":null,"abstract":"<div><div>The game of Go, renowned for its strategic depth, has been a central focus in both competitive gaming and artificial intelligence (AI) research. This paper explores the application of deep learning techniques to recognize the playstyles of human Go players, a task that offers valuable insights into complex human decision-making. The study employs a neural network architecture, leveraging convolutional layers, residual connections, and attention mechanisms, to categorize player styles into three specific groups: Fighting, Balanced, and Territorial. Trained on a dataset of 70,000 original Go game records, which was expanded through data augmentation to 483,712 samples, the model achieved a high testing accuracy of 82.6 % on a separate, unseen dataset of 10,000 game records. These results demonstrate the model’s effectiveness in accurately distinguishing between these playstyles and its strong generalization capability, with a final validation accuracy of 81.03 %. The model successfully identifies players preferred playing styles, revealing consistent preferences aligned with Go literature. This work contributes to the field of behavioral stylometry by showcasing how deep learning can be applied to complex strategic behaviors, with potential implications for player modeling and AI-human collaboration in various strategic contexts.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101036"},"PeriodicalIF":2.4,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145618300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Can entertainment and information gratifications influence compulsive short video app use? The pivotal function of immersive experience and emotional attachment 娱乐和信息满足会影响强迫性短视频应用的使用吗？沉浸式体验和情感依恋的关键功能

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-09-01 DOI: 10.1016/j.entcom.2025.101030

Hua Pang , Jingyuan Zhao

Existing studies have documented the detrimental consequences associated with the compulsive and excessive utilization of short video app, yet the exact causes of these problematic usage patterns remain unclear. Addressing this gap, this study employs the Stimulus-Organism-Response (SOR) paradigm to investigate how entertainment, information, and sociality gratifications influence immersive experience and emotional attachment, and how these psychological states in turn drive compulsive usage behaviors among young users. Employing a questionnaire survey method to collect data, the research uses a sample of 896 short video app users and employs structural equation modeling to validate a conceptual framework. The findings reveal that entertainment gratification and information gratification exert a significant influence on users’ immersive experience and emotional attachment. Furthermore, this study discovers that immersive experience and emotional attachment serve as two mediators in shaping the influence of users’ gratifications sought on compulsive app utilization. By identifying the factors driving compulsive use among younger generation, this research provides insights for app developers and organizations within the short video app industry, as well as for public health authorities and educational institutions.

现有的研究已经记录了与强迫性和过度使用短视频应用相关的有害后果，但这些问题使用模式的确切原因尚不清楚。为了解决这一差距，本研究采用刺激-有机体-反应（SOR）范式来研究娱乐、信息和社会性满足如何影响沉浸式体验和情感依恋，以及这些心理状态如何反过来驱动年轻用户的强迫性使用行为。本研究采用问卷调查法收集数据，以896个短视频应用用户为样本，采用结构方程模型对概念框架进行验证。研究发现，娱乐满足和信息满足对用户沉浸式体验和情感依恋有显著影响。此外，本研究还发现，沉浸式体验和情感依恋在用户寻求满足对强迫性应用使用的影响中起着两个中介作用。通过确定导致年轻一代强迫性使用的因素，这项研究为短视频应用程序行业的应用程序开发人员和组织，以及公共卫生当局和教育机构提供了见解。

{"title":"Can entertainment and information gratifications influence compulsive short video app use? The pivotal function of immersive experience and emotional attachment","authors":"Hua Pang , Jingyuan Zhao","doi":"10.1016/j.entcom.2025.101030","DOIUrl":"10.1016/j.entcom.2025.101030","url":null,"abstract":"<div><div>Existing studies have documented the detrimental consequences associated with the compulsive and excessive utilization of short video app, yet the exact causes of these problematic usage patterns remain unclear. Addressing this gap, this study employs the Stimulus-Organism-Response (SOR) paradigm to investigate how entertainment, information, and sociality gratifications influence immersive experience and emotional attachment, and how these psychological states in turn drive compulsive usage behaviors among young users. Employing a questionnaire survey method to collect data, the research uses a sample of 896 short video app users and employs structural equation modeling to validate a conceptual framework. The findings reveal that entertainment gratification and information gratification exert a significant influence on users’ immersive experience and emotional attachment. Furthermore, this study discovers that immersive experience and emotional attachment serve as two mediators in shaping the influence of users’ gratifications sought on compulsive app utilization. By identifying the factors driving compulsive use among younger generation, this research provides insights for app developers and organizations within the short video app industry, as well as for public health authorities and educational institutions.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101030"},"PeriodicalIF":2.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145265877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Embodied functions and symbolic meaning of eyewear items in varied game environments 眼镜物品在不同游戏环境中的体现功能和象征意义

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-09-01 DOI: 10.1016/j.entcom.2025.101047

Samyoung Yu , Jihye Ahn , Moonsung Choi

This study examines the functional roles of eyewear items across three distinct game environments – PvX (hybrid PvP-PvE), PvP (player versus player), and PvE (player versus environment) – analyzing their relationship with real-world eyewear. Hierarchical clustering and text mining techniques are used to categorize eyewear items according to their functional roles in gaming environments. PvX eyewear items integrate PvP-oriented combat functions (e.g., dexterity, luck) with PvE-oriented conventional functions (e.g., collection, detection, intelligence), thereby enabling seamless adaptation to hybrid gameplay environments. PvP eyewear items support combat efficiency and display minimal association with the conventional meanings of real-world eyewear. PvE eyewear items support exploration and resource management and align with the conventional meanings of real-world eyewear. These functional meanings differ across PvX, PvP, and PvE environments as each emphasizes distinct gameplay priorities. These interactions demonstrate how eyewear items mediate the adaptation of real-world meanings within game environments. Therefore, game items are reconstructed by the interaction between game environments and conventional meanings. The meanings of game items are primarily shaped by the game’s core content and environment, with real-world meanings playing a supplementary role.

本研究考察了眼镜在三种不同游戏环境中的功能角色——PvX（混合PvP-PvE）、PvP（玩家对玩家）和PvE（玩家对环境）——分析了它们与现实世界眼镜的关系。分层聚类和文本挖掘技术用于根据眼镜在游戏环境中的功能角色对其进行分类。《PvX》眼镜道具将面向pvp的战斗功能（如灵巧、运气）与面向pve的传统功能（如收集、探测、情报）结合在一起，从而能够无缝适应混合游戏玩法环境。PvP眼镜道具支持战斗效率，并与现实世界眼镜的传统含义保持最小关联。PvE眼镜项目支持探索和资源管理，并与现实世界眼镜的传统含义保持一致。这些功能意义在PvX、PvP和PvE环境中有所不同，因为它们都强调不同的玩法优先级。这些互动展示了眼镜道具如何在游戏环境中调解现实意义的适应。因此，游戏道具是通过游戏环境与传统意义之间的交互作用进行重构的。游戏道具的意义主要是由游戏的核心内容和环境决定的，现实世界的意义只是一个补充。

{"title":"Embodied functions and symbolic meaning of eyewear items in varied game environments","authors":"Samyoung Yu , Jihye Ahn , Moonsung Choi","doi":"10.1016/j.entcom.2025.101047","DOIUrl":"10.1016/j.entcom.2025.101047","url":null,"abstract":"<div><div>This study examines the functional roles of eyewear items across three distinct game environments – PvX (hybrid PvP-PvE), PvP (player versus player), and PvE (player versus environment) – analyzing their relationship with real-world eyewear. Hierarchical clustering and text mining techniques are used to categorize eyewear items according to their functional roles in gaming environments. PvX eyewear items integrate PvP-oriented combat functions (e.g., dexterity, luck) with PvE-oriented conventional functions (e.g., collection, detection, intelligence), thereby enabling seamless adaptation to hybrid gameplay environments. PvP eyewear items support combat efficiency and display minimal association with the conventional meanings of real-world eyewear. PvE eyewear items support exploration and resource management and align with the conventional meanings of real-world eyewear. These functional meanings differ across PvX, PvP, and PvE environments as each emphasizes distinct gameplay priorities. These interactions demonstrate how eyewear items mediate the adaptation of real-world meanings within game environments. Therefore, game items are reconstructed by the interaction between game environments and conventional meanings. The meanings of game items are primarily shaped by the game’s core content and environment, with real-world meanings playing a supplementary role.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101047"},"PeriodicalIF":2.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The only good orc is a dead orc: does playing good or evil monster races influence ethnocentrism in real life? A brief report 唯一善良的兽人是死去的兽人：扮演善良或邪恶的怪物种族会影响现实生活中的种族中心主义吗？简短的报告

IF 2.4 3区计算机科学 Q2 COMPUTER SCIENCE, CYBERNETICS

Entertainment Computing

Pub Date : 2025-09-01 DOI: 10.1016/j.entcom.2025.101023

Christopher J. Ferguson, Cassandra Bradley, Breanna Karon, Ashleigh Korn, Jenna Kotschessa, Deandra Lazos, Shardae Madison, Jessie Quince, Cassie Rice, Noureen Saeed, Chloe Washington

Does killing orcs in fantasy games make people feel racist toward other people in real life? Recent controversies within role-playing games have focused on whether playing with inherently evil monster races increases ethnocentrism in real life. This has led some game makers to change the content of their games away from themes of good humans, elves, and dwarves fighting evil monster races, to themes of moral ambiguity where any race can be good or evil. This has also resulted in pushbacks from some players who claim these efforts cater to politically left narratives on race and identity that are themselves harmful. For the current study, the belief that fighting against evil orcs contributes to racist attitudes was tested with a sample of 102 young adults. Participants were randomized to play a video game with either inherently evil orcs, or those that were morally neutral. Participants were then tested with regard to ethnocentrism. No evidence emerged that playing in a game with evil orcs increased ethnocentrism. This evidence finds that causal concerns about role-playing games with evil monsters may be misplaced.

在幻想游戏中杀死兽人是否会让人们对现实生活中的其他人产生种族歧视？最近关于角色扮演游戏的争论主要集中在玩邪恶的怪物种族是否会增加现实生活中的种族中心主义。这导致一些游戏开发者将游戏内容从善良的人类，精灵和矮人对抗邪恶的怪物种族的主题转变为道德模糊的主题，即任何种族都可以是善或恶。这也导致了一些玩家的反对，他们声称这些努力迎合了种族和身份的政治左翼叙事，这本身就是有害的。在目前的研究中，对102名年轻人的样本进行了测试，他们认为与邪恶的兽人作战会导致种族主义态度。参与者被随机分成两组，一组是天生邪恶的兽人，另一组是道德中立的兽人。然后对参与者进行了关于种族中心主义的测试。没有证据表明，与邪恶的兽人一起玩游戏会增加种族中心主义。这一证据表明，对带有邪恶怪物的角色扮演游戏的因果关系担忧可能是错误的。

{"title":"The only good orc is a dead orc: does playing good or evil monster races influence ethnocentrism in real life? A brief report","authors":"Christopher J. Ferguson, Cassandra Bradley, Breanna Karon, Ashleigh Korn, Jenna Kotschessa, Deandra Lazos, Shardae Madison, Jessie Quince, Cassie Rice, Noureen Saeed, Chloe Washington","doi":"10.1016/j.entcom.2025.101023","DOIUrl":"10.1016/j.entcom.2025.101023","url":null,"abstract":"<div><div>Does killing orcs in fantasy games make people feel racist toward other people in real life? Recent controversies within role-playing games have focused on whether playing with inherently evil monster races increases ethnocentrism in real life. This has led some game makers to change the content of their games away from themes of good humans, elves, and dwarves fighting evil monster races, to themes of moral ambiguity where any race can be good or evil. This has also resulted in pushbacks from some players who claim these efforts cater to politically left narratives on race and identity that are themselves harmful. For the current study, the belief that fighting against evil orcs contributes to racist attitudes was tested with a sample of 102 young adults. Participants were randomized to play a video game with either inherently evil orcs, or those that were morally neutral. Participants were then tested with regard to ethnocentrism. No evidence emerged that playing in a game with evil orcs increased ethnocentrism. This evidence finds that causal concerns about role-playing games with evil monsters may be misplaced.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101023"},"PeriodicalIF":2.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0