Entertainment Computing最新文献

Unravelling the projective identity in computer role-playing games: A narrative inquiry 揭示电脑角色扮演游戏中的投射身份：一种叙事探究

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-01-17 DOI: 10.1016/j.entcom.2026.101084

Fatima Zohra Benzert, Hanane Sarnou

{"title":"Unravelling the projective identity in computer role-playing games: A narrative inquiry","authors":"Fatima Zohra Benzert, Hanane Sarnou","doi":"10.1016/j.entcom.2026.101084","DOIUrl":"10.1016/j.entcom.2026.101084","url":null,"abstract":"<div><div>In computer role-playing games (CRPGs), players are afforded a large scope of identificatory possibilities, allowing for the formation of multi-layered and complex player-as-avatar constructs. Framing this liminal entanglement within James Gee’s projective identity theory, this study explored indepth the composition and structure of player-as-avatar constructs. We employed a narrative inquiry approach using semi-structured interviews to collect comprehensive storied accounts of projective identity formation experiences from the subjective perspective of 14 players from different backgrounds, specifically in CRPG contexts. Findings indicated that projective identities may constitute various overlapping self-defining components across personal, social, relational, and material levels. These identities are shaped by both game affordances and players’ transgressive engagement with game design and content, which highlights the nuanced and fluid nature of identity formation in virtual spaces. This research provides new insights into the multi-layered structure of projective identities and emphasises the importance of understanding player perspectives in the study of virtual identity construction.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101084"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025770","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

When the audience joins the game: Live streaming’s influence on league of legends gameplay 当玩家加入游戏时：直播对英雄联盟玩法的影响

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-04-24 DOI: 10.1016/j.entcom.2026.101135

Emre Akif Arslan

{"title":"When the audience joins the game: Live streaming’s influence on league of legends gameplay","authors":"Emre Akif Arslan","doi":"10.1016/j.entcom.2026.101135","DOIUrl":"10.1016/j.entcom.2026.101135","url":null,"abstract":"<div><div>Live streaming embeds real-time audiences into competitive play, yet its links to in-game performance and strategic behavior remain unclear. We analyzed 10,621 ranked solo-queue League of Legends matches on the Europe West server (January–August 2024), including opponent-sampled non-streamer matches (n = 4,921), off-stream streamer matches (n = 4,863), and on-stream matches during live broadcasts (n = 837). Match telemetry came from the Riot Games API, and streaming status was classified using Twitch broadcast timestamps. Between-group analyses compared streamer-associated versus non-streamer matches; within-streamer effects were estimated with mixed-effects models (player random intercept) adjusting for match duration, consecutive matches, and role. Streamer-associated matches showed higher kills and slightly higher turret kills, but lower creep score and weaker vision activity than non-streamer opponents. Within streamers, on-stream matches showed fewer kills and deaths, higher KDA, improved vision control, and more consistent lane selection, with no win-rate difference. In adjusted within-player models, live broadcasting remained associated with fewer deaths, more assists, higher kill/death/assist ratio, and increased vision control, while kills, turret kills, kill participation, and win probability were not significantly associated with streaming. Overall, live play aligned with risk-managed, support-oriented, information-focused strategies rather than better match outcomes.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101135"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797863","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

Research on an interactive film and entertainment style generation system based on multimodal input and AI models 基于多模态输入和AI模型的互动影视娱乐风格生成系统研究

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-04-19 DOI: 10.1016/j.entcom.2026.101129

Yingying Jiao

{"title":"Research on an interactive film and entertainment style generation system based on multimodal input and AI models","authors":"Yingying Jiao","doi":"10.1016/j.entcom.2026.101129","DOIUrl":"10.1016/j.entcom.2026.101129","url":null,"abstract":"<div><div>The research on an interactive film and entertainment style generation system based on multimodal input and AI models aims to meet users’ demand for personalized, interactive film experiences amid the evolution of digital media forms. By integrating multimodal inputs such as text, vision, and voice with generative artificial intelligence technology, an interactive film system is constructed that can respond to users’ intentions in real − time and dynamically generate content with an appropriate style. The system integrates multimodal feature extraction modules, such as BERT (Bidirectional Encoder Representations from Transformers)-based semantic understanding, facial behavior analysis, and voice emotion recognition. It uses generative adversarial networks to achieve collaborative generation of style transfer and branch narrative. Experiments show that integrating vision, text, and audio in can multimodal combination can significantly improve generation quality, with a style fit of 88%, an emotion conveyance of 86%, and an overall satisfaction of 87%. After process optimization, the average response delay for the three-modal input is reduced to 2.4 min, the user-perceived waiting time is shortened to 2.7 min, and the timeout rate is reduced to 5%. In terms of style consistency, after introducing the cross-modal constraint and user-state tracking mechanism, the main-line style retention rate increases to 85%, the style deviation during branch switching decreases to 15%, and the comprehensive consistency index reaches 83%.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101129"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797866","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

Beyond the screen: Machine learning models for forecasting relationship compatibility after initial meetings 屏幕之外：用于预测初次见面后关系兼容性的机器学习模型

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-01-11 DOI: 10.1016/j.entcom.2026.101085

Tao Yan

{"title":"Beyond the screen: Machine learning models for forecasting relationship compatibility after initial meetings","authors":"Tao Yan","doi":"10.1016/j.entcom.2026.101085","DOIUrl":"10.1016/j.entcom.2026.101085","url":null,"abstract":"<div><div>Within this regard, the pervasiveness of the Internet and social networking websites has fully dramaturgically altered traditional cultural attitudes towards dating and relationships in the trend of establishing acquaintances through cyberspace prior to face-to-face dates. During these first dates, it is quite common that an individual must make one of life’s most grueling decisions-to pursue or foreclose an emerging relationship. This research deals with the prediction of potential partners’ compatibility and the relation trajectory after the first date in online dating. In this research, the possibility of mutual compatibility of relationships could be estimated using artificial intelligence and machine learning approaches, which include the CATC, SVC, and LRC models optimized by Giant Armadillo Optimization. By carefully studying a wide variety of input parameters and corresponding prediction results, the present study brings out that an optimized result of CATC with GAO, known as the CAGA model, derives an accuracy of 0.987 with the same level of precision at the time of training itself. Thus, in this regard, the model CAGA emerges as the ultimate best predictor and has been especially marked for their accuracy towards real-world relationships.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101085"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080582","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

Decoding the mechanisms of the Hattrick football manager game using Bayesian network structure learning 利用贝叶斯网络结构学习解码《帽子戏法》足球经理游戏的机制

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-04-27 DOI: 10.1016/j.entcom.2026.101131

Anthony C. Constantinou, Nicholas Higgins, Neville K. Kitson

{"title":"Decoding the mechanisms of the Hattrick football manager game using Bayesian network structure learning","authors":"Anthony C. Constantinou, Nicholas Higgins, Neville K. Kitson","doi":"10.1016/j.entcom.2026.101131","DOIUrl":"10.1016/j.entcom.2026.101131","url":null,"abstract":"<div><div>Hattrick is a free web-based probabilistic football manager game with over 200,000 users competing for titles at national and international levels. Launched in Sweden in 1997 as part of an MSc project, the game’s slow-paced design has fostered a loyal community, with users remaining active for decades. Hattrick’s game-engine mechanics are partially hidden, and users have attempted to decode them with incremental success over the years. Rule-based, statistical and machine learning models have been developed to aid this effort and are widely used by the community, but have not been formally evaluated in the scientific literature. This study is the first to explore Hattrick using structure learning techniques and Bayesian networks, integrating expert knowledge with data to develop models that simulate and explain the game-engine. We assess the effectiveness of structure learning algorithms in relation to knowledge-based structures, and publicly share a fully specified Bayesian network model that matches the performance of top models used by the Hattrick community. We further demonstrate how analysis extends beyond prediction by providing a visual representation of dependencies between features, and using the optimal model for in-game decision-making. To support future research, we make all data, graphical structures, and models publicly available online.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101131"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797867","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

Prediction of MOBA game events based on In-Game Data 基于游戏内数据的MOBA游戏事件预测

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-01-22 DOI: 10.1016/j.entcom.2026.101091

Michail Vardakis , George Margetis , Ioannis Chatzakis , Konstantinos C. Apostolakis , Constantine Stephanidis

{"title":"Prediction of MOBA game events based on In-Game Data","authors":"Michail Vardakis , George Margetis , Ioannis Chatzakis , Konstantinos C. Apostolakis , Constantine Stephanidis","doi":"10.1016/j.entcom.2026.101091","DOIUrl":"10.1016/j.entcom.2026.101091","url":null,"abstract":"<div><div>The growth of esports as a widely enjoyed activity for entertainment and social engagement has positioned it as one of the prominent domains of entertainment, gaming, and sports, attracting considerable interest from the research community. Considering that esports generate rich, real-time telemetry data, which can constitute the critical mass needed for researching data analysis and forecasting, a significant potential arises, especially in providing more engaging viewing and commentary. In this work, we study short-horizon event prediction in League of Legends, focusing on predicting imminent player elimination events (”deaths”) instead of overall outcome prediction during professional matches. We propose a time-series forecasting approach based on Temporal Fusion Transformers that uses multi-modal in-game data formulated as time-series to forecast near-term elimination events. Our system is designed to facilitate esports sportscasters, directors, producers, and content creators, attempting to surface likely high-impact moments and support proactive narrative cues. Trained in less than 200 matches, for a 5.0-second forecasting horizon and based on 10.0 s worth of historical data, our model achieves a <span><math><msub><mrow><mi>F</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span> score of around 0.6, which constitutes its performance comparable to similar work. This study demonstrates that short-horizon event forecasting is feasible using in-game data and transformer-based temporal models for the esports domain, thereby introducing a novel approach addressing a research topic that is rarely explored in esports analytics literature. Its findings suggest practical improvements for real-time support of esports’ storytelling experience and open avenues for future research on anticipatory analytics in interactive and spectator-driven digital sports.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101091"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025771","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

Avatar identification in online games: the moderating role of presence 网络游戏角色认同：在场的调节作用

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-01-18 DOI: 10.1016/j.entcom.2026.101089

Zhenglin Zhang, Chenyan Li

{"title":"Avatar identification in online games: the moderating role of presence","authors":"Zhenglin Zhang, Chenyan Li","doi":"10.1016/j.entcom.2026.101089","DOIUrl":"10.1016/j.entcom.2026.101089","url":null,"abstract":"<div><div>With the Internet’s growth and evolving lifestyle needs, social activities have extended into virtual online environments. We investigate factors affecting avatar identification in online games and their consequences, to guide game design and prevent internet addiction. This study analyzes the impact of avatar similarity and attachment styles on self-avatar and avatar-avatar identification through questionnaires, also examining presence’s moderating and substitutive roles. Using Smart PLS 4.0, we constructs a structural equation model showing that similarity enhances avatar identification; anxious attachment positively and avoidant attachment negatively influence it; avatar identification promotes game engagement; presence and avatar similarity mutually influence and substitute in avatar identification; Presence weakens the avoidant attachment-avatar identification link. This paper advises game developers to conduct market research for user profiling, offer customizable avatars, minimize user-avatar differences, and enhance immersion. It also encourages gamers to balance real and virtual identities, promoting enjoyable avatar identification and personal development.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101089"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146025769","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 antecedents and consequences of Cross-platform Media credibility in an emerging country: The integration of News-Finds-Me Perception and Bandwagon Effect 新兴国家跨平台媒体可信度的前因后果：新闻发现与从众效应的整合

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-01-16 DOI: 10.1016/j.entcom.2026.101087

Doan Viet Phuong Nguyen , Thanh-Binh Phung , Angelina Nhat-Hanh Le

引用次数: 0

Determining the effects of League of Legends ranked tiers on outcome prediction models 确定《英雄联盟》等级对结果预测模型的影响

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-01-12 DOI: 10.1016/j.entcom.2026.101088

Artin Lafrance, Ratvinder Grewal

{"title":"Determining the effects of League of Legends ranked tiers on outcome prediction models","authors":"Artin Lafrance, Ratvinder Grewal","doi":"10.1016/j.entcom.2026.101088","DOIUrl":"10.1016/j.entcom.2026.101088","url":null,"abstract":"<div><div>League of Legends (LoL) is a popular <em>Multiplayer Online Battle Arena</em> (MOBA) video game with a competitive ranked system. This study trained XGBoost, Random Forest, and Logistic Regression models on Bronze and Diamond tier datasets in order to predict match outcomes as well as observe differences in model performance on Bronze to Diamond tiers. Exactly, 20,781 matches were collected using the Riot API with the intended goal of having 5000 matches for Bronze and Diamond tiers and 1500 for the remaining tiers. Datasets were created for 10, 15, 20 and 25 min for each tier. XGBoost outperformed the other models, as it achieved an accuracy of 72.7% at 10 min for both Bronze and Diamond-trained tiers. At the 15 min interval, the XGBoost model achieved an accuracy of 77.1% trained on Bronze and 76.9% trained on Diamond. At the 20 min interval, it reached an accuracy of 79.3% for the Bronze-trained model and 80.1% on the Diamond-trained model. At the 25 min interval, this accuracy increased to 82.1% for Bronze-trained and 82.8% for Diamond-trained. The Diamond test datasets between 10 to 25 min were more accurately predicted compared to other tiers.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101088"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145996324","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

Native code, greener games? Investigating energy efficiency in unity builds 原生代码，绿色游戏？调查统一建筑的能源效率

IF 2.4 3区计算机科学

Entertainment Computing Pub Date : 2026-05-01 Epub Date: 2026-04-30 DOI: 10.1016/j.entcom.2026.101132

José Miguel Aragón-Jurado , Ruck Thawonmas , Patricia Ruiz , Bernabé Dorronsoro

{"title":"Native code, greener games? Investigating energy efficiency in unity builds","authors":"José Miguel Aragón-Jurado , Ruck Thawonmas , Patricia Ruiz , Bernabé Dorronsoro","doi":"10.1016/j.entcom.2026.101132","DOIUrl":"10.1016/j.entcom.2026.101132","url":null,"abstract":"<div><div>Video games are among the largest entertainment industries, generating over $187 billion in 2024 and running on platforms from PCs to mobile devices. Their increasing complexity and computational demands have pushed energy consumption to levels with significant environmental impact. Game engines such as Unity provide configuration options that could improve efficiency, yet their effects on performance and power usage remain poorly understood. This work presents an empirical study on how Unity build configurations influence frame rate, power consumption, and energy usage. Five publicly available Unity projects were compiled with both Mono and IL2CPP backends and evaluated across multiple build configurations and branches. Results were analyzed using the Game Performance and Energy Efficiency Quadrant, a novel framework that classifies builds based on simultaneous gains in frame rate and energy efficiency. Statistical analysis shows that production-oriented configurations generally deliver better energy outcomes than development versions, with IL2CPP <span>Faster Runtime</span> with the <span>Release</span> branch providing the most consistent balance of performance and efficiency, although Mono remains competitive in several cases. These findings indicate that greener and faster builds require pairing the right backend with optimized production settings, and that native code generation alone does not guarantee better energy efficiency.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101132"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797865","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