Entertainment Computing最新文献

{"title":"A recognition method for hitting movements of table tennis players based on fuzzy decision support system","authors":"Xin Liu ,&nbsp;Fangxian Yi","doi":"10.1016/j.entcom.2026.101090","DOIUrl":"10.1016/j.entcom.2026.101090","url":null,"abstract":"<div><div>Due to table tennis’s speed and complexity, movement analysis and planning are essential. The pace of these actions and the athletes’ playing styles make conventional analytical approaches difficult. This work introduces a fuzzy decision-support system for the analysis of table tennis striking movements. Fuzzy Inference and Signal Processing for Table Tennis Striking Movement Analysis is the method. Preprocessing includes noise reduction and signal segmentation using preset criteria. Statistical and frequency metrics may be extracted from motion data via feature extraction. To improve accuracy, the hybrid technique employs an Echo State Network (ESN) classifier to combine expert knowledge with empirical data. The suggested approach can recognize striking motions with over 99.7% accuracy across various skill levels. Due to its versatility and real-time performance, this system is ideal for automated sports analytics, coaching, and officiating. Since the research provides a clear and flexible framework for analyzing table tennis motions, it may be applied to other racket sports. The suggested study offers a complete table tennis evaluation and improvement tool.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101090"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080581","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}

{"title":"“Leveling-up” executive functions in children and adolescents with digital gamified interventions: a scoping review","authors":"Nicholas Napolitano ,&nbsp;Cristian A. Rojas-Barahona","doi":"10.1016/j.entcom.2026.101130","DOIUrl":"10.1016/j.entcom.2026.101130","url":null,"abstract":"<div><div>The adequate development of executive functions (EFs) in children and adolescents plays an important role in their academic performance and quality of life. For this reason, numerous studies have designed interventions to improve EF in both typically and atypically developing children. Many of these interventions are digital and contain elements of gamification in order to promote motivation and participation. To have a better understanding regarding the state of the art of digital gamified interventions, a scoping review has been designed to assess their effectiveness at improving executive functions in children and adolescents that are both typically and atypically developing. Among 65 reviewed studies, 86% reported improvements in at least one EF after training. Additionally, of the 41 studies that measured effects in untrained areas, 68% observed enhancements. No significant age-based differences were noted, and the interventions were nearly equally effective at improving EF when controlling for participants’ development. Furthermore, common game elements such as points and puzzles appeared in nearly all interventions, while more complex elements like storytelling and progression were more often present in those that significantly improved EF. This comprehensive review underscores the effectiveness of digital gamified interventions at improving EF and highlights their accessibility and motivational benefits.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101130"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797847","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}

{"title":"Opening the black box: A lightweight, explainable machine learning approach for UGC short video price prediction","authors":"Jian Zhang ,&nbsp;Yuhan Di ,&nbsp;Yuan Ni ,&nbsp;Jinyu Fang","doi":"10.1016/j.entcom.2026.101133","DOIUrl":"10.1016/j.entcom.2026.101133","url":null,"abstract":"<div><div>With the rapid development of short video platforms and the expanding scale of content creators, the issues of intellectual property transactions and value assessment related to short video content have garnered widespread attention. To enhance the fairness and transparency of transaction pricing, this paper proposes an explainable machine learning model (GBDT mimic) for entertainment content pricing scenarios, balancing prediction accuracy and model usability. We first construct a high-performance LightGBM model reinforced by Particle Swarm Optimization (PSO) as the “teacher model”, and then train a Gradient Boosting Decision Tree (GBDT) model as the “student model” using knowledge distillation techniques, achieving the transfer and simplification of prediction logic. The results show that this model not only achieves similar prediction accuracy to the teacher model in price prediction tasks, but also significantly improves computational efficiency and interpretability. By integrating a visualization mechanism for local feature contributions and global pricing factors, the model provides transparent and reliable decision-making references for creators, platform operators, and other stakeholders, breaking the barriers of traditional “black-box” models and providing technical support for the development of a healthy and sustainable ecosystem for digital entertainment content trading.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"57 ","pages":"Article 101133"},"PeriodicalIF":2.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147797864","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}

{"title":"Educational games for learning vocabulary in English as a Foreign Language","authors":"Anna Tonda ,&nbsp;Ricardo Pardo ,&nbsp;Inmaculada Remolar ,&nbsp;Veronica Rossano","doi":"10.1016/j.entcom.2025.101070","DOIUrl":"10.1016/j.entcom.2025.101070","url":null,"abstract":"<div><div>Today’s immigration challenges underscore the importance of learning English as a key to accessing better opportunities and integrating into society, given its status as a standard language for communication. A common challenge in studying English as a foreign language is the lack of commitment to courses, resulting in inconsistent progress and difficulty achieving fluency. This study explores the impact of a Virtual Reality game on English vocabulary acquisition among learners of English as a Foreign Language. The game simulates a kitchen environment where users reproduce food recipes, an everyday topic universally relatable across cultures.</div><div>To validate the virtual environment, tests were conducted with 40 participants divided equally into experimental and control groups. Pre and post-tests measured vocabulary acquisition and listening comprehension, while a usability questionnaire assessed participants’ interaction with the VR system. Results showed that the experimental group achieved significant vocabulary improvements, with p-values of 0.02 and 0.01, compared to more modest gains in the control group. The usability test indicated high satisfaction and engagement levels, highlighting the VR tool as a compelling method for vocabulary learning in EFL learners.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101070"},"PeriodicalIF":2.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839658","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}

{"title":"A comprehensive review and ensemble CNN approach for Bharatanatyam single-hand gesture classification","authors":"Kokul Thanikasalam,&nbsp;Amirthalingam Ramanan,&nbsp;Pavithra Kanmanirajah","doi":"10.1016/j.entcom.2025.101069","DOIUrl":"10.1016/j.entcom.2025.101069","url":null,"abstract":"<div><div>Bharatanatyam, the oldest Indian classical dance form, relies on hand gestures to convey meanings and narratives. Recognizing these gestures is important for performance analysis and for supporting novice learners. This study presents the first comprehensive review of classification methods for Bharatanatyam single-hand gestures (Asamyukta Hastas), identifying key limitations in existing work. To address the lack of comprehensive datasets and their limited generalization, this study introduces a robust benchmark dataset collected from a large number of dancers. Previous methods, which relied solely on either deep or hand-crafted features, struggled to capture the fine-grained details of complex gestures. To overcome this, an ensemble Convolutional Neural Network (CNN) based model is proposed to classify 30 Asamyukta Hastas using both deep and hand-crafted features. From each raw hand-gesture image, a hand-landmark skeleton image is generated to capture finger positions while removing extraneous details. In addition, an embedded hand-landmark image is produced to provide landmark cues alongside the raw visual features. Three individual CNN models are trained using raw hand gesture images, hand-landmark skeleton images, and embedded hand-landmark images, as each modality provides complementary information. The performance of each CNN is further enhanced using an attention module, and their outputs are ultimately combined through a majority-voting ensemble strategy. The proposed model achieved an average accuracy of 98.28% and an average F1-score of 97.18% on the test set, with a mean recognition time of 325 ms. The source code and dataset for this work are publicly available at <span><span>https://doi.org/10.5281/zenodo.11514705</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101069"},"PeriodicalIF":2.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840243","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}

{"title":"Beyond pre-scripted interactions: mapping the integration of LLMs in digital game-based learning – a scoping review","authors":"Yu-lin Gong ,&nbsp;Min-kai Wang ,&nbsp;Yun-Fang Tu ,&nbsp;Chang-qin Huang ,&nbsp;Di Zhang","doi":"10.1016/j.entcom.2026.101082","DOIUrl":"10.1016/j.entcom.2026.101082","url":null,"abstract":"<div><div>Digital Game-Based Learning (DGBL) has demonstrated effectiveness in fostering engagement and academic achievement but faces challenges in adaptability, real-time feedback, and personalized scaffolding. Large Language Models (LLMs) offer promising solutions by enabling interactive learning experiences, dynamic assessments, and adaptive instructional support. This scoping review systematically examines the integration of LLMs in DGBL, assessing their impact on student engagement, learning outcomes, and pedagogical effectiveness. Following PRISMA-ScR guidelines, seven peer-reviewed studies published between 2024 and 2025 were identified from Web of Science, Scopus, ERIC, and PubMed. Thematic analysis revealed that LLM-enhanced DGBL primarily supports three functional roles: (1) conversational AI for interactive scaffolding, facilitating real-time student-NPC interactions; (2) adaptive learning support, personalizing feedback and guiding problem-solving strategies; and (3) automated assessment, evaluating student performance and providing instructional interventions. Findings indicate that LLM-driven DGBL enhances student motivation, cognitive engagement, and academic performance while reducing cognitive load. However, key challenges persist, including AI over-reliance, transparency concerns, and the need for ethical safeguards. Future research should explore longitudinal effects, interdisciplinary applications, and AI literacy strategies to ensure responsible and effective integration of LLMs in game-based learning.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101082"},"PeriodicalIF":2.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977102","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}

{"title":"Identifying fighting, balanced, and territorial go player styles with deep learning","authors":"Tejal R. Shirsat,&nbsp;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":"2026-01-01","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}

{"title":"Improving group navigation for VR-based entertainment applications","authors":"Jalal Safari Bazargani,&nbsp;Jong-min Jeon,&nbsp;Abolghasem Sadeghi-Niaraki,&nbsp;Soo-Mi Choi","doi":"10.1016/j.entcom.2026.101086","DOIUrl":"10.1016/j.entcom.2026.101086","url":null,"abstract":"<div><div>Various aspects of shared virtual environments have been explored to improve communication, collaboration, and entertainment among users. However, one crucial element, group navigation, remains in its early stages of development. The research gap suggests investigating different approaches to achieve suitable group navigation approaches within virtual reality environments. The employment of customized avatars that provide gestures and voice chat communication, along with controlled transitions between individual and group navigations, has not yet been fully studied. In this regard, this paper proposes a new approach for examining the aforementioned unexplored features of group navigation along with other modifications to current techniques. Moreover, features such as animated paths, transparent materials, switching between first-person view and third-person distant view, and preview avatars were incorporated into this approach. As the locomotion technique of the proposed solution varies noticeably with existing ones, the solution was evaluated in a user study comparing with teleportation and steering methods in terms of human behavior and psychology from usability, immersion, efficiency, safety, attention-guiding mechanism, and entertainment perspectives. The findings revealed that our approach outperformed teleportation and steering, providing promising insights into developing more interactive, entertaining, and socially immersive group navigation techniques in VR.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101086"},"PeriodicalIF":2.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977103","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}

{"title":"Learning transferable collaborative behaviors for multiple agents in the game environment","authors":"Wei Li ,&nbsp;Jiali Lv ,&nbsp;Xu Zhang ,&nbsp;Kaizhu Huang ,&nbsp;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":"2026-01-01","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}

{"title":"Deceptive algorithms in games: A systematic literature review","authors":"Jason Starace,&nbsp;Jennie Tafoya,&nbsp;Anmol Singh,&nbsp;Terence Soule","doi":"10.1016/j.entcom.2025.101078","DOIUrl":"10.1016/j.entcom.2025.101078","url":null,"abstract":"<div><div>This systematic literature review examines the evolving landscape of deception in video games and artificial intelligence (AI). The integration of deceptive strategies in AI, particularly within gaming environments, represents a growing area of interest with significant implications for both gameplay and broader applications, such as cybersecurity. Through a systematic review of 97 papers, 79 were excluded after introduction analysis revealed focus on deception outside gaming contexts (e.g., advertising, propaganda, movement detection), leaving 18 papers directly applicable to game-based deception. Of these 18, 61% provided formal or contextual definitions while 39% relied on assumed understanding. The review categorizes the current body of research into three primary areas: definitions of deception, methods for implementing and mitigating deception, and the frameworks used to analyze these strategies. The review highlights the diversity in the conceptualization of deception, ranging from formal definitions grounded in game theory, to more context-specific operational definitions. Key models such as signaling games (information asymmetry scenarios), Stackelberg games (leader–follower dynamics), and hypergames (perception-based interactions) are explored alongside AI-driven approaches like reinforcement learning (trial-and-error learning) and generative neural networks, which simulate and detect deception in complex environments. The review identifies significant gaps in the standardization of definitions and the practical implementation of deceptive strategies, calling for further interdisciplinary research to address these challenges. The ethical implications of deploying deceptive AI systems are discussed, emphasizing the need for comprehensive frameworks that balance innovation with responsible usage. Future research must prioritize the standardized definitions and interdisciplinary collaboration across ethics, law, and social sciences to address the expanding applications and ethical implications of deceptive AI technologies.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"56 ","pages":"Article 101078"},"PeriodicalIF":2.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883258","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}