{"title":"Deep multimodal fusion for video game age rating classification","authors":"Caner BALIM","doi":"10.1016/j.entcom.2025.100980","DOIUrl":"10.1016/j.entcom.2025.100980","url":null,"abstract":"<div><div>Video games appeal to a wide range of ages, from children to adults. As a result, reliable age rating systems like the Entertainment Software Rating Board (ESRB) and Pan European Game Information (PEGI) are essential for guarding younger gamers from improper content. These organizations rate games based on content submitted by video game developers. This paper proposes a multimodal deep learning framework that predicts age ratings by analyzing both video game cover images and textual descriptions. A dataset of 39,212 games was constructed using publicly available information, including ESRB and PEGI labels. Both individual models based on visual or textual features and fusion models that combine these modalities using simple concatenation and Deep Canonical Correlation Analysis (DCCA) were employed to perform the classification task. Experimental results indicate that the simple concatenation model achieves the highest accuracy compared to the individual modalities and the DCCA-based approach, reaching 0.678 for ESRB prediction and 0.584 for PEGI prediction. The findings highlight that using only visual information has limitations, and that textual descriptions play an important role in determining the appropriate age rating for a game. This study shows that future research can benefit from using additional content like gameplay videos and audio.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100980"},"PeriodicalIF":2.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330338","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}
Irene C.E. van Blerck , Edirlei Soares de Lima , Margot M.E. Neggers , Toon Calders
{"title":"Unveiling gender bias in LLM-generated hero and heroine narratives","authors":"Irene C.E. van Blerck , Edirlei Soares de Lima , Margot M.E. Neggers , Toon Calders","doi":"10.1016/j.entcom.2025.100972","DOIUrl":"10.1016/j.entcom.2025.100972","url":null,"abstract":"<div><div>This article investigates gender bias in narratives generated by Large Language Models (LLMs) through a two-phase study. Building on our existing work in narrative generation, we employ a structured methodology to analyze the influence of protagonist gender on both the generation and classification of fictional stories. In Phase 1, factual narratives were generated using six LLMs, guided by predefined narrative structures (Hero’s Journey and Heroine’s Journey). Gender bias was quantified through specialized metrics and statistical analyses, revealing significant disparities in protagonist gender distribution and associations with narrative archetypes. In Phase 2, counterfactual narratives were constructed by altering the protagonists’ genders while preserving all other narrative elements. These narratives were then classified by the same LLMs to assess how gender influences their interpretation of narrative structures. Results indicate that LLMs exhibit difficulty in disentangling the protagonist’s gender from the narrative structure, often using gender as a heuristic to classify stories. Male protagonists in emotionally driven narratives were frequently misclassified as following the Heroine’s Journey, while female protagonists in logic-driven conflicts were misclassified as adhering to the Hero’s Journey. These findings provide empirical evidence of embedded gender biases in LLM-generated narratives, highlighting the need for bias mitigation strategies in AI-driven storytelling to promote diversity and inclusivity in computational narrative generation.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100972"},"PeriodicalIF":2.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306909","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":"Comic-Shelf vectors: Convoluting the co-occurrence among comics on the bookshelf","authors":"Kodai Imaizumi, Ryosuke Yamanishi, Mitsunori Matsushita","doi":"10.1016/j.entcom.2025.100973","DOIUrl":"10.1016/j.entcom.2025.100973","url":null,"abstract":"<div><div>This paper proposed <strong>Comic-Shelf (CS) vectors</strong>, which convolve the co-occurrence of comic titles on the bookshelves ordered by ranking, as a method for modeling sensibilities toward comic titles. By extracting semantic relationships from the orderings based on readers’ subjective evaluations and representing them as numerical vectors, we aim to establish a new information representation that reflects user sensibilities. In vector mapping analysis, it was revealed that the comic vectors of titles stored on the same bookshelf were plotted relatively close to one another. Assuming that the affection toward titles included on the same bookshelf is similar, it was inferred that higher vector similarity corresponds to comics that are closer in human affection. Furthermore, it was demonstrated that not only similarities between individual titles but also similarities between bookshelf themes could be visually captured. In a mock recommendation, we investigated whether CS vectors could select titles that aligned with participants’ preferences. The results showed that using CS vectors allowed for the selection of comics that better aligned with participants’ preferences compared to other methods, demonstrating the effectiveness of the CS vectors.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100973"},"PeriodicalIF":2.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330339","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":"Canine-centric interactive systems: Wavelet-based IMU motion recognition in edge AI scenarios","authors":"Guanyu Chen , Hiroki Watanabe , Kohei Matsumura , Yoshinari Takegawa","doi":"10.1016/j.entcom.2025.100971","DOIUrl":"10.1016/j.entcom.2025.100971","url":null,"abstract":"<div><div>Accurate and real-time recognition of canine motions has significant potential in entertainment computing, especially when combined with wearable devices and gamified interactions. Therefore, a lightweight canine behavior recognition method capable of operating on wearable devices is required.This paper presents a novel wavelet-based approach for lightweight machine learning (ML) on edge devices, focusing on canine motion classification via inertial measurement unit (IMU) data. Our pipeline utilizes wavelet transforms for feature extraction and applies a compact classifier to handle computational constraints common in embedded systems. Experiments demonstrate an overall accuracy of approximately 85% across a variety of dog activities, including running, jumping, and body shaking. Building on this foundation, we propose multiple gamified scenarios to encourage dog owners to engage in daily activities, such as multi-dog leaderboards, achievement badges, and real-time interaction through sound or lighting effects. We further explore camera-based features like automatic highlight capture and augmented reality overlays, enriching user experience through playful, immersive elements. The proposed approach provides a feasible solution for canine-centric entertainment systems, balancing accuracy, low power consumption, and interactive functionality.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100971"},"PeriodicalIF":2.8,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281188","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}
Faezeh Shabanali Fami , Ali Akbar Arjmandnia , Hadi Moradisabzevar
{"title":"Design, development, and analysis of validity for a computer-based cognitive rehabilitation (CBCR) program for children with specific learning disorder (SLD) − Dyslexia: A design-based approach","authors":"Faezeh Shabanali Fami , Ali Akbar Arjmandnia , Hadi Moradisabzevar","doi":"10.1016/j.entcom.2025.100955","DOIUrl":"10.1016/j.entcom.2025.100955","url":null,"abstract":"<div><h3>Introduction</h3><div>Dyslexia is a prevalent learning disorder that impairs children’s reading abilities and language processing. Cognitive deficits, particularly in language processing and phonological awareness, pose significant challenges, making targeted interventions essential for improving reading skills and academic outcomes.</div></div><div><h3>Objective</h3><div>This study aimed to develop a computer-based cognitive rehabilitation program specifically tailored for children with dyslexia, designed to enhance cognitive and academic skills through targeted exercises and adaptive training.</div></div><div><h3>Methods</h3><div>A developmental approach was used to construct the program, incorporating insights from prior research and the needs of dyslexic children. The program included practical game tasks addressing key cognitive deficits. Validity was assessed through semi-structured interviews with professionals, using both qualitative and quantitative feedback. K-means clustering was applied to categorize tasks based on cognitive functions such as executive functions, memory, and attention, aligning tasks with specific cognitive goals.</div></div><div><h3>Results</h3><div>Expert feedback led to refinements, achieving a content validity coefficient of 0.74, with indices for simplicity, clarity, and relevance at 0.93, 0.97, and 0.94, respectively.</div></div><div><h3>Conclusion</h3><div>The program effectively addresses cognitive deficits in dyslexia through adaptive training and clustered tasks. While expert evaluations are promising, further research is needed to validate its effectiveness in real-life settings and for diverse populations.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100955"},"PeriodicalIF":2.8,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270920","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":"Predicting post-VR game experiences with wearable physiological sensors","authors":"Wen Huang , Jiayi Gao , Xinyuan Chen","doi":"10.1016/j.entcom.2025.100977","DOIUrl":"10.1016/j.entcom.2025.100977","url":null,"abstract":"<div><div>Players’ post-game experiences determine their loyalty to a virtual reality (VR) game. However, methods for identifying players’ post-game experiences in the early stages have received far less attention than those for in-game experiences. In this study, we explored the potential of using measurements from wearable physiological sensors to predict players’ post–VR game experiences. The methods employed were correlation analyses and machine learning techniques. The results showed that electrodermal activity (EDA) measurements, particularly the mean EDA and mean EDA peak, are associated with players’ post-VR game experiences after accounting for noise. By utilizing machine learning technology, physiological metrics can forecast players’ diverse reactions after playing VR games with high accuracy. The symptoms of depersonalization/derealization experienced after VR gaming are attributed to being induced by actions within the virtual environment. This research makes significant contributions to the field of user experience recognition and the progression of VR gaming by demonstrating the potential for future VR game centers to analyze player emotions remotely and cost-effectively. This achievement provides the prerequisite for these centers to create tailored new 3D game scenarios to enhance players’ post-game experiences with the support of future advanced generative artificial intelligence technologies.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100977"},"PeriodicalIF":2.8,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253682","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":"Exploring older people’s user experiences with VR: A case study of Taiwanese seniors","authors":"Cheih-Ying Chen , Fanfan Chen , Cheng-En Tsai","doi":"10.1016/j.entcom.2025.100974","DOIUrl":"10.1016/j.entcom.2025.100974","url":null,"abstract":"<div><div>Despite much research on virtual reality (VR) techniques, few studies have explored older people’s use. Virtual reality is emerging as a promising tool to stimulate physical activity, overcome barriers to aging, and enrich older people’s leisure and recreational lives. In Taiwan, medical teams have formally introduced VR equipment to help seniors use serious games for rehabilitation. In the wake of such VR leveraging, our study aims to investigate the operation and usability assessment of VR devices of Taiwan’s older people over 70, who felt comfortable in virtual environments throughout the experiment and enjoyed VR task performance and interaction. We used two sets of virtual devices to play game levels and discuss elderly control and usage. The study shows that the two handheld controller designs (symmetric and asymmetric) significantly affected the intuitive mapping of older people’s use, with a more intuitive response to the natural mapping of asymmetric controllers mimicking hand shapes. Three key factors (oculomotor disturbance, disorientation, and nausea) were extracted from previous VR motion sickness studies, using the SSQ scale to measure motion sickness issues. The results indicate that more than half of the subjects were not affected by motion sickness issues, indirectly confirming some previous studies that older people are better off than young people with motion sickness. Therefore, more senior-friendly VR content is expected as most older people, physically<!--> <!-->aging though, yet with fewer sickness issues incurred, are willing to experience VR.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100974"},"PeriodicalIF":2.8,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253683","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}
Yuqian Sun , Hanyi Wang , Pok Man Chan , Morteza Tabibi , Yan Zhang , Huan Lu , Yuheng Chen , Chang Hee Lee , Ali Asadipour
{"title":"Bring game characters to the social space: Developing storytelling community AI agents driven by LLMs","authors":"Yuqian Sun , Hanyi Wang , Pok Man Chan , Morteza Tabibi , Yan Zhang , Huan Lu , Yuheng Chen , Chang Hee Lee , Ali Asadipour","doi":"10.1016/j.entcom.2025.100948","DOIUrl":"10.1016/j.entcom.2025.100948","url":null,"abstract":"<div><div>AI agents driven by Large Language Models (LLMs) are now ubiquitous in our daily life, so can they bring characters from games into reality? We address the integration of storytelling and AI agents driven by LLMs to develop engaging and believable fictional characters in community settings. Motivated by the potential of fictional characters to enhance social interactions, we introduce <em>Storytelling Community AI Agents</em> (SCAs) and the concept of <em>story engineering</em> to transform fictional game characters into ”live” social entities within player communities. Our story engineering process includes three steps: (1) Character and story creation, defining the SCA’s personality and worldview, (2) Presenting Live Stories to the Community, allowing the agent to recount challenges and seek suggestions, and (3) Communication with community members, enabling interaction between the agent and users. We employed the LLM GPT-3 to drive our SCAs, “David” and “Catherine,” and evaluated their performance in an online gaming community, “DE (Alias),” on Discord. Our mixed-method analysis, based on questionnaires (N=15) and interviews (N=8) with community members, reveals that storytelling significantly enhances the engagement and believability of AI agents in community settings.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"54 ","pages":"Article 100948"},"PeriodicalIF":2.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144204582","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":"Testing positive mood effects of playing Gris, a eudaimonic video game","authors":"Gary L. Wagener , Elisabeth Holl , André Melzer","doi":"10.1016/j.entcom.2025.100976","DOIUrl":"10.1016/j.entcom.2025.100976","url":null,"abstract":"<div><div>Video games (VGs) are known for their positive impact on players’ mood [<span><span>1</span></span>], emotions and emotion regulation [<span><span>2</span></span>], depressive symptoms [<span><span>3</span></span>], and general well-being [<span><span>4</span></span>]. However, only few studies have focused on the effects of eudaimonic (i.e., meaningful) VGs. In two laboratory studies (N = 145), we examined eudaimonic VG effects. In Study 1, we tested whether the game could improve mood by enhancing participants’ current emotional state. In Study 2, in addition to testing mood improvement, we explored the game’s potential for mood repair, defined as the ability to cope with acute negative distress and to alleviate negative emotions following a sadness induction. Additionally, we investigated whether the game could trigger physiological relaxation in both studies. We also hypothesized that people with higher depression scores might benefit more because VGs can improve depressive symptoms. Although there was no interaction with depression levels and no significant effect on mood improvement, playing the eudaimonic VG after sadness induction in Study 2 led to mood repair. In addition, the increase in heart rate variability in both studies indicated physiological relaxation. The present findings suggest that eudaimonic VGs can facilitate mood repair and physiological relaxation, thereby highlighting their potential for future clinical interventions.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"54 ","pages":"Article 100976"},"PeriodicalIF":2.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144242922","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":"Do games have the power to reduce power distance in co-design?","authors":"Ziheng Zhang , Tengjia Zuo , Yuqiao Du","doi":"10.1016/j.entcom.2025.100978","DOIUrl":"10.1016/j.entcom.2025.100978","url":null,"abstract":"<div><div>As globalization progresses, online co-design activities, including participants with different cultural backgrounds, offer distinctive insights from diverse perspectives, yet face challenges in adapting to cultural differences and bridging communication gaps. Power distance is considered a key factor that hinders co-design activities, especially in East Asian culture. In this study, we conducted a quasi-experiment to investigate the impact of a gameful co-design workshop on several key dimensions: participants’ perceptions of power distance, interpersonal communication, intrinsic motivation, and player experience of need satisfaction. A total of 92 participants were assigned to co-design groups under three different conditions: online game-based, online non-game-based, and offline non-game-based workshops. We examined the effectiveness of gameful design in these contexts and the correlation between perceived power distance and player experience. Our goal is to identify game design strategies that can reduce power distance and foster engagement in co-design, especially in hierarchical cultures. This research contributes to the fields of Human-Computer Interaction (HCI) and game design by offering actionable design strategies and theoretical insights to address social and collaborative innovation challenges in global co-design environments.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"54 ","pages":"Article 100978"},"PeriodicalIF":2.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144230520","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}