Pub Date : 2025-07-03DOI: 10.1016/j.entcom.2025.100982
Pablo Gutiérrez-Sánchez, Pedro P. Gómez-Martín, Pedro A. González-Calero, Marco A. Gómez-Martín
The increasing ubiquity of mobile devices has enabled the surge of interactive experiences at cultural heritage sites, enriching visitor immersion. However, adapting interactive resources for different settings and types of creators remains a challenge. This paper introduces EnigMachine Editor, a web-based authoring tool for crafting augmented reality-enabled adventures inspired by treasure hunts and escape rooms. Designed for curators and hobbyists, it simplifies the generation of custom experiences without prior technical expertise, streamlining development compared to using traditional game engines directly.
The main objective of this work is to comprehensively evaluate the usability of EnigMachine Editor for non-technical users, alongside its ability to generate engaging game experiences. A game experience study was first conducted in which participants interacted with games from the platform and subsequently completed the Game Experience Questionnaire (GEQ). Next, two usability studies were conducted in which participants first completed a tutorial with Single Ease Questions (SEQ) after each exercise, and then a series of both short- and long-term tasks on the tool concluded with the System Usability Scale (SUS) questionnaire. The results obtained demonstrate that EnigMachine Editoris able to generate satisfactory experiences for museum visitors and highlight desirable usability properties, especially in the short-term test group.
{"title":"Evaluating usability for an AR-enabled escape room authoring ecosystem","authors":"Pablo Gutiérrez-Sánchez, Pedro P. Gómez-Martín, Pedro A. González-Calero, Marco A. Gómez-Martín","doi":"10.1016/j.entcom.2025.100982","DOIUrl":"10.1016/j.entcom.2025.100982","url":null,"abstract":"<div><div>The increasing ubiquity of mobile devices has enabled the surge of interactive experiences at cultural heritage sites, enriching visitor immersion. However, adapting interactive resources for different settings and types of creators remains a challenge. This paper introduces <span>EnigMachine Editor</span>, a web-based authoring tool for crafting augmented reality-enabled adventures inspired by treasure hunts and escape rooms. Designed for curators and hobbyists, it simplifies the generation of custom experiences without prior technical expertise, streamlining development compared to using traditional game engines directly.</div><div>The main objective of this work is to comprehensively evaluate the usability of <span>EnigMachine Editor</span> for non-technical users, alongside its ability to generate engaging game experiences. A game experience study was first conducted in which participants interacted with games from the platform and subsequently completed the Game Experience Questionnaire (GEQ). Next, two usability studies were conducted in which participants first completed a tutorial with Single Ease Questions (SEQ) after each exercise, and then a series of both short- and long-term tasks on the tool concluded with the System Usability Scale (SUS) questionnaire. The results obtained demonstrate that <span>EnigMachine Editor</span>is able to generate satisfactory experiences for museum visitors and highlight desirable usability properties, especially in the short-term test group.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100982"},"PeriodicalIF":2.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144588065","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}
Pub Date : 2025-06-30DOI: 10.1016/j.entcom.2025.100990
Lu Huang , Wendan Yang
In film and television animation works, colour is an ideographic symbol distinct from other elements. Color language and image language are separate concepts, with image language unable to fully capture the ideographic nature of color. Even when images appear visually similar, differences in brightness can create significant contrasts or opposing meanings. Thus, color language plays an ideographic role between color and concept. This paper uses semantic segmentation techniques to integrate the three modalities of color content and text, establishing a consistent representation relationship. We propose a color-depth (RGB-D) image semantic segmentation method based on two-stream weighted Gabor convolutional network fusion. To capture Orientation- and scale-invariant features, we design a weighted Gabor orientation filter within a deep convolutional network (DCN) to adapt to changes in Orientation and scale. A wide residual-weighted Gabor convolutional network extracts features from the dual-stream images of colour and depth. To quantitatively assess our method’s representational ability regarding the ideographic functions of color language, we conduct extensive experiments on public datasets. The results demonstrate that the proposed algorithm outperforms existing RGB-D image semantic segmentation methods. Specifically, the technique achieves superior accuracy across several performance metrics, with a notable improvement of 2.5%–6.6% compared to baseline models. Our approach enhances segmentation precision for objects of varying scales and directions. It exhibits robustness in complex lighting environments, thus confirming its potential in real-world applications of color language in animation.
{"title":"Deep analysis on the color language in film and television animation works via semantic segmentation technique","authors":"Lu Huang , Wendan Yang","doi":"10.1016/j.entcom.2025.100990","DOIUrl":"10.1016/j.entcom.2025.100990","url":null,"abstract":"<div><div>In film and television animation works, colour is an ideographic symbol distinct from other elements. Color language and image language are separate concepts, with image language unable to fully capture the ideographic nature of color. Even when images appear visually similar, differences in brightness can create significant contrasts or opposing meanings. Thus, color language plays an ideographic role between color and concept. This paper uses semantic segmentation techniques to integrate the three modalities of color content and text, establishing a consistent representation relationship. We propose a color-depth (RGB-D) image semantic segmentation method based on two-stream weighted Gabor convolutional network fusion. To capture Orientation- and scale-invariant features, we design a weighted Gabor orientation filter within a deep convolutional network (DCN) to adapt to changes in Orientation and scale. A wide residual-weighted Gabor convolutional network extracts features from the dual-stream images of colour and depth. To quantitatively assess our method’s representational ability regarding the ideographic functions of color language, we conduct extensive experiments on public datasets. The results demonstrate that the proposed algorithm outperforms existing RGB-D image semantic segmentation methods. Specifically, the technique achieves superior accuracy across several performance metrics, with a notable improvement of 2.5%–6.6% compared to baseline models. Our approach enhances segmentation precision for objects of varying scales and directions. It exhibits robustness in complex lighting environments, thus confirming its potential in real-world applications of color language in animation.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100990"},"PeriodicalIF":2.8,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144570043","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}
Pub Date : 2025-06-29DOI: 10.1016/j.entcom.2025.100991
WeiYa Sun , MengJin Yao
Nowadays, leisure sports events are obtaining a significant role in the community at large, and they are acknowledged as an important choice in terms of lifestyle. The goal of these leisure sports events is to promote an active and healthy lifestyle while also fostering a sense of connection among participants of all abilities. Effective scheduling of leisure sports events based on fuzzy logic is important to handle uncertainties in the preference of participants over time and aims to enhance the efficiency and adaptability of the decision-making process. Hence, a technique named Fuzzy-assisted Leisure Sports Scheduling and Optimization (FLSS-O) is introduced to address the complexities in identifying the influencing factors of events for efficient decision making. Initially, the research focuses on collecting survey responses from participants in leisure sports events to assess their satisfaction and align event schedules with their preferences. The dynamic event scheduling incorporates linguistic preferences, and a Fuzzy Analytic Hierarchy Process(F-AHP) is applied to determine weights through a pairwise comparison matrix. The outcomes are used to calculate a fuzzy weighted sum for each selected criterion, which involves a decision-making process. The study emphasizes the importance of leisure sports to participants by prioritizing iteratively collected feedback and utilizing genetic algorithms to optimize the scheduling process continually. In this decision process, the imprecise alternatives in scheduling the events towards the specific performance based on criteria are fine-tuned by maximizing the participant preferences. The results demonstrate the effectiveness of our approach in aiding leisure sports event organizers to make informed decisions that balance time slots, adaptability, preferences, and participant-centric scheduling among varying age groups.
{"title":"Optimization and scheduling of leisure sports events based on fuzzy decision support system","authors":"WeiYa Sun , MengJin Yao","doi":"10.1016/j.entcom.2025.100991","DOIUrl":"10.1016/j.entcom.2025.100991","url":null,"abstract":"<div><div>Nowadays, leisure sports events are obtaining a significant role in the community at large, and they are acknowledged as an important choice in terms of lifestyle. The goal of these leisure sports events is to promote an active and healthy lifestyle while also fostering a sense of connection among participants of all abilities. Effective scheduling of leisure sports events based on fuzzy logic is important to handle uncertainties in the preference of participants over time and aims to enhance the efficiency and adaptability of the decision-making process. Hence, a technique named Fuzzy-assisted Leisure Sports Scheduling and Optimization (FLSS-O) is introduced to address the complexities in identifying the influencing factors of events for efficient decision making. Initially, the research focuses on collecting survey responses from participants in leisure sports events to assess their satisfaction and align event schedules with their preferences. The dynamic event scheduling incorporates linguistic preferences, and a Fuzzy Analytic Hierarchy Process(F-AHP) is applied to determine weights through a pairwise comparison matrix. The outcomes are used to calculate a fuzzy weighted sum for each selected criterion, which involves a decision-making process. The study emphasizes the importance of leisure sports to participants by prioritizing iteratively collected feedback and utilizing genetic algorithms to optimize the scheduling process continually. In this decision process, the imprecise alternatives in scheduling the events towards the specific performance based on criteria are fine-tuned by maximizing the participant preferences. The results demonstrate the effectiveness of our approach in aiding leisure sports event organizers to make informed decisions that balance time slots, adaptability, preferences, and participant-centric scheduling among varying age groups.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100991"},"PeriodicalIF":2.8,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535522","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}
Pub Date : 2025-06-29DOI: 10.1016/j.entcom.2025.100989
Winston Wenchen Guo , Wenjuan Chen , Yining Zhang , Caro Menghan Shi , Hailiang Wang
As urbanization accelerates, modern cities face many challenges. One key dimension is the lack of identity awareness and emotional interaction between the public and the city. This paper reports an interdisciplinary project, Portrait of the City, an interactive installation located in various public spaces in Beijing, which aims to utilize Human-computer interaction (HCI) technologies (localized media data-driven, motion capture, AIGC, etc.) in conjunction with public spaces to bridge the emotional and humanities of the public’s connection to the city. We further evaluated its accessibility and practical effectiveness through exhibitions and mixed research methodology. The findings suggest that public interactive installations can activate collective memories, evoke diverse personal experiences, encourage ongoing dialogue about the city, and promote a closer link between civic and place identities. Our interdisciplinary case study may provide insights into HCI and public design as well as practical ideas for fostering more vibrant and culturally distinctive cities in the future.
{"title":"Portrait of the City: Case Study on Bridging Place Identity and Emotional Engagement via Interactive Art Installations","authors":"Winston Wenchen Guo , Wenjuan Chen , Yining Zhang , Caro Menghan Shi , Hailiang Wang","doi":"10.1016/j.entcom.2025.100989","DOIUrl":"10.1016/j.entcom.2025.100989","url":null,"abstract":"<div><div>As urbanization accelerates, modern cities face many challenges. One key dimension is the lack of identity awareness and emotional interaction between the public and the city. This paper reports an interdisciplinary project, Portrait of the City, an interactive installation located in various public spaces in Beijing, which aims to utilize Human-computer interaction (HCI) technologies (localized media data-driven, motion capture, AIGC, etc.) in conjunction with public spaces to bridge the emotional and humanities of the public’s connection to the city. We further evaluated its accessibility and practical effectiveness through exhibitions and mixed research methodology. The findings suggest that public interactive installations can activate collective memories, evoke diverse personal experiences, encourage ongoing dialogue about the city, and promote a closer link between civic and place identities. Our interdisciplinary case study may provide insights into HCI and public design as well as practical ideas for fostering more vibrant and culturally distinctive cities in the future.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100989"},"PeriodicalIF":2.8,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572550","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}
Pub Date : 2025-06-29DOI: 10.1016/j.entcom.2025.100987
Lauro V.R. Cavadas, Esteban W.G. Clua, Troy C. Kohwalter, Sidney A. Melo
Non-Player Characters (NPCs) play a crucial role in the immersive experience of a game world. When designed effectively, NPCs have unique personalities and react realistically to player actions. Meeting players’ expectations for NPCs to resemble real individuals has become a major focus for game developers striving to enhance immersion.
In this work, we propose the use of data collected via provenance to create a model for training an NPC to act similarly to a human player using Imitation Learning. The main goal of this work is to improve the training efficiency of the agent, while preserving the high level of believability achieved in previous work. To this end, provenance is employed not only as a form of logging, but also as a means to guide and optimize the learning process — a contribution not previously explored in the literature.
To validate our model, we used the DodgeBall game within the Unity ML-Agents Toolkit for the Unity Engine. We compared our trained agent with an agent from previous work that used provenance solely for logging. Using win rate as a proxy for training efficiency, agents trained with our new model outperformed those trained with the previous approach, when evaluated after the same number of training steps.
Additionally, we created scenarios in which players participated in matches against both the new and previous agents, rating their believability. The results were promising in terms of both perceived believability and the efficiency of the training process.
In this work we propose to use data collected via provenance to create a model for training an NPC to act similarly to a human player using Imitation Learning. We use provenance not only as a form of log, but also to improve training efficiency, something that has not been presented in the literature until now. To validate our model, we used the DodgeBall game within the Unity ML-Agents Toolkit for Unity Engine. We compared our trained agent with an agent trained in previous work, which use provenance as a form of logging. Through matches between the two agents, those that were trained with our new model demonstrated greater efficiency. Additionally, we created scenarios of players participating in games against our current agent and our previous solutions, rating the believability of each. The results were quite promising, both in terms of believability and training efficiency.
{"title":"Enhancing imitation learning training for non-player characters based on provenance data","authors":"Lauro V.R. Cavadas, Esteban W.G. Clua, Troy C. Kohwalter, Sidney A. Melo","doi":"10.1016/j.entcom.2025.100987","DOIUrl":"10.1016/j.entcom.2025.100987","url":null,"abstract":"<div><div>Non-Player Characters (NPCs) play a crucial role in the immersive experience of a game world. When designed effectively, NPCs have unique personalities and react realistically to player actions. Meeting players’ expectations for NPCs to resemble real individuals has become a major focus for game developers striving to enhance immersion.</div><div>In this work, we propose the use of data collected via provenance to create a model for training an NPC to act similarly to a human player using Imitation Learning. The main goal of this work is to improve the training efficiency of the agent, while preserving the high level of believability achieved in previous work. To this end, provenance is employed not only as a form of logging, but also as a means to guide and optimize the learning process — a contribution not previously explored in the literature.</div><div>To validate our model, we used the DodgeBall game within the Unity ML-Agents Toolkit for the Unity Engine. We compared our trained agent with an agent from previous work that used provenance solely for logging. Using win rate as a proxy for training efficiency, agents trained with our new model outperformed those trained with the previous approach, when evaluated after the same number of training steps.</div><div>Additionally, we created scenarios in which players participated in matches against both the new and previous agents, rating their believability. The results were promising in terms of both perceived believability and the efficiency of the training process.</div><div>In this work we propose to use data collected via provenance to create a model for training an NPC to act similarly to a human player using Imitation Learning. We use provenance not only as a form of log, but also to improve training efficiency, something that has not been presented in the literature until now. To validate our model, we used the DodgeBall game within the Unity ML-Agents Toolkit for Unity Engine. We compared our trained agent with an agent trained in previous work, which use provenance as a form of logging. Through matches between the two agents, those that were trained with our new model demonstrated greater efficiency. Additionally, we created scenarios of players participating in games against our current agent and our previous solutions, rating the believability of each. The results were quite promising, both in terms of believability and training efficiency.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100987"},"PeriodicalIF":2.8,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572551","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}
Pub Date : 2025-06-24DOI: 10.1016/j.entcom.2025.100979
Boning Li, Lehao Zhou, Junichi Hoshino
In recent years, cultural learning has required the design of experiential and reflective environments that go beyond mere knowledge acquisition to support the understanding and internalization of cultural values. This study constructed a collaborative VR learning environment focused on food culture, enabling learners to actively interpret and engage in the meaning-making of cultural values in a virtual space. The system consists of scenarios based on three themes: ingredients, tableware, and cuisine. It offers experiences that engage learners with cultural elements through exploration, observation, and cooking. Through voice and non-verbal gestures via avatars, learners shared their insights and emotions, deepening their learning. A comparative experiment showed that participants in the collaborative learning condition significantly outperformed those in the individual learning condition in terms of recognition of cultural values, knowledge acquisition, learning motivation, and cultural awareness. Observations also revealed the natural formation of joint attention through gestures such as pointing and shared gaze, which facilitated reflective meaning-making. Based on these findings, four design recommendations were derived: (1) supporting meaning-making through experience and dialogue, (2) supporting collaboration through non-verbal interaction, (3) designing immersive experiences that enhance intrinsic motivation, and (4) creating scenarios and tasks that encourage reflection.
{"title":"Collaborative VR environment for supporting food culture learning","authors":"Boning Li, Lehao Zhou, Junichi Hoshino","doi":"10.1016/j.entcom.2025.100979","DOIUrl":"10.1016/j.entcom.2025.100979","url":null,"abstract":"<div><div>In recent years, cultural learning has required the design of experiential and reflective environments that go beyond mere knowledge acquisition to support the understanding and internalization of cultural values. This study constructed a collaborative VR learning environment focused on food culture, enabling learners to actively interpret and engage in the meaning-making of cultural values in a virtual space. The system consists of scenarios based on three themes: ingredients, tableware, and cuisine. It offers experiences that engage learners with cultural elements through exploration, observation, and cooking. Through voice and non-verbal gestures via avatars, learners shared their insights and emotions, deepening their learning. A comparative experiment showed that participants in the collaborative learning condition significantly outperformed those in the individual learning condition in terms of recognition of cultural values, knowledge acquisition, learning motivation, and cultural awareness. Observations also revealed the natural formation of joint attention through gestures such as pointing and shared gaze, which facilitated reflective meaning-making. Based on these findings, four design recommendations were derived: (1) supporting meaning-making through experience and dialogue, (2) supporting collaboration through non-verbal interaction, (3) designing immersive experiences that enhance intrinsic motivation, and (4) creating scenarios and tasks that encourage reflection.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100979"},"PeriodicalIF":2.8,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518522","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}
Pub Date : 2025-06-23DOI: 10.1016/j.entcom.2025.100983
Feizhou Quan , Tianya Xu , Luning Zang , Yanlai Li , Dianfeng Zhang
Enhancing the competitiveness of live music venues (LMVs) carries significant implications for the sustainable development of the music industry. This study proposes a quantitative evaluation method that integrates mixed probabilistic information with cumulative prospect theory (CPT), aiming to accurately assess the competitiveness of live music venues. Online customer reviews (OCR) were adopted, core requirement attributes were identified using the Latent Dirichlet Allocation (LDA) model, and sentiment scores were derived through employing the Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory (BERT-BiLSTM) model. Subsequently, a satisfaction model based on the Probabilistic Linguistic Term Set (PLTS) framework was constructed to quantitatively assess customer satisfaction levels. Building on this, the competitiveness index(CI) of LMVs was determined using a hybrid probabilistic information approach. CPT was then applied to evaluate the competitiveness rankings of different types of live music venues. Finally, the sensitivity and comparative analyses confirm the high accuracy, robustness, and generalizability of the proposed methodology. The results of this study deepen enterprises’ understanding of customer consumption behavior patterns and clarify the core indicators influencing competitiveness. This provides valuable insights for strategic adjustments aimed at enhancing competitiveness and offers a solid foundation for the sustainable development of the live music industry.
{"title":"Research on improving the competitiveness of live music venues based on hybrid probabilistic information and cumulative prospect theory","authors":"Feizhou Quan , Tianya Xu , Luning Zang , Yanlai Li , Dianfeng Zhang","doi":"10.1016/j.entcom.2025.100983","DOIUrl":"10.1016/j.entcom.2025.100983","url":null,"abstract":"<div><div>Enhancing the competitiveness of live music venues (LMVs) carries significant implications for the sustainable development of the music industry. This study proposes a quantitative evaluation method that integrates mixed probabilistic information with cumulative prospect theory (CPT), aiming to accurately assess the competitiveness of live music venues. Online customer reviews (OCR) were adopted, core requirement attributes were identified using the Latent Dirichlet Allocation (LDA) model, and sentiment scores were derived through employing the Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory (BERT-BiLSTM) model. Subsequently, a satisfaction model based on the Probabilistic Linguistic Term Set (PLTS) framework was constructed to quantitatively assess customer satisfaction levels. Building on this, the competitiveness index(CI) of LMVs was determined using a hybrid probabilistic information approach. CPT was then applied to evaluate the competitiveness rankings of different types of live music venues. Finally, the sensitivity and comparative analyses confirm the high accuracy, robustness, and generalizability of the proposed methodology. The results of this study deepen enterprises’ understanding of customer consumption behavior patterns and clarify the core indicators influencing competitiveness. This provides valuable insights for strategic adjustments aimed at enhancing competitiveness and offers a solid foundation for the sustainable development of the live music industry.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100983"},"PeriodicalIF":2.8,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144490270","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}
This study investigates the impact of video gaming activities versus watching a nature film on heart rate (HR) and vagally-mediated heart rate variability (vmHRV) in healthy young men. Employing a randomized within-subject design, 31 male participants (average age: 23 years; BMI: 25.68; gaming experience: 8.69 years; daily gaming time: 1.96 h) were assigned to either start with playing video games for 120 min on two consecutive days, followed by watching a nature film for the same duration in the following week, or the reverse order. HR and vmHRV were measured via ECG before and after each activity. Results showed that Video gaming activities had no significant effect on HR and vmHRV. It is indicated that video gaming does not appear to have notable physiological impacts on the autonomic nervous system. Conversely, watching a nature film significantly reduced HR and increased vmHRV compared to playing video games. These findings suggest that watching nature films exerts a calming effect and enhances parasympathetic activity, potentially offering health benefits through stress reduction and relaxation. This study contributes important insights into the physiological effects of digital media and underscores the need for further research in this area.
Objective
Playing video games is associated with increased autonomic sympathetic nervous system activity, which may lead to a reduction in vagally-mediated HRV (vmHRV) and Heart Rate (HR). Hence the aim of this study was to investigate the effect of the vmHRV and HR in healthy young adults between playing a computer game and watching a nature film.
Methods
The study was designed as a randomized within subject design with N = 31 male players (age: M = 23,00 ± 3,53 years, BMI: M = 25,68 ± 3,34, time of experience: M = 8,69 ± 4,74 years, and daily gaming time: M = 1,96 ± 1,32 h). Group A started in week 1 with two consecutive days of 120 min gaming and in week 2 with two consecutive days of 120 min watching a film. Group B started in the opposite order. HR and HRV were measured with ECG before and after the intervention.
Results
The results demonstrated that playing videogames had no effect on HR (t(55) = 1.80, p = 0.08) and vmHRV measured by HF-HRV (t(55) = -1.57, p = 0.12) and RMSSD (t(55) = -1.48, p = 0.15). In contrast, watching a nature film led to a lower HR (t(561.6) = -7.29, p = 0<.001) and an increase vmHRV measured by HF-HRV (t(561.4) = 4.02, p = 0<.001) and RMSSD (t(561.4) = 4.97, p = 0<.001) compared to playing videogame.
Conclusions
These findings indicate that, among this group of male participants, playing video games did not seem to affect the autonomic nervous system in a manner that notably modified heart
本研究调查了视频游戏活动与观看自然电影对健康年轻男性心率（HR）和迷走神经介导的心率变异性（vmHRV）的影响。采用随机受试者内设计，31名男性受试者(平均年龄：23岁；体重指数:25.68;游戏经验：8.69年；每天的游戏时间（1.96小时）被分配到连续两天玩120分钟的视频游戏，然后在接下来的一周看同样时间的自然电影，或者相反的顺序。在每次活动前后通过ECG测量HR和vmHRV。结果显示，电子游戏活动对HR和vmHRV无显著影响。这表明电子游戏似乎对自主神经系统没有显著的生理影响。相反，与玩电子游戏相比，观看自然电影可以显著降低HR，增加vmHRV。这些发现表明，观看自然电影有镇静作用，增强副交感神经活动，可能通过减轻压力和放松对健康有益。这项研究为数字媒体的生理效应提供了重要的见解，并强调了在这一领域进一步研究的必要性。玩电子游戏与自主交感神经系统活动增加有关，这可能导致迷走神经介导的HRV （vmHRV）和心率（HR）的降低。因此，本研究的目的是调查在玩电脑游戏和看自然电影之间，健康年轻人的vmHRV和HR的影响。方法本研究采用随机受试者设计，共有31名男性游戏玩家（年龄：M = 23,00±3,53岁，BMI: M = 25,68±3,34，经验时间：M = 8,69±4,74岁，每日游戏时间：M = 1,96±1,32小时）。A组在第一周开始连续两天玩120分钟的游戏，在第二周连续两天看120分钟的电影。B组以相反的顺序开始。干预前后分别用心电图测量HR、HRV。结果玩电子游戏对HR （t(55) = 1.80, p = 0.08）和vmHRV （t(55) = -1.57, p = 0.12）和RMSSD （t(55) = -1.48, p = 0.15）没有影响。相比之下，观看自然电影会导致较低的HR （t(561.6) = -7.29, p = 0<.001）和更高的vmHRV （t(561.4) = 4.02, p = 0<.001）和RMSSD （t(561.4) = 4.97, p = 0<.001）。这些发现表明，在这组男性参与者中，玩电子游戏似乎并没有以明显改变心率或迷走神经张力的方式影响自主神经系统。相反，观看自然纪录片会唤起一种平静感，增加副交感神经活动，这可能会促进整体健康。
{"title":"Is gaming stress or Relaxation? An HRV-Based Investigation of physiological responses in young adults","authors":"André Alesi , Kristina Klier , Benedict Herhaus , Klara Brixius , Ingo Froböse , Katja Petrowski , Matthias Wagner","doi":"10.1016/j.entcom.2025.100981","DOIUrl":"10.1016/j.entcom.2025.100981","url":null,"abstract":"<div><div>This study investigates the impact of video gaming activities versus watching a nature film on heart rate (HR) and vagally-mediated heart rate variability (vmHRV) in healthy young men. Employing a randomized within-subject design, 31 male participants (average age: 23 years; BMI: 25.68; gaming experience: 8.69 years; daily gaming time: 1.96 h) were assigned to either start with playing video games for 120 min on two consecutive days, followed by watching a nature film for the same duration in the following week, or the reverse order. HR and vmHRV were measured via ECG before and after each activity. Results showed that Video gaming activities had no significant effect on HR and vmHRV. It is indicated that video gaming does not appear to have notable physiological impacts on the autonomic nervous system. Conversely, watching a nature film significantly reduced HR and increased vmHRV compared to playing video games. These findings suggest that watching nature films exerts a calming effect and enhances parasympathetic activity, potentially offering health benefits through stress reduction and relaxation. This study contributes important insights into the physiological effects of digital media and underscores the need for further research in this area.</div></div><div><h3>Objective</h3><div>Playing video games is associated with increased autonomic sympathetic nervous system activity, which may lead to a reduction in vagally-mediated HRV (vmHRV) and Heart Rate (HR). Hence the aim of this study was to investigate the effect of the vmHRV and HR in healthy young adults between playing a computer game and watching a nature film.</div></div><div><h3>Methods</h3><div>The study was designed as a randomized within subject design with <em>N =</em> 31 male players (age: <em>M =</em> 23,00 ± 3,53 years, BMI: <em>M =</em> 25,68 ± 3,34, time of experience: <em>M =</em> 8,69 ± 4,74 years, and daily gaming time: <em>M =</em> 1,96 ± 1,32 h). Group A started in week 1 with two consecutive days of 120 min gaming and in week 2 with two consecutive days of 120 min watching a film. Group B started in the opposite order. HR and HRV were measured with ECG before and after the intervention.</div></div><div><h3>Results</h3><div>The results demonstrated that playing videogames had no effect on HR (<em>t</em>(55) = 1.80, <em>p</em> = 0.08) and vmHRV measured by HF-HRV (<em>t</em>(55) = -1.57, <em>p</em> = 0.12) and RMSSD (<em>t</em>(55) = -1.48, <em>p</em> = 0.15). In contrast, watching a nature film led to a lower HR (<em>t</em>(561.6) = -7.29, <em>p</em> = 0<.001) and an increase vmHRV measured by HF-HRV (<em>t</em>(561.4) = 4.02, <em>p</em> = 0<.001) and RMSSD (<em>t</em>(561.4) = 4.97, <em>p</em> = 0<.001) compared to playing videogame.</div></div><div><h3>Conclusions</h3><div>These findings indicate that, among this group of male participants, playing video games did not seem to affect the autonomic nervous system in a manner that notably modified heart","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100981"},"PeriodicalIF":2.8,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365095","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}
Pub Date : 2025-06-18DOI: 10.1016/j.entcom.2025.100980
Caner BALIM
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.
{"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}
Pub Date : 2025-06-16DOI: 10.1016/j.entcom.2025.100972
Irene C.E. van Blerck , Edirlei Soares de Lima , Margot M.E. Neggers , Toon Calders
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.
{"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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号