Entertainment Computing最新文献

{"title":"Chasing the Rush: How horror games trigger adrenaline and fuel Fear-Inducing elements","authors":"Klarisse Nicole N. Savino ,&nbsp;Ronila Angela B. Mateo ,&nbsp;Ardvin Kester S. Ong","doi":"10.1016/j.entcom.2025.101001","DOIUrl":"10.1016/j.entcom.2025.101001","url":null,"abstract":"<div><div>Fear has been capitalized through horror video games, driving players to develop a craving for adrenaline-fueled fear, fostering fear-inducing elements, and leading to unhealthy behavioral patterns. This study examined how fear and adrenaline are triggered in horror video games, influencing play intention and actual gameplay, and how these experiences contribute to fear-inducing elements analyzed based on their stimulus-organism-response (S-O-R) aspects. The objective was to determine significant predictors of actual gaming of horror video games by analyzing data from 1,015 valid players using the Partial Least Squares Structural Equation Modeling (PLS-SEM) approach with SOR-based analysis. Findings revealed that fear-inducing elements strongly influenced psychological response and emotional value. In contrast, game design elements primarily impacted perceived control and play intention. It was revealed that both psychological and physiological responses contribute to emotional value, while cognitive processing played a more dominant role than physiological arousal in shaping emotional impact. In accordance, play intention strongly predicts actual gameplay, but excessive fear-inducing elements can reduce actual gameplay. These results highlight the need for game designers and developers to balance fear elements with adaptive difficulty, strategic pacing, and perceived control to enhance immersion while being physiologically, and psychologically safe. Horror game players can use these insights to manage their expectations and experiences effectively. For gaming industry marketers and publishers, responsible promotion of horror games should emphasize thrilling engagement and psychological safety, ensuring sustainable and innovative gaming practices.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101001"},"PeriodicalIF":2.4,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723462","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":"Dynamic difficulty adjustment using a large language model: A case study in magic: The Gathering","authors":"Xiaoxu Li ,&nbsp;Zifan Ye ,&nbsp;Yi Xia ,&nbsp;Ruck Thawonmas","doi":"10.1016/j.entcom.2025.100997","DOIUrl":"10.1016/j.entcom.2025.100997","url":null,"abstract":"<div><div>This paper presents a framework called LLM-MTG-DDA, which uses a large language model (LLM) in the real-world card game Magic: The Gathering (MTG) to act as a player and implement a dynamic difficulty adjustment (DDA) mechanism. LLMs, as a highly useful technology, have been explored across various fields. However, research on using LLMs for DDA in games, particularly in complex turn-based games, is very limited. In this paper, GPT-4o acts as two players in a simplified version of MTG. One GPT-4o player plays as a regular player (LLM-Player), while the other GPT-4o player adjusts its strategy based on the current game state to balance the difficulty (LLM-DDA). Our LLM-MTG-DDA framework, with a suitable objectives for different players, demonstrates reasonable DDA, with the LLM-Player’s win rate and the win rate per round (excluding draws) both approaching 50%. This framework provides insights for applying LLMs as DDA mechanisms in other similar games.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100997"},"PeriodicalIF":2.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739408","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":"AI-powered virtual streamers and viewer behavior: An image-inspiration-behavior framework","authors":"Ting (Tina) Li ,&nbsp;Zhongyuan Zhou ,&nbsp;Xianfeng Zhang ,&nbsp;Yang Zhou ,&nbsp;Si Wen","doi":"10.1016/j.entcom.2025.101000","DOIUrl":"10.1016/j.entcom.2025.101000","url":null,"abstract":"<div><div>Today, a new form of live-streaming has emerged: virtual streamers powered by Artificial Intelligence technology, which autonomously perform live-streaming tasks as human streamers do. This form of live-streaming has quickly gained popularity. However, studies in this area are scarce. This study aims to fill this research gap by investigating how virtual AI streamers impact viewers by adopting the image-inspiration-behavior framework, in which the image of virtual AI streamers is described by warmth, competence, and coolness, and behavior is studied as interaction and purchase intentions. The data were collected from 559 participants via a scenario-based survey. The partial least squares – structural equation modeling and artificial neural network are used to analyze the data. It was found that the three image dimensions (warmth, competence, and coolness) influence consumer interaction and purchase intentions through the mediating effect of inspiration. The findings of this study advance previous studies mainly by investigating how virtual AI streamers impact viewer behaviors and offer insights to live-streaming companies in their adoption of virtual AI streamers.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101000"},"PeriodicalIF":2.8,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695283","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":"Leveraging deep reinforcement learning for dynamic NPC behavior and enhanced player experience in unity3d","authors":"Ahmad Affandi Supli,&nbsp;Xu Siqi","doi":"10.1016/j.entcom.2025.101007","DOIUrl":"10.1016/j.entcom.2025.101007","url":null,"abstract":"<div><div>With the innovation of information technology and the improvement of computer hardware and software, players’ needs gradually change from pursuing the ultimate visual and auditory feast to the inner performance, gameplay, interactive elements, etc. As an essential part of game content, game AI plays the role of communication and interaction with players. Since the emergence of game AI, it has been paid attention to by game developers. However, it is also a difficult job to make brilliant game AI. The common approaches to implementing game AI are finite state machines and behavior trees. Still, these two approaches require much work to implement flexible game AI and are difficult to maintain later. Therefore, this paper aims to investigate machine learning to train a compliant and flexible game AI. Specifically, this paper adopts a method to train game AI in Unity scenes using machine learning methods such as deep reinforcement learning with the help of the ML-Agents toolkit and Python programming interface. In order to better test the performance of the machine learning method, this study designs a game based on the Unity game engine, which includes a game AI implemented using behavior trees and machine learning. Through the production process and the final implementation results, this paper compares the differences in design ideas and implementation process between using behavior trees and using machine learning to implement game AI, as well as the advantages and disadvantages of each. The purpose of this study is to promote machine learning in the field of game research and achieve higher operational efficiency. Relevant existing principles and guidelines inform the game design process. In addition, the game proposed in this paper can be used as future research to promote machine learning in games to achieve a more efficient, more straightforward design and better player experience. After the game implementation, a quantitative research method is used to measure the players’ immersion in the game and the players’ satisfaction with the designed game AI. The evaluation results showed that most respondents believed that the proposed agents performed well against both human players and inbuilt game agents.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101007"},"PeriodicalIF":2.8,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703555","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":"Developing an advanced machine learning model for identifying virtual montages in digital media","authors":"Yuxuan Liu","doi":"10.1016/j.entcom.2025.101002","DOIUrl":"10.1016/j.entcom.2025.101002","url":null,"abstract":"<div><div>Virtual montages are compositions that blend several digital materials to produce a new, visually appealing narrative and are becoming increasingly popular, as a result of the quick development of digital media. Virtual montages have emerged as a potent technique for improving visual storytelling and content presentation across platforms in the digital age. However, the quick expansion of digital content has made advanced methods for effectively recognizing and classifying these montages necessary. This work suggests a novel method for virtual montage identification across a broad range of visual themes, content types, and media resolutions, and resolutions utilizing an Adaptive Flower Pollination Optimized Mutual Information with Naïve Bayes (AFPO-MI-NB) model. The research’s dataset comprises a variety of content from virtual montage detection dataset which enables the model to generalize effectively to data from the real world. To improve the model’s capacity to handle various image and video qualities, pre-processing methods, including data augmentation and pixel value normalization are used. Convolutional neural networks (CNN) are used for feature extraction to capture spatial patterns. The model uses AFPO-MI-NB classification to enhance classification accuracy and computational efficiency. AFPO allows for more adaptable feature weights, MI evaluates the relationship between visual features and the classification task, and NB classifier processes feature matrices for binary classification. The hybrid approach strengthens feature selection through global and local searches, resulting in a model that enhances classification accuracy and improves computational efficiency. According to the experimental data, this model provides a reliable solution for virtual montage identification across a variety of media formats, outperforming current techniques in terms of F1-score of 0.95, recall of 0.92, and precision of 0.97. This work has significant applications in automated digital media analysis, copyright enforcement, and content control.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101002"},"PeriodicalIF":2.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723154","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 game-based psychological empowerment and its motivational and wellbeing effects","authors":"Jukka Vahlo ,&nbsp;Suvi K. Holm ,&nbsp;Johanna K. Kaakinen ,&nbsp;Aki Koponen","doi":"10.1016/j.entcom.2025.100970","DOIUrl":"10.1016/j.entcom.2025.100970","url":null,"abstract":"<div><div>This study empirically investigates how individuals experience psychological empowerment through gaming compared to their daily life interactions. Drawing on a survey of 2,594 participants from Finland and Denmark, we examine the prevalence, predictors, and implications of psychological empowerment in gaming. Our findings show that 29 percent of respondents from the nationally representative subsamples in both countries report experiencing greater psychological empowerment in gaming than in life in general. Further analysis using Partial Least Squares Structural Equation Modeling (PLS-SEM) reveals that gameplay preferences, positive affect, and playtime predict game-based psychological empowerment. Moreover, the meaningfulness component of game-based empowerment significantly influences gaming motivation — particularly immersion, achievement, relaxation, and challenge motives — as well as subjective vitality in daily life, suggesting potential transfer effects. Adapting Spreitzer’s (1995) model of psychological empowerment, this study contextualizes these findings within gaming experiences. The results contribute to a deeper understanding of psychological empowerment in games and offer insights for game design, emphasizing the value of creating meaningful and empowering play experiences.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100970"},"PeriodicalIF":2.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144723155","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":"Emotion dynamics in social deception games: Analysis of professional and nonprofessional players through electrodermal activity in werewolf games","authors":"Sho Mitarai ,&nbsp;Chang Liu ,&nbsp;Goshiro Yamamoto ,&nbsp;Nagisa Munekata","doi":"10.1016/j.entcom.2025.100986","DOIUrl":"10.1016/j.entcom.2025.100986","url":null,"abstract":"<div><div>The development of AI systems capable of emotionally resonant communication remains a significant challenge. This study examines how humans influence emotions in social deception games by comparing professional and non-professional players. We measured electrodermal activity during gameplay to capture physiological emotional responses and analyzed communication patterns during periods of high emotional arousal. Our results revealed distinct communication strategies: professional players maintained persuasion-based approaches under high arousal, while nonprofessional players shifted toward information-focused communication. Statistical analysis confirmed significant differences in expression patterns between expertise levels. Professional players exhibited more stable emotional states during gameplay, indicating better emotional regulation. These findings inform the design of AI systems that can adapt their communication strategies based on recipient characteristics, advancing the development of emotionally intelligent artificial agents.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100986"},"PeriodicalIF":2.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739409","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":"An optimized deep learning approach for detection and classification of player actions in football game","authors":"K. Kausalya ,&nbsp;Kanaga Suba Raja S ,&nbsp;S. Sudha","doi":"10.1016/j.entcom.2025.101003","DOIUrl":"10.1016/j.entcom.2025.101003","url":null,"abstract":"<div><div>Player position detection and movement prediction is a hot research topic in sports. In this research work, the detection of players and classification of actions are performed using deep learning algorithms You Only Look Once (YOLO-V5) and Mayfly optimized deep neural network. The major contribution of this work is YOLO-V5, MixNet Convolutional Neural Network (MixNetCNN), and the mayfly optimization algorithm is applied for new domains like player actions in football games to show these techniques’ innovative performance. Here, the YOLOv5 (version 6.1) is used to accurately detect and classify the actions in football games. MixNet CNN is utilized to resolve the overfitting issue while classifying the actions of the football players. The mayfly optimization algorithm is utilized for optimizing the Boltzmann machine weights and parameters of classifiers helps to resolve the local optima issues. Experimentations on our dataset provide better prediction performance for recall, precision, f1-score, and mean average precision (mAP) metrics. The precision obtained by the proposed model is the maximum for all classes when the confidence score is 0.911. Comparative analysis with the existing approaches validates the better performance of the proposed detection and classification model.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 101003"},"PeriodicalIF":2.8,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703463","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":"Dynamic notification placement based on gaze concentration in HMD-VR","authors":"Kuma Kawakubo,&nbsp;Haruki Takahashi,&nbsp;Kohei Matsumura","doi":"10.1016/j.entcom.2025.100993","DOIUrl":"10.1016/j.entcom.2025.100993","url":null,"abstract":"<div><div>Virtual Reality (VR) offers users immersive experiences, but it has been shown that users often need messages and notifications from the outside world even during VR activities. However, inappropriate notification placement can lead to unnecessary task interruptions and information overload when notifications obstruct important visual areas or are positioned outside users’ attention zones. To address this issue, this study proposes a system that dynamically arranges notifications at different gaze concentration levels to evaluate optimal placement strategies in VR. This system utilizes eye-tracking technology to generate a 360-degree heatmap, identifying where users focus their attention. Notifications are then placed at three different gaze concentration levels (20th, 55th, and 85th percentiles) to examine the effects of placement proximity to attention areas. An experiment was conducted to evaluate the impact of notification placement on user experience. Results indicate that in environments with limited gaze movement, positioning notifications in high-gaze areas enhances visibility and recognition. Additionally, varying notification positions across different gaze concentration areas did not significantly affect perceived intrusiveness, urgency, immersion reduction, or comprehension. These findings suggest that gaze-adaptive notification placement can improve visibility without negatively impacting user experience, contributing to more effective VR notification systems.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100993"},"PeriodicalIF":2.4,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739410","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":"Can data journalism be sniffed? Exploring the possibilities of olfactory interfaces for the presentation of data journalism information","authors":"Winston Wenchen GUO ,&nbsp;Zhirui CHEN ,&nbsp;Caro Menghan SHI ,&nbsp;Guoyu SUN ,&nbsp;Hailiang WANG","doi":"10.1016/j.entcom.2025.100996","DOIUrl":"10.1016/j.entcom.2025.100996","url":null,"abstract":"<div><div>In recent years, data journalism has seen significant global growth, yet its presentation remains visual. With the advancement of sensory journalism and immersive technologies, olfaction has the potential to bring a unique experience and value to users as an interface for data journalism. In this study, we innovatively used olfactory interaction technology and developed a prototype olfactory device for data journalism. Then, a pilot study (<em>N</em> = 36) was conducted to evaluate the impact of the olfaction interface on users’ perception, experience, and memory. Preliminary results suggest that the olfactory interface is effective in several ways, including aiding storytelling, enhancing users’ long-term memory of news content (especially qualitative data), and increasing user engagement and immersion. We further shared our experiences, design insights, and lessons learned regarding the olfactory mapping method, the olfactory interface’s value in data journalism, the challenges faced, and the scope for future applications. While still in its nascent stages, olfactory interfaces show considerable promise for enriching the data journalism experience.</div></div>","PeriodicalId":55997,"journal":{"name":"Entertainment Computing","volume":"55 ","pages":"Article 100996"},"PeriodicalIF":2.8,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695286","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}