Game Difficulty Research Articles

Discussion on the Sense of Exploration in Games

Abstract: This paper explores human curiosity and desire to explore, particularly how these desires are stimulated in unknown environments. Electronic games, as a medium that is completely unknown before the experience and gives players freedom of movement, can particularly arouse players' curiosity. This article analyzes existing game design examples, studies how to meet players' exploration needs, and proposes several design ideas that help enhance the sense of exploration. Firstly, this article emphasizes that games should try to avoid excessive guidance and interference, reduce players' frustration in exploration, and ensure that the immersion of the game world is not disrupted. Secondly, the article proposes that maintaining challenge and appropriate difficulty in games can increase the excitement of exploration. At the same time, by setting diverse reward mechanisms and unexpected surprises, the fun of the exploration process can be further enhanced. This article summarizes these design strategies and provides specific guidance for exploratory games, aiming to help game designers better meet the needs of exploratory players and stimulate their desire to explore, enabling them to have a richer experience in the game.

Evolutionary game and LGPSO for attack-defense confrontation analysis in WSN from macro perspective

Wireless sensor network node security requires effective security mechanisms to protect the security and reliability, so as to ensure that sensor nodes can operate normally and provide reliable data in various environments. The security state change of wireless sensor network nodes is an important research content in the field of wireless sensor security. In this paper, an evolutionary game model is proposed to analyze the security state changes of sensor network nodes from a macro perspective. The existing methods define the parameters subjectively, which leads to the lack of rationality. In this paper, a Levy Flight Global Learning Particle Swarm Optimization (LGPSO) is proposed to calculate the Nash equilibrium of the game and quantify the parameters of the evolutionary game. The method proposed in this paper determines the parameters of the evolutionary game by solving the Nash equilibrium, which makes the model more realistic. The LGPSO has better optimization performance than other algorithms in solving Nash equilibrium problems. The CEC2013 dataset is used to test the performance of LGPSO. The experimental results show that LGPSO is superior to all other algorithms on 68% of the problems. This paper also discusses the influence of the game difficulty coefficient on the evolution process, and experiments show that a larger coefficient is more beneficial to the defender. The macro analysis in this paper provides the method of active defense for the attack-defense confrontation in wireless sensor networks.

Application and effectiveness of adaptive AI in elderly healthcare.

In addressing elderly healthcare issues, cognitive impairment can cause significant disruptions in daily life and may potentially develop into dementia. Thus, finding ways to delay the progression of cognitive impairment is a critical issue. This study aims to develop an adaptive artificial intelligence (AI) mechanism that creates enjoyable and beneficial content to help delay cognitive impairment in the elderly. Utilising virtual reality (VR) and a fishing game, the design enhances reaction time and attention through interactive fishing activities. The AI personalises content based on individual performance to improve cognitive function. Experimental results showed that adaptive AI increased participant satisfaction from 86.84 to 91.05 points and future willingness from 75.26 to 85.68 points. The number of fish caught rose from 98 to 120, with the average per participant increasing from 2.64 to 2.85. This is undoubtedly the trend of the future. VR allows the elderly to have a more impactful and memorable first experience, while AI dynamically adjusts the game's difficulty based on the elderly's performance, addressing the issue of reduced willingness to continue due to inappropriate game difficulty. The VR game developed in this study is designed to be relaxing and incorporates mechanisms to promote the elderly's health. It is not restricted by location or time and, more importantly, meets the health promotion needs of the elderly.

EXPRESS: The Effect of Game Ad Outcome on Subsequent Mobile Gaming Experience: the Mediating Role of Inferred Difficulty

This study investigates the effect of game advertisement outcomes on a player’s subsequent gaming experience. Research on vicarious experience shows that individuals infer game difficulty to be higher when watching game advertisements where players lose (vs. win) the game. Building on the effort–paradox paradigm, the first of this three-part study shows that such higher inferred difficulty enhances enjoyment and engagement during subsequent gaming experiences, especially for advertisements featuring easy game levels. Solely manipulating the difficulty level, Study 2 confirms the underlying mechanism of inferred difficulty for the observed effect of game advertisement outcomes. Study 3a finds that the main positive effect of losing (vs. winning) ads does not hold for advertisements featuring difficult game levels. Study 3b further explores this by focusing only on advertisements with difficult game levels, investigating how variations in players’ self-efficacy might influence their response to losing advertisements depicting difficult game levels. The findings across four studies suggest that, when promoting easy game levels, marketers can use advertisements with losing outcomes to extend gaming sessions, thereby increasing revenue from in-game advertisements. However, for difficult game levels, advertisements with losing outcomes are effective only for those with high self-efficacy.

Game Difficulty Prediction Based on Facial Cues and Game Performance

Current research on game difficulty prediction mainly uses heuristic functions or physiological signals. The former does not consider user data, while the latter easily causes interference to the user. This paper proposes a difficulty prediction method based on multiple facial cues and game performance. Specifically, we first utilize various computer vision methods to detect players’ facial expressions, gaze directions, and head poses. Then, we build a dataset by combining these three kinds of data and game performance as inputs, with the subjective difficulty ratings as labels. Finally, we compare the performance of several machine learning methods on this dataset using two classification tasks. The experimental results showed that the multilayer perceptron classifier (abbreviated as MLP) achieved the highest performance on these tasks, and its accuracy increased with the increase in input feature dimensions. These results demonstrate the effectiveness of our method. The proposed method could assist in improving game design and user experience.

A genetic algorithm-based method to modulate the difficulty of serious games along consecutive robot-assisted therapy sessions

Background and Objective:One of the biggest challenges during neurorehabilitation therapies is finding an appropriate level of therapy intensity for each patient to ensure the recovery of movement of the affected limbs while maintaining motivation. Different studies have proposed adapting the difficulty of exercises based on psychophysiological state, based on success rate, or by modeling the user’s skills. However, all studies propose solutions for a single session, requiring a calibration process before using it in each session. We propose a dynamic adaptation method that can be used during different rehabilitation sessions, without the need for recalibration between sessions. Methods:The adaptation architecture is based on a genetic algorithm that aims to maintain a certain score level and to motivate the user to move. The method has been evaluated with two serious games for five sessions using a rehabilitation robot. A common initial evaluation was made for all the users involved in the study, and the game parameters that best suited each user from the previous session were introduced as the starting point of the next session. In addition, the desired score rate was lowered between sessions to increase the difficulty level. The psychophysiological state of the users was measured based on the Self-Assessment Manikin test, as well as different cardiorespiratory and galvanic skin response signals were analyzed. Results:The adaptation architecture proposed can find those game parameters that maximize the user movement for both games. In one of the games, the score rate set for each session is followed with high fidelity. The degree of personalization in the games increases between sessions as the dispersion of the game parameters grows. The Self-Assessment Manikin test and the physiological signals results would indicate that the psychophysiological state remains equal between sessions despite an increase in game difficulty. Conclusions:The genetic algorithm-based game adaptation has proven efficacy in maximizing the therapy performance through the sessions without needing recalibration. It also can be concluded that the design of the game influences the adaptation performance. Additionally, adaptive game design facilitated by our method does not significantly impact players’ emotional or physiological states.

The influence of scaffolding on intrinsic motivation and autonomous adherence to a game-based, sparsely supervised home rehabilitation program for people with upper extremity hemiparesis due to stroke. A randomized controlled trial

BackgroundThis parallel, randomized controlled trial examined intrinsic motivation, adherence and motor function improvement demonstrated by two groups of subjects that performed a 12-week, home-based upper extremity rehabilitation program. Seventeen subjects played scaffolded games, presenting eight to twelve discrete levels of increasing difficulty. Sixteen subjects performed the same activities controlled by success algorithms that modify game difficulty incrementally.Methods33 persons 20–80 years of age, at least 6 months post stroke with moderate to mild hemiparesis were randomized using a random number generator into the two groups. They were tested using the Action Research Arm Test, Upper Extremity Fugl Meyer Assessment, Stroke Impact Scale and Intrinsic Motivation Inventory pre and post training. Adherence was measured using timestamps generated by the gaming system. Subjects had the Home Virtual Rehabilitation System (Qiu in J Neuroeng Rehabil 17: 1–10, 2020) placed in their homes and were taught to perform rehabilitation games using it. Subjects were instructed to train twenty minutes per day but were allowed to train as much as they chose. Subjects trained for 12 weeks without appointments and received intermittent support from study staff. Group outcomes were compared using ANOVA. Correlations between subject demographics and adherence, as well as motor outcome, were evaluated using Pearson Correlation Coefficients.ResultsThere were 5 dropouts and no adverse events. The main effect of time was statistically significant for four of the five clinical outcome measures. There were no significant training group by time interactions. Measures of adherence did not differ significantly between groups. The combined groups improved their UEFMA scores on average by 5.85 (95% CI 4.73–6.98). 21 subjects from both groups demonstrating improvements in UEFMA scores of at least 5 points, exceeding the minimal clinically important difference of 4.25. IMI scores were stable pre to post training.ConclusionsScaffolding challenges during game based rehabilitation did not elicit higher levels of adherence when compared to algorithm control of game difficulty. Both sparsely supervised programs of game-based treatment in the home were sufficient to elicit statistically significant, clinically meaningful improvements in motor function and activities of daily living.Trial registration: Clinical Trials.gov—NCT03985761, Registered June 14, 2019.

Predicting Online Gaming Behaviour Using Machine Learning Techniques

Understanding player behaviour in online gaming is essential for enhancing user engagement and retention. This study utilizes a dataset from Kaggle, capturing a wide range of player demographics and in-game metrics to predict player engagement levels categorized as 'High,' 'Medium,' or 'Low.' The dataset includes features such as age, gender, location, game genre, playtime, in-game purchases, game difficulty, session frequency, session duration, player level, and achievements. The research employs a Gaussian Naive Bayes model, with data pre-processing steps including feature selection, categorical data encoding, and scaling of numerical features. The dataset is split into training (80%) and testing (20%) sets, and a 5-fold cross-validation is used to ensure model robustness. The model's performance is evaluated using accuracy, precision, recall, and F1-score. The results show consistent performance across different folds, with an average accuracy of 84.27%, precision of 85.59%, recall of 84.27%, and F1-score of 83.98%. These findings indicate that the Gaussian Naive Bayes model can reliably predict player engagement levels, identifying significant predictors such as session frequency and in-game purchases. The study contributes to game analytics by providing a predictive model that can help game developers and marketers design more engaging gaming experiences. Future research should incorporate a broader range of features, including psychological and social factors, and explore other machine learning algorithms to enhance predictive accuracy. This study's insights are valuable for developing strategies to improve player retention and satisfaction in the gaming industry.

LapBot-Safe Chole: validation of an artificial intelligence-powered mobile game app to teach safe cholecystectomy.

Gaming can serve as an educational tool to allow trainees to practice surgical decision-making in a low-stakes environment. LapBot is a novel free interactive mobile game application that uses artificial intelligence (AI) to provide players with feedback on safe dissection during laparoscopic cholecystectomy (LC). This study aims to provide validity evidence for this mobile game. Trainees and surgeons participated by downloading and playing LapBot on their smartphone. Players were presented with intraoperative LC scenes and required to locate their preferred location of dissection of the hepatocystic triangle. They received immediate accuracy scores and personalized feedback using an AI algorithm ("GoNoGoNet") that identifies safe/dangerous zones of dissection. Player scores were assessed globally and across training experience using non-parametric ANOVA. Three-month questionnaires were administered to assess the educational value of LapBot. A total of 903 participants from 64 countries played LapBot. As game difficulty increased, average scores (p < 0.0001) and confidence levels (p < 0.0001) decreased significantly. Scores were significantly positively correlated with players' case volume (p = 0.0002) and training level (p = 0.0003). Most agreed that LapBot should be incorporated as an adjunct into training programs (64.1%), as it improved their ability to reflect critically on feedback they receive during LC (47.5%) or while watching others perform LC (57.5%). Serious games, such as LapBot, can be effective educational tools for deliberate practice and surgical coaching by promoting learner engagement and experiential learning. Our study demonstrates that players' scores were correlated to their level of expertise, and that after playing the game, most players perceived a significant educational value.

Adaptive mixed reality robotic games for personalized consumer robot entertainment

The Adaptive Mixed Reality Robot Games (AMRRG) framework represents an innovative approach to integrating consumer robots into public spaces for personalized and engaging entertainment. AMRRG uses a combination of mixed reality headsets, robot movement, and interactive objects. These responsive entertainment environments need a new way to tell their story. Admixing game mechanics algorithm utilizes the world’s most advanced depth perception, computer vision, and simultaneous mapping and localization (SLAM) to enable effective distinguishing between player spaces, mixed reality areas, and robot paths for safe interaction. Reinforcement learning enables real-time adaptation of game difficulty and gameplay mechanics as players react to it. At 35 % higher than traditional video-game installations in a 5 m × 5 m environment accommodating up to 20 people, adaptive algorithms recorded efficiency values of 92 % and responsiveness of 98 %. The AMRRG framework brings home consumer robot platforms to deliver a happy gaming experience. Future research will explore the potential of AMRRG beyond simple adaptation, extending its use to therapy and education.

The influence of scaffolding on intrinsic motivation and autonomous adherence to a game-based, unsupervised home rehabilitation program for people with upper extremity hemiparesis due to stroke. A randomized controlled trial.

This parallel, randomized controlled trial examines intrinsic motivation, adherence and motor function improvement demonstrated by two groups of subjects that performed a twelve-week, home-based upper extremity rehabilitation program. Seventeen subjects played games presenting eight to twelve discrete levels of increasing difficulty. Sixteen subjects performed the same activities controlled by success algorithms that modify game difficulty incrementally. 33 persons 20 to 80 years of age, at least six months post stroke with moderate to mild hemiparesis were randomized using a random number generator into the two groups. They were tested using the Action Research Arm Test, Upper Extremity Fugl Meyer Assessment, Stroke Impact Scale and Intrinsic Motivation Inventory pre and post training. Adherence was measured using timestamps generated by the system. Subjects had the Home Virtual Rehabilitation System [1]systems placed in their homes and were taught to perform rehabilitation games using it. Subjects were instructed to train twenty minutes per day but were allowed to train as much as they chose. Subjects trained for twelve weeks without appointments and received intermittent support from study staff. Group outcomes were compared using ANOVA. Correlations between subject demographics and adherence, as well as motor outcome, were evaluated using Pearson Correlation Coefficients. Classification and Regression Tree (CART) models were generated to predict responders using demographics and baseline measures. There were 5 dropouts and no adverse events. The main effect of time was statistically significant for four of the five clinical outcome measures. There were no significant training group by time interactions. Measures of adherence did not differ between groups. 21 subjects from both groups, demonstrated clinically important improvements in UEFMA score of at least 4.25 points. Subjects with pre training UEFMA scores below 53.5 averaged a seven-point UEFMA increase. IMI scores were stable pre to post training. Scaffolding did not have a meaningful impact on adherence or motor function improvement. A sparsely supervised program of game-based treatment in the home was sufficient to elicit meaningful improvements in motor function and activities of daily living. Common factors considered barriers to the utilization of telerehabilitation did not impact adherence or motor outcome. Clinical Trials.gov - NCT03985761, Registered June 14, 2019.

Metaverse gaming: analyzing the impact of self-expression, achievement, social interaction, violence, and difficulty

ABSTRACT In the burgeoning landscape of metaverse gaming, understanding player behaviour and preferences is crucial for both academic and practical applications. This study delves into the dynamic realm of metaverse gaming, exploring the influence of various factors on user satisfaction and continuance intention. The primary purpose was to examine the roles of self-expression, challenge and achievement, social interaction, violence catharsis, and game difficulty in shaping player experiences in the metaverse. Employing Partial Least Squares Structural Equation Modeling (PLS-SEM) as the analytical method, the study analysed responses from 171 metaverse game users. The findings revealed intriguing patterns: while self-expression significantly impacts continuance intention, it does not affect immediate satisfaction. Challenge and achievement enhance satisfaction but not continuance intention, emphasizing the complex relationship between these constructs. Social interaction emerged as a critical factor positively influencing both satisfaction and continuance intention. Contrary to popular belief, violence catharsis did not significantly affect either satisfaction or continuance intention. Additionally, increased game difficulty was found to negatively impact both satisfaction and continuance intention. Satisfaction was shown to drive continuance intention. These insights bear significant implications for game developers and marketers, highlighting the need for nuanced game design strategies that emphasize social interaction and balanced challenges.

Rethinking dynamic difficulty adjustment for video game design

Dynamic Difficulty Adjustment (DDA) has garnered significant interest in game research fields for many years. Despite high expectations, the effectiveness of DDA in enhancing player experiences has yielded mixed results. This paper aims to rethink the theoretical foundations of DDA by addressing four crucial questions about the issues, definition, scope, value, and design of DDA. A comprehensive literature review was conducted to provide novel insights into DDA and DDA design. We revealed DDA’s unhealthy reliance on Flow theory, redefined DDA based on the concept of game difficulty, and discussed DDA’s scope and value. Additionally, we presented a goal-based DDA design framework and proposed a 6-step DDA design process as a practical approach. This work offers theoretical support for understanding and designing DDA in future game research.

Emotion Evoking Game Design: Evaluating Induced Emotions Among Individuals with Healthy, Problematic, and Disordered Gaming

Background: Individuals diagnosed with gaming disorder (GD) often exhibit increased arousal during gameplay. Objectives: This study aims to compare arousal levels among individuals with GD, problematic gamers (PG), and those with healthy gaming habits (HG) using a 14-stage hyper-casual racing game. It further investigates how game difficulty affects emotional responses. Methods: We developed a detailed game and involved 146 participants to evaluate their feelings of dominance, arousal, and valence at each game stage, utilizing the Self-Assessment Manikin Test. Results: Problematic gamers and those with healthy gaming habits displayed similar emotional fluctuations throughout the game, whereas individuals with GD demonstrated a stable emotional pattern, regardless of game difficulty. An increase in game difficulty was associated with enhanced positive emotional experiences and a decrease in feelings of dominance. Stages 4, 12, and 13 of the game were identified as particularly emotionally engaging. Conclusions: Individuals with GD may possess a distinct emotional profile, providing valuable insights into the psychology of gaming and emotional well-being in today's digital era.

Breaking presence in Immersive Virtual Reality toward behavioral and emotional engagement

Background and objectiveMany recent studies in virtual reality (VR) have managed the sense of Presence to assess the suitability of their designs, mainly when focused on learning goals that require high user engagement, such as in serious games for psychomotor training. However, the place and plausibility illusions needed to promote Presence are achieved by combining different VR-based design cues, and their individual contribution to preserving the Presence's engagement/involvement component is still unclear. This article explored the single effect of breaking the sense of Presence per VR factor, i.e., removing VR cues related to Social Presence (human interactions), Self-Presence (embodiment), and Physical Presence (Scenario realism). MethodsThirty-three participants were asked to play an immersive VR simulation of an arcade game three times by experiencing a stepped Break of Illusion in one of the VR factors, i.e., while two factors were kept high, the remaining one was reduced to a low and null (hypothetical) level. The game difficulty was fixed after assessing each person's skills. ResultsResults showed that psychophysiology indicators (heart rate and skin conductance) were not affected by the level of illusion, whereas exercise intensity was significantly higher with low body and social presence-based conditions. Moreover, skin conductance was lower in the Social-presence group, which suggests that perspiration is only affected by breaks in realism (scenario and body representations). Based on the obtained evidence, we proposed some guidelines for adapting the design of immersive virtual environments through Breaks in Presence, mainly by changing the realism of the scenario and body representation depending on the skin conductance or the interaction with virtual humans depending on exercise intensity.

A methodology for using players’ chat content for dynamic difficulty adjustment in metaverse multiplayer games

Personalization of game difficulty is a critical task in leveraging artificial intelligence (AI) technologies to enhance player engagement in virtual worlds like metaverse. One of the key challenges in this area is developing methods for assessing a player’s perception of game difficulty. This information can be used to dynamically adjust the game difficulty to match the player’s skill level and preferences, which can improve the player’s experience and engagement. The existing approaches have limitations such as relying on costly external devices, requiring time-consuming feedback or questionnaires, and being specific to certain game genres and narratives. In this paper, we propose a new method called ChatDDA for evaluating a player’s perception of game difficulty by analyzing the content of their chat messages. Our method uses a pre-trained language model to extract semantic features from the chat messages, which are then used to train a feed-forward neural network to predict the player’s level of hopefulness or despair about succeeding in the game. Three pre-trained language models—BERT, RoBERTa, and Twitter-roBERTa—are fine-tuned on a purpose-built dataset of player chat messages of the popular multiplayer online game PlayerUnknown’s Battlegrounds (PUBG) tagged as expressing optimism or pessimism regarding game success. The results showed that our method can accurately predict a player’s perception of game difficulty, with an accuracy of 0.953 on the test dataset of player chat messages. This suggests that our method has the potential to enhance player engagement and immersion within the game, ultimately leading to more satisfying and enjoyable metaverse experiences.

Impact of Gamification Elements on Live Streaming E-Commerce (Live Commerce)

Live commerce is a new type of social commerce that involves live-streaming shopping (LSS). This method enables real-time and interactive communication between consumers. Nevertheless, research examining the effects of gamification in LSS, particularly in Indonesia, is scarce. Therefore, this study examines the relationships between gamification, consumer engagement, and purchase intention in the realm of live commerce. The empirical validation of the research model is achieved through the administration of an online survey in the form of a questionnaire to LSS viewers. This study demonstrates, via sampling-based analysis of 400 questionnaires, that gamification elements (including social and achievement-based components) can increase customers' engagement (consisting of a sense of presence and immersion), motivation (autonomy, competence, and relatedness), and purchase intent. Furthermore, the indirect effects of achievement and social status on purchase intention are significantly mediated by a sense of presence, whereas immersion does not serve as a mediator for these effects. By incorporating achievement and social elements into LSS programs, retailers and brands can increase consumers' sense of presence, immersion, and intent to purchase. More so than immersion, they should prioritize presence strategically to achieve their LSS objectives. The implications of this study focus on Indonesian users of e-commerce applications with live streaming capabilities. This research can be used to assess the perceived impact of gamification in the context of e-commerce live streaming and the significance of gamification to their overall experience. According to these findings, there is a difference that is statistically significant between autonomy and achievement. This difference has a significant impact on consumer behavior, driving engagement and purchase intention, with the original sample method demonstrating positive value. These findings suggest an adaptive difficulty, namely real-time analysis that adjusts the game's difficulty level to suit the player's skill level.

The impact of artificial intelligence on the Go level examination

This article explores the application of artificial intelligence (AI) technology in Go level examinations and its impact on Go education and evaluation systems. With the advancement of science and technology, especially the rapid development of AI technology, Go, as an ancient strategic game, has experienced revolutionary changes in its competitive scenes and learning methods. After AlphaGo defeated world Go champion Lee Sedol in 2016, the application of AI in the field of Go received widespread attention. AI has not only demonstrated capabilities beyond humans in high-level Go games, but has also played an increasingly important role in Go teaching and training. The global spread of the COVID-19 epidemic has forced Go level examinations to find new ways to adapt. The Go online intelligent test came into being, providing a new, efficient and objective assessment method. Although the introduction of online intelligent examinations has brought convenience, it has also raised issues in organizational structure adjustment, revenue distribution, and examination fairness. Challenges faced by the Go online intelligence examination in terms of fairness, including lack of face-to-face supervision, possible cheating, etc., pose new challenges to the fairness and authority of the Go level examination. This article compares the differences between intelligent Go exams and traditional exams, including assessment format, exam content and passing rate. The online intelligent examination has added test questions and raised the requirements for candidates’ computing power. It also shows a higher passing rate than traditional methods. However, the authenticity and fairness of online intelligent examinations have been challenged, including the adaptability of AI game difficulty and the lack of examination supervision, leading to the emergence of cheating. The positive impacts of implementing online smart exams include improving the convenience and efficiency of exams, simplifying event organization, and promoting the development of Go players’ skills. But at the same time, this new form has had an impact on the original Go organizational structure and benefit distribution, causing concerns and adjustments from local associations. In order to solve these problems, this article puts forward a series of suggestions, including setting up a supervision mechanism for intelligent examinations, optimizing the assessment system, and adjusting the revenue distribution ratio to ensure the long-term sustainable development of online intelligent examinations. In summary, the use of artificial intelligence in Go level examinations not only reflects the persistence of the interaction between technology and traditional cultural activities, but also poses ongoing challenges to the fairness and validity of education and assessment methods. By deeply understanding these impacts and taking corresponding countermeasures, we can find a balance between innovation and tradition, and provide support for the development of Go education and evaluation systems.

Frontal lobe epilepsy: an eye tracking study of memory and attention.

To explore the characteristics and mechanisms of working memory impairment in patients with frontal lobe epilepsy (FLE) through a memory game paradigm combined with eye tracking technology. We included 44 patients with FLE and 50 healthy controls (HC). All participants completed a series of neuropsychological scale assessments and a short-term memory game on an automated computer-based memory evaluation platform with an eye tracker. Memory scale scores of FLE patients including digit span (U = 747.50, p = 0.007), visual recognition (U = 766.50, p = 0.010), and logical memory (U = 544.00, p < 0.001) were significantly lower than HC. The patients with FLE took longer to complete the four levels of difficulty of the short-term memory game than healthy controls (level 1: U = 2974.50, p = 0.000; level 2: U = 3060.50, p = 0.000; level 3: U = 2465.00, p = 0.000; level 4: U = 2199.00, p = 0.000). During the memory decoding period, first fixation on the targets took significantly longer for FLE patients for all difficulty levels compared to controls (level 1: U = 3407.00, p = 0.008; level 2: U = 3618.00, p = 0.036; level 3: U = 3345.00, p = 0.006; level 4: U = 2781.00, p = 0.000). The average fixation duration per target among patients with FLE was found to be significantly longer compared to HC (level 1: U = 2994.50, p = 0.000; level 2: U = 3101.00, p = 0.000; level 3: U = 2559.50, p = 0.000; level 4: U = 2184.50, p = 0.000). The total fixation duration on AOI/total completion time of FLE patients was significantly lower than those of HC for levels 1 to 3 (level 1: U = 1557.00, p = 0.000; level 2: U = 2333.00, p = 0.000; level 3: U = 2757.00, p = 0.000). Furthermore, the eye tracking data during the memory decoding phase were correlated with neuropsychological scale scores (p < 0.05). Patients with FLE exhibited short-term memory impairment probably due to deficits in attentional maintenance, especially during the memory decoding phase. Eye tracking technology provided the possibility to help separate and quantify visual attention from memory processing, contributing to exploring underlying mechanisms of memory impairment in FLE.

A black-box model for predicting difficulty of word puzzle games: a case study of Wordle

A black-box model for predicting difficulty of word puzzle games: a case study of Wordle