User Feedback Research Articles

AI-Enabled Optimization of University of Cebu Computer Laboratories: A Sit-in Reservation and Monitoring System for Enhanced Resource Management

In an era where technological advancements are reshaping various sectors, including education, Artificial Intelligence (AI) offers significant potential to enhance resource management in academic institutions. This study focuses on optimizing the computer laboratory sit-in reservation and monitoring process at the University of Cebu - Main Campus, College of Computer Studies. The current manual system presents inefficiencies, such as difficulty in scheduling, suboptimal utilization of resources, and lack of real-time monitoring. To address these challenges, this research proposes the development of an AI-enabled Sit-in Reservation and Monitoring System designed to streamline reservation processes, optimize resource allocation, and provide real-time visibility into laboratory usage. The system aims to achieve four key objectives: creating a user-friendly reservation interface, developing an AI-based algorithm to optimize computer resource allocation, implementing a real-time monitoring dashboard, and evaluating the system’s effectiveness based on user feedback and performance metrics. This AI-driven solution is expected to enhance the student experience by improving accessibility and reducing wait times, while also enabling better resource management through data-driven decision-making. By maximizing the utilization of available resources, the system offers cost savings and operational efficiency improvements for the college. The study's scope is limited to the College of Computer Studies’ computer laboratory and focuses on optimizing the sit-in reservation and monitoring processes.

Temporal dual-target cross-domain recommendation framework for next basket recommendation

Next Basket Recommender systems in e-commerce face challenges such as data sparsity, evolving user preferences, and cross-domain transfer limitations. We propose the Temporal Dual-Target Cross-Domain Recommendation Framework (T-DualCRF) to address these issues. T-DualCRF integrates multi-channel embeddings (user feedback, knowledge graphs, temporal features) and a dual-target mechanism for robust cross-domain knowledge transfer. It also employs time-aware embeddings and a temporal heterogeneous graph to model user preference changes. The framework’s hybrid optimization mechanism, combining the Multi-Verse Optimizer and Whale Optimization Algorithm, enhances recommendation accuracy and stability. Experimental results on Amazon datasets show that T-DualCRF significantly outperforms existing models, with improvements of up to 20% in F1-score and 17% in NDCG, effectively mitigating data sparsity and adapting to real-time user behavior changes.

Development and Evaluation of Pakistan Explorer: A Recommender Web Platform for Navigating Pakistani Culture

The study seeks to bridge the gap in existing cultural exploration resources by offering a personalized, technology-driven understanding of Pakistan’s diverse cultural heritage, which answers the significant void in tailored cultural exploration, particularly for Pakistani heritage. This project not only showcases the rich traditions, cuisine, and arts of Pakistan but also addresses the lack of tailored cultural information available for this region. The platform's advanced recommendation algorithms promote personalized user experiences, thus fostering cross-cultural understanding and appreciation. The backbone of this platform is a hybrid- recommendation system which combines both content-based filtering with collaborative-filtering through the innovative use of the 'Surprise' library's Singular Value Decomposition (SVD) algorithm, a method not typically applied in cultural context platforms. Additionally, the system integrates real-time data processing for dynamic content updates, including weather and local events, which are crucial for real-time travel and cultural recommendations. The platform has demonstrated a capability to offer personalized and dynamic cultural insights, substantially improving user engagement and satisfaction. The application of the SVD algorithm in a new domain—cultural recommendations—is a novel adaptation, showing promising results in enhancing the relevancy of content delivered to users. For future scalability, transitioning from embedded data within the Flask app to a more robust database system, such as SQL or NoSQL, is recommended. This would facilitate easier data management and richer feature implementation. The research could also benefit from focusing on integrating more AI-driven capabilities, such as natural language processing (NLP) to parse and categorize user reviews and feedback, which could further refine and personalize recommendations. The innovative use of SVD in cultural context platforms presents a new avenue for academic exploration and can be expanded to other cultural recommendation systems.

Community case study: Our Wave, an online platform to facilitate survivor disclosure of sexual assault and trauma recovery

This community case study introduces Our Wave, an online platform that provides a safe, anonymous space for survivors of sexual harm to share their stories, reflect on their healing journeys, and connect with others. Designed to empower survivors, the platform allows users to post anonymous stories or visual media, ask questions, and send messages of hope, all while prioritizing privacy and security. It also aims to create a broader impact by analyzing shared narratives to detect patterns, identify best practices for healing, and inform global approaches to SV recovery. With over 100,000 members and over 1,200 stories and forms of media shared, the platform has become a valuable resource for survivors. Using mixed-methods analysis of platform usage data and anonymous user feedback surveys (n = 288), we examined patterns of engagement and impact. Analysis revealed that 57% of story submissions included “Messages of Healing” and 52% included “Messages of Hope,” with survey responses indicating that anonymity and peer support were crucial factors in facilitating disclosure. Research shows that the social and emotional dynamics of SV disclosure, as well as the responses from others, play a crucial role in a survivor’s healing. By focusing on confidentiality, trauma-informed support, and community-building, Our Wave offers a safe space for survivors to heal, connect, and access resources to support their journey toward recovery.

Medical education videos – comparative analysis of sonography vs. clinical examination videos: user perception and educational value

BackgroundVideo content has become an increasingly valuable tool in medical education, particularly for teaching hands-on skills like sonography and clinical examination. This study evaluates the satisfaction and content of sonography and clinical examination videos on the AMBOSS platform, a prominent medical education resource in Germany.ObjectiveThe goal of this study was to compare how effective and well-received sonography and clinical examination videos are on the AMBOSS platform. The study looked at aspects such as the medical and technical quality of the videos, their usefulness for learning, and overall user satisfaction.MethodsEighteen instructional videos were chosen and made accessible on the AMBOSS platform, grouped into sonography (n = 9) and clinical examination (n = 9) categories. Users were asked to voluntarily and anonymously fill out a questionnaire evaluating the videos. Over 49.5 months, data from 1,643,274 video views and 936 completed questionnaires were gathered.ResultsClinical examination videos were watched significantly more often than sonography videos (86 vs. 14%). Both video types were highly rated in terms of medical and technical quality. However, sonography videos were judged superior in technical quality and clarity, whereas clinical examination videos were preferred for their medical quality and practical application. Feedback from users indicated a desire for more detailed annotations and clearer explanations.ConclusionThe findings underline the crucial role of video resources in medical education, particularly in teaching practical skills. To improve educational outcomes, it is important to tailor content to the specific needs of medical students and professionals, incorporate user feedback, and take advantage of technological advancements.

Investigating the Impact of AI-Driven Voice Assistants on User Productivity and Satisfaction in Smart Homes

Artificial Intelligence (AI)-driven voice assistants, such as Amazon's Alexa and Google Assistant, have become essential components in modern smart home ecosystems, revolutionizing the way users interact with their environments. These voice assistants enable hands-free control over various home automation systems, offering unprecedented levels of convenience and enhancing daily productivity. By integrating with a wide range of smart devices—from lighting and temperature control to security systems and entertainment—AI-driven voice assistants simplify the management of daily routines, allowing users to perform tasks more efficiently with minimal effort. This study aims to explore the influence of AI-driven voice assistants on user productivity and overall satisfaction within smart homes. Employing both quantitative data collection methods, such as usage statistics and automation completion rates, alongside qualitative insights gathered from user feedback, we conduct a comprehensive analysis of how voice-controlled smart home interactions affect daily activities. The research examines aspects such as task completion speed, automation accuracy, and the seamlessness of multi-device integrations, in addition to the subjective user experience, including perceived ease of use, convenience, and general satisfaction with the system. Our findings suggest that AI-driven voice assistants offer considerable improvements in user productivity, reducing the time and effort required to complete tasks by streamlining processes and enabling multi-tasking. Additionally, users reported higher satisfaction levels due to the simplicity and efficiency introduced by these technologies. However, the study also highlights ongoing challenges, particularly regarding the assistants' limited ability to understand complex contextual information and the growing concerns over privacy and data security. Despite these issues, the positive impact of AI-driven voice assistants on smart home ecosystems is clear, with potential for further enhancements as the technology evolves.

One Step at a Time: Incremental Approaches to HIV Prevention

HIV prevention remains a global priority, with diverse strategies continuously developed to address the needs of high-risk populations. Incremental approaches—emphasizing gradual, step-by-step advancements—are gaining traction as an effective method to tailor interventions, increase accessibility, and foster long-term engagement. These strategies build on existing resources, adjust to unique local contexts, and prioritize community involvement, making them especially impactful in resource-limited or culturally diverse settings. By setting measurable, short-term goals, incremental approaches offer a sustainable pathway for reducing HIV transmission rates. One significant example of incremental HIV prevention is the phased implementation of Pre-Exposure Prophylaxis (PrEP), which has shown remarkable results when introduced progressively to high-risk groups. Alongside PrEP, behavioral interventions such as safe-sex education and harm reduction for injecting drug users are adapted incrementally to shift cultural norms and reduce stigma. Biomedical innovations, like microbicides, are similarly introduced in stages, with user feedback and adherence monitored to enhance real-world effectiveness. By allowing for community-specific refinements, these interventions become more accepted and impactful. Keywords: HIV Prevention, Incremental Strategies, PrEP, Behavioral Interventions, Community Education

Review Analyzer

This project focuses on leveraging generative AI to analyse user reviews from the Play Store for diverse applications. By utilizing advanced large language models (LLMs), the system processes extensive user feedback to identify key trends, sentiments, and actionable insights. The AI analyses reviews to categorize overall user sentiment (positive, negative, or neutral), highlight recurring issues, and identify popular feature requests. The generative AI’s capabilities enable it to provide nuanced suggestions to developers, such as improving app functionality, addressing common complaints, and implementing features aligned with user preferences. Additionally, the system can generate concise summaries of user reactions, offering developers a clear understanding of their app's strengths and areas needing improvement. This data-driven approach enhances app development by prioritizing updates based on real user needs, improving user satisfaction, and fostering higher ratings on the Play Store. The integration of generative AI streamlines the review analysis process, ensuring actionable recommendations for sustained app success. Key Words: Generative AI, Large Language Models (LLMs), sentiment analysis, App improvement, review analysis 1.INTRODUCTION This project utilizes generative AI to analyze Play Store reviews across various applications, providing developers with actionable insights. By leveraging large language models (LLMs), the system processes user feedback to identify sentiment trends, highlight common issues, and suggest improvements. This approach enables developers to understand user reactions effectively and prioritize updates, ultimately enhancing app quality, user satisfaction, and ratings. The integration of AI streamlines review analysis, ensuring data-driven decisions for better app performance.

Enhancing digital currency adoption: examining user experiences

PurposeThis study aimed to analyse user experiences and perceptions of eRupee banking applications in India, focussing on understanding the key factors driving user satisfaction and dissatisfaction.Design/methodology/approachA comprehensive text-mining approach was employed to analyse 5,176 user reviews collected from the Google Play Store. Sentiment analysis and latent Dirichlet allocation (LDA) were used to classify reviews and uncover prevailing themes.FindingsThe analysis revealed that positive reviews highlighted the themes of usefulness, convenience, satisfaction, app attributes, and ease of use. Negative reviews emphasise issues related to lack of trust, faulty updates, unreliability, security concerns, and inadequate customer support. The Logistic Regression model demonstrated superior performance in predicting user sentiments, achieving an AUC of 0.7926 and an accuracy rate of 77.90%.Research limitations/implicationsThis study was limited to reviews from a single-platform source. Future research could incorporate data from multiple online sources and employ qualitative methods to gain deeper insight. Additionally, longitudinal studies and cross-cultural analyses are recommended to capture evolving user sentiments and global perspectives.Practical implicationsThe findings provide actionable insights for bank managers, app developers and policymakers to enhance eRupee applications by addressing identified issues and leveraging positive aspects to improve overall user experience and satisfaction.Originality/valueThis study makes a novel contribution to the literature on digital currency and advanced text-mining techniques using machine-learning models to analyse user feedback in the context of an emerging economy. The proposed conceptual model and practical recommendations serve as the foundation for future research and practical development in digital financial services.

Comparative Analysis of Generative AI Tools in Making Marketing Copywriting in the Era of New Media

In the background of the development of new media, generative Artificial Intelligence (AI) tools have become powerful assets to create marketing copywriting, which provides efficiency and innovation ability for the generation of content. This study analyzes the performance of 4 types of AI tools ChatGPT4o, Image-TO-Prompt-AI(Poe), Tiangong3.0 and Doubao when producing and promoting copywriting. The study discussed the performance of these AI to generate the text which can cause emotional resonance, capture key marketing elements and show special language style. By applying the BROKE instruction framework, this study ensures that the evaluation method of AI-generated content is consistent and structured. Research results reveal significant differences in content quality through user feedback and questionnaire collection, among them, ChatGPT4o is leading in overall attractiveness and TianGong3.0 has an outstanding performance on the unique perspective and logical structure. This study not only provides insights into the current capabilities of AI in content creation, but also lays the foundation for the future development of AI and artificial collaboration in the new media field.

Trends in Smart Restaurant Research: Bibliometric Review and Research Agenda

Background The automation of processes and services has transformed various industries, including the restaurant sector. Technologies such as the Internet of Things (IoT), machine learning, Radio Frequency Identification (RFID), and big data have been increasingly adopted to enhance service delivery, improve user experiences, and enable data traceability. By collecting user feedback and analyzing sentiments, these technologies facilitate decision-making and offer predictive insights into future food preferences. This study aims to explore current research trends in intelligent restaurants, focusing on technological applications that improve service and decision-making. Methods A bibliometric analysis was conducted in accordance with the PRISMA-2020 guidelines. A total of 94 academic documents were reviewed from the Scopus and Web of Science databases, focusing on publications related to intelligent restaurant systems, particularly involving IoT and automation technologies. Results The analysis revealed that the United States, India, and China have contributed the most to the field, with a particular emphasis on China’s implementation of IoT architecture and robotics in restaurant settings. Chinese restaurant innovations, particularly in robotics, are among the most frequently cited in the literature. The study identifies these countries as leading the research in the intelligent restaurant domain. Conclusions Technologies such as IoT, machine learning, RFID, and big data are driving advancements in restaurant automation, enhancing service efficiency and user experience. The United States, India, and China are leading research in this area, with China standing out for its application of robotics and IoT in restaurants. This research provides a foundation for future studies aimed at improving predictive models for food selection and service optimization.

The Application of Augmented Reality in Simulation-Based Design Evaluations of Trauma Rooms.

This study examined the augmented reality (AR) application in design evaluations through an immersive experience of medical task simulations in combination with a full-scale physical mock-up of a trauma room. Augmented reality technology is emerging in various fields including architectural design. Traditionally, building physical mock-ups has been the most effective tool to involve end-users in design evaluations. However, AR can eliminate cost- and labor-intensive components of a physical mock-up by replacing them with holograms. Two simulation sessions with emergency department clinicians were conducted using AR. The research team collected user feedback through simulations and interviews. Clinicians' feedback was systematically categorized and summarized according to various design elements. The integration of mock-up and AR simulations enabled the evaluation of design elements that were previously unattainable. Examples include simulating color-coded floor boundaries and adjusting door widths, which enhanced clinicians' immersion and involvement in design changes. Interviews and analyses of video recordings captured from the clinicians' perspectives supported the design evaluations during simulations. Augmented reality has great potential to be used widely in the evaluation of healthcare environment design. Augmented reality is an innovative approach that can benefit end-users in interacting with a mix of real spaces and virtual components. It also introduces new ways of data collection and analysis to architectural design evaluation methods.

Enhancing POI recommendations on social media: a sequential approach incorporating LSTM and user feedback

Enhancing POI recommendations on social media: a sequential approach incorporating LSTM and user feedback

Adaptive Learning in AI Agents for the Metaverse: The ALMAA Framework

This study investigates the adaptability of Artificial Intelligence (AI) agents in the Metaverse, focusing on their ability to enhance responsiveness, decision-making, and engagement through the proposed Adaptive Learning Model for AI Agents (ALMAA) framework. The research does not introduce new interventions to existing platforms like Epic Games or AltspaceVR but instead analyzes how their operations align with adaptive learning principles. By examining these platforms, the study demonstrates the alignment between real-world practices and theoretical constructs, offering insights into how adaptive AI systems operate in dynamic virtual environments. Case observations highlight key metrics such as user interaction efficiency, contextual decision accuracy, and predictive engagement strategies. The data, derived from detailed user interaction logs and feedback reports, underscore the practical application of adaptive learning in optimizing user satisfaction and system performance. Statistical analyses reveal notable gains in response speed, predictive precision, and user engagement, validating the theoretical framework’s relevance. This paper positions the ALMAA framework as a critical lens for understanding and analyzing adaptive AI in virtual settings. It emphasizes theoretical exploration rather than experimental application, providing a foundation for future research into scalable, user-centered AI systems tailored for the Metaverse’s evolving demands.

The Implementation of AWS Cloud Technology to Enhance the Performance and Security of the Pharmacy Cashier Management System

This study examines the implementation of Amazon Web Services (AWS) in the MEKATEK pharmacy cashier management system to address the limitations of traditional systems, such as slow transaction processing, data loss risks, and challenges in handling transaction surges. The prototyping method was employed, involving user requirements analysis through interviews and observations, followed by iterative development of core features like inventory management, transactions, reporting, and data backups. Black box testing demonstrated a 100% success rate for core functionalities. Performance analysis recorded stable CPU utilisation below 5% under normal workloads and the ability to handle throughput up to 2532 packets/minute. System optimisation reduced AWS operational costs to IDR 150,000–160,000 per month. AWS implementation improved operational efficiency, strengthened data security through encryption and role-based access control, and minimised human errors. Initial user feedback indicated faster workflows, although adjustments are needed for users with limited technical backgrounds. This study recommends further development, including AI-based analytics and digital payment integration, to enhance MEKATEK’s functionality and competitiveness in the future.

The Employee Performance Management of the Regional Technical Implementation Unit (UPTD) of the Animal Health and Veterinary Public Health Center of Seruyan Regency in Improving Public Services.

This research aims to analyze the quality of animal health service management at the Regional Technical Implementation Unit (UPTD) Animal Health Center of Seruyan Regency using the POAC (Planning, Organizing, Actuating, Controlling) management approach. Conducted from June 1 to September 1, 2024, this study employs a qualitative method with descriptive analysis. Data were collected through literature reviews, direct observations, and interviews with staff and management involved in the service delivery process. The findings reveal that the service planning at the UPTD Animal Health Center and Veterinary Public Health has not effectively engaged farmers, which has resulted in a disconnect between the programs offered and the actual needs of the farming community. Although the internal organization of the center is assessed as practical, the accessibility of services for farmers residing in remote areas remains a significant concern that requires attention. The execution of veterinary health services showcases the competence and skills of health workers. However, there are notable deficiencies in communication and the availability of information that hinder effective service delivery. Furthermore, the existing control system does not adequately accommodate user feedback, highlighting an urgent need for enhanced communication channels. Overall, this research aims to provide actionable recommendations to improve the quality of veterinary health services in Seruyan Regency, ultimately fostering a more responsive and user-centered service environment. The insights gained from this study will contribute to the ongoing efforts to align veterinary health services with the community's needs, ensuring better health outcomes for livestock and the farming population.

Optimizing Personalized and Context-Aware Recommendations in Pervasive Computing Environments

The researchers in the current era provided many new recommendation methodologies. Though various recommendation techniques exist, there is a need to develop a unique technique for capturing latent factors and patterns from sparse and high-dimensional data in pervasive environments, specifically for optimizing dynamic recommendations. This study proposes a hybrid approach for optimizing dynamic recommendations in pervasive environments by combining Non-Negative Matrix Factorization (NMF) with deep learning and reinforcement learning techniques. The goal is to overcome the challenge of capturing latent factors and patterns from sparse and high-dimensional data. By leveraging NMF, meaningful latent factors are extracted, while deep learning, specifically Faster recurrent neural networks (FRNNs), learns complex feature representations. Reinforcement learning algorithms optimize the recommendation policy based on user feedback. This Hybrid Context-Aware Optimized Recommendation (HCOR) approach improves recommendation accuracy and relevance in pervasive environments, adapts to changing contexts, and enhances user experiences. The performance benefits are achieved by effectively capturing latent factors and patterns, resulting in improved accuracy and the ability to provide personalized and context-aware recommendations. The performance indicators to validate the research work include the recommendations' accuracy, relevance, and adaptability in pervasive environments. Additionally, metrics, such as precision, recall, and F1-score, are used to evaluate the effectiveness of the hybrid approach in capturing latent factors and patterns. User feedback and satisfaction are also measured to assess the impact on user experiences. The HCOR approach shows substantial performance gains, measuring a precision of 0.932, a recall of 0.922, and an F1-score of 0.943, which indicates the excellent ability of the approach to deliver accurate and personalized recommendations in a pervasive environment.

USER ACCEPTANCE OF MOBILE-JKN: INSIGHTS FROM THE TECHNOLOGY ACCEPTANCE MODEL

Background: Technological advancements in healthcare have driven BPJS Kesehatan Indonesia to develop the Mobile JKN application to enhance accessibility, efficiency, and quality of services. Despite its potential benefits, the implementation of this application faces various challenges, such as application errors, differing levels of digital literacy, and data security issues, necessitating an evaluation of its adoption and acceptance. Aims: To analyse the public acceptance of Mobile JKN based on the Technology Acceptance Model (TAM) variable while also exploring user experiences towards the application. Methods: A descriptive-analytical approach with a cross-sectional design. Data were collected through a questionnaire developed based on the TAM model, involving 406 respondents across Indonesia. Data analysis was performed using a regression linear test with SPSS after all basic assumptions were met. Results: Perceived Ease of Use, Perceived Usefulness, and Attitude Toward Use individually and simultaneously impact Actual System Use (Sig. 0.000; R-Square 0.827). Respondents generally answered “Agree” to all TAM indicators, with mean scores of 4.20 for Perceived Usefulness, 4.16 for Perceived Ease of Use, 4.25 for Attitude Toward Use, and 4.33 for Actual System Use. Most users accessed the app through self-access (48%), frequently used features were membership information (28%), and encountered issues such as application errors (25%). Conclusion: The app was deemed relevant, accurate, easy to use, and beneficial. To enhance public acceptance, BPJS Kesehatan should focus on developing a user-friendly Mobile JKN app by incorporating key TAM factors, optimizing popular features, improving technical stability, and regularly addressing user feedback to ensure effective health administration and service delivery. Keywords: Adoption, Application, BPJS Kesehatan, Mobile JKN, TAM

Mitigative Strategies for Recovering From Large Language Model Trust Violations

In this study, we investigated strategies to address trust issues arising from errors in large language models (LLMs). The study examined the impact of confidence scores, system capability explanations, and user feedback on trust restoration post-error. 68 participants viewed the responses of an LLM to 20 general trivia questions, with an error introduced on the third trial. Each participant was presented with one mitigation strategy. Participants rated their overall trust in the model and the reliability of the answer. Results showed an immediate drop in trust after the error; however, there were no differences across the three strategies in trust recovery. All conditions had a logarithmic trend in trust recovery following error. Differences in overall trust were predicted by perceived reliability of the answer, suggesting that participants were evaluating results critically and using that to inform their trust in the model. Qualitative data supported this finding; participants expressed lasting distrust despite the LLM’s later accuracy. Results showcase the need to prioritize accuracy in LLM deployment, because early errors may irrevocably damage user trust calibration and later adoption.

Accelerating Precision: Using AI to Fine-Tune Workout Form and Motion Speed

This is an extension of the paper that we published earlier on AI for workout Form Optimization. In the earlier paper, we presented a software solution for workout form optimization using joint angles. Just like the effectiveness of the workout is in the precision of the body form, it also gets hugely impacted by the workout speed, i.e., muscle contraction and relaxation speed. This paper covers a software solution that can be used to give users feedback on their workout speed for specific workout exercises. It uses computer vision and artificial intelligence libraries. The sample implementation is provided on GitHub GitHub - pythonioncoder/Fit-Form-AI. Keywords— Pose Detection AI Libraries, Media pipe, AI Programming, Computer Vision, Artificial Intelligence, Fit Form AI