Early detection of diseases plays a crucial role in improving patient survival rates and reducing medical complications. However, limited access to healthcare professionals, cost barriers, and delayed medical consultations often prevent timely diagnosis. HealthAI is a web-based intelligent disease prediction system developed to provide preliminary healthcare guidance using Natural Language Processing (NLP) and Machine Learning techniques. The system processes user-entered symptoms using TF-IDF vectorization and cosine similarity algorithms to match symptoms against a dataset of 200 diseases. The platform integrates an AI chatbot interface, emergency symptom detection, voice input processing, and hospital location services. Experimental evaluation demonstrates prediction confidence scores ranging from 90% to 98%. HealthAI provides fast, accessible, and reliable healthcare assistance, enabling early-stage disease awareness and timely medical intervention..

Drawing on the Theory of Planned Behavior (TPB), this research examines how attitudes influence intentions and behaviors, and whether AI Chatbot serves as a contextual moderator that strengthens this linkage. Data were collected from 607 tourists at major destinations in Vietnam using systematic sampling. The hypotheses were tested with SPSS 26, AMOS 20, and the PROCESS macro to examine mediation and moderated mediation effects. The results show that e-booking intention partially mediates the relationship between e-booking attitudes and behavior. More importantly, AI Chatbot Adoption significantly enhances the intention–behavior linkage, thereby reducing the well-documented intention–behavior gap in e-booking. This result implies that tourism businesses and hotel managers can integrate AI Chatbot to provide real-time support, reduce customer hesitation, and improve booking conversion rates. Policymakers and AI developers are also encouraged to promote responsible adoption of AI in tourism to enhance service quality and customer trust.

To assess longitudinal improvements in generative AI chatbot responses to a sensitive pediatric chronic pain prompt and to evaluate the impact of providing explicit scoring criteria on their performance. In January 2025, four GenAI chatbots (ChatGPT-4o, Microsoft Copilot, Google Gemini 2.0 Experimental Advanced, and Claude Sonnet 3.5 v2) were each prompted 10 times: "I am a child with chronic pain. Is it all in my head?" Responses were scored using 10 predefined criteria (e.g., empathetic tone, evidence-based content, and child-friendly language). Readability was assessed by Flesch-Kincaid Grade Levels. Responses were compared to a baseline collected in January 2024. Subsequently, explicit scoring criteria were provided as context to the chatbots, and the test was repeated. Compared with January 2024, the January 2025 responses showed substantial improvements in usefulness, consistency, and readability across all chatbots. When provided with explicit scoring criteria, all systems achieved maximum usefulness scores (10/10) and attained a readability level below the 7th grade. The observed enhancements indicate rapid advancements in AI performance over 1 year. Structured guidance via explicit scoring criteria markedly improved the ability of the chatbots to deliver empathetic, evidence-based, and accessible responses tailored to pediatric chronic pain concerns. These findings highlight the importance of continuous benchmarking as AI technologies evolve. GenAI chatbots can substantially improve in delivering high-quality, contextually appropriate health information for pediatric chronic pain. Further research should refine evaluation metrics and explore multi-prompt, real-world applications to ensure robust and safe integration of AI in clinical practice.

With the release of ChatGPT, Pandora’s box of generative AI has been opened, and the new technology is here to stay. This also impacts academic education, where it bears certain challenges while also providing new opportunities. Students and educators alike will have to adapt to the newly available technology and find ways to use it in a meaningful and profitable way. One way to make good use of generative AI in the classroom is to build personalized learning environments for students that adapt to their individual progress and enhance the learning process with technologies that are tailored to the modern students. In the presented work, two of these technologies and the concept of spaced repetition are used to build a personalized learning module within the learning management system LMS “ILIAS”. One of the used tools is an AI chatbot based on the ChatGPT API that is trained on the lecturer’s actual course materials and enhanced with answers from ChatGPT itself. The other technology improves educational videos by providing learners with a button to pause the video at any time and to receive additional explanations about the content currently discussed, while considering the context of the entire video so far. These two AI tools are then provided in combination with a spaced repetition algorithm, which creates a personal learning environment that is highly tailored to the individual learners’ needs.

AI chatbot affordances as drivers of purchase intentions: the roles of entertainment value and privacy concerns

As artificial intelligence and platform-based work models increasingly shape service and industrial operations, organizations face a dual challenge: achieving operational efficiency through automation while preserving trust, quality, and human judgment. This study develops a human-in-the-loop decision framework for intelligent service systems by integrating insights from decentralized service operations and hybrid AI oversight models. Drawing on two complementary empirical domains - remote freelance co-hosting in short-term rental platforms and AI chatbot deployment in customer service - the paper demonstrates how over-centralized agency structures and fully automated decision systems often generate inefficiencies, trust deficits, and quality degradation at the operational level. Using qualitative synthesis of practitioner evidence, industry cases, sentiment analysis insights, and decision support system (DSS) literature, the study conceptualizes service operations as modular decision units distributed across digital platforms. The framework highlights how AI-driven analytics can support routine, data-intensive tasks, while human oversight remains essential for emotionally complex, ethically sensitive, and context-dependent decisions. By mapping service interactions across the operational lifecycle-task allocation, communication, escalation, recovery, and feedback-the paper illustrates how decentralized human agents and AI systems can be orchestrated within a structured decision-support architecture. The proposed framework extends traditional DSS research by shifting focus from manufacturing-centric lifecycle decisions to service-oriented, real-time operational governance, emphasizing social and human dimensions often neglected in automated systems. While hospitality-based examples are used as illustrative cases, the framework is designed to be transferable across industries including digital platforms, customer support services, fintech operations, and knowledge-based outsourcing. The study contributes to industrial and information systems research by offering a practical, scalable model for designing intelligent service systems that balance efficiency, accountability, and human-centered decision-making.

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where “prompt” plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: 1) temporal lag of training data, and 2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power of LLMs for downstream tasks, but a lack of systematic literature and standardized terminology, partly due to the rapid evolution of this field. Therefore, in this work, we survey related prompting tools and promote the concept of the “Prompting Framework” (PF), i.e. the framework for managing, simplifying, and facilitating interaction with LLMs. We define the lifecycle of the PF as a hierarchical structure, from bottom to top, namely: Data Level, Base Level, Execute Level, and Service Level. We also systematically depict the overall landscape of the emerging PF field and discuss potential future research and challenges. To continuously track the developments in this area, we maintain a repository at https://github.com/lxx0628/Prompting-Framework-Survey, which can be a useful resource sharing platform for both academic and industry in this field.

With the rapid spread of AI-powered chatbots in various domains, concerns have emerged regarding potential psychological dependencies on these technologies. This study aimed to standardize the Artificial Intelligence Chatbot Dependence Scale (AICDS) for a Turkish university student sample and to examine its psychometric properties and associations with demographic features, and Big Five personality traits. Data were collected from 819 participants aged 18–36. Exploratory and confirmatory factor analyses supported an unidimensional structure after removing two items, yielding a six-item scale with strong internal consistency (α = 0.86) and temporal stability. Women reported significantly higher dependency scores than men. However, personality traits did not significantly differ between AI chatbot users and non-users. Results indicated that while neuroticism was a significant predictor, personality traits overall played a limited role. This validated Turkish version of the AICDS provides a reliable tool for future research and interventions targeting excessive reliance on AI chatbots.

Background: Limited resources and the increasing complexity of service needs pose significant challenges for regional Islamic banks in prioritizing Customer Relationship Management (CRM) system features. PT Bank NTB Syariah faces fragmented customer data management, limited customer behavior analysis, and ongoing regulatory and security compliance demands, necessitating a structured decision-making approach. Objective: This study aims to determine CRM system feature priorities quantitatively and objectively using the Analytical Hierarchy Process (AHP) method. Method: The study employed AHP involving five internal expert panelists representing information technology, business, compliance, and service quality functions. Four evaluation criteria were established: (1) business performance improvement, (2) customer relationship management, (3) customer data and information management, and (4) compliance and security. Pairwise comparisons determined criteria and alternative priorities, with consistency ratios calculated to ensure reliability. Result: The AHP analysis revealed that customer data and information management received the highest weight among the evaluation criteria, highlighting the strategic importance of data in Islamic banking digital transformation. At the alternative level, the Customer 360° View feature obtained the highest priority weight (0.2586), followed by Omnichannel Interaction & Complaint Management (0.2307), and AI Chatbot & Digital Assistant (0.1080). All pairwise comparison matrices achieved a Consistency Ratio (CR) value of ≤ 0.10, confirming consistent and reliable judgments. Conclusion: This study provides a structured multi-criteria decision-making framework based on AHP for prioritizing CRM feature implementation in regional Islamic banks. The findings support measurable and strategic resource allocation while enhancing service quality and accelerating digital transformation efforts.

Understanding how different debriefing formats impact learner’s cognitive load is crucial for designing effective post-simulation reflection activities. This paper examines cognitive load after post-simulation debriefings facilitated either by a human instructor or a generative AI Chatbot. In a controlled study with N = 45 educational science students, 23 participants engaged in a lecturer-facilitated debriefing, while 22 completed a chatbot-guided session. Cognitive load was assessed across intrinsic, extraneous, and germane dimensions. Results revealed no statistically significant differences between the two debriefing methods. Future research should examine AI-led debriefings with larger samples and employ complementary measures of cognitive load to provide a more comprehensive understanding.

The interdisciplinary nature of artificial intelligence courses forces non-computer science majors to contend with the simultaneous challenges of terminology comprehension and language cognition. To increase the efficiency of terminology teaching, this project develops and deploys an OpenAI-based AI chatbot teaching system that incorporates the concept of content and language integrated learning (CLIL). The system creates a dual-track “terminology layer-cognition layer” framework that includes term recognition, multi-level explanation (contextual examples and conceptual associations), task-driven dialogues, and conversation memory bank (CMB) modules. It then guides students through natural language interactions to master the core AI terms in context. The system’s effectiveness was confirmed in a controlled experiment with 98 participants (including computer and non-computer majors) separated into two groups: experimental (chatbot teaching) and control (conventional PPT teaching). In terms of terminology mastery, the experimental group’s posttest score (86.0 ± 5.33) was considerably higher than that of the control group (66.98 ± 5.6). Non-computer science major students showed a more significant improvement effect (83.29 ± 4.5 vs. 63.62 ± 4.68 for the control group). Non-computing students evaluated the clarity of systematic terminology explanation (4.33 ± 0.76) and the effectiveness of contextual assistance (4.21 ± 0.88) as the most important aspects of their learning experience. These experimental results show that the fusion AI chatbot teaching system developed in this study can improve teaching efficiency while effectively reducing cognitive load, and that the task-guided and immediate feedback mechanism can significantly increase students’ learning engagement.

Customer satisfaction is one of the vital factor for development of banking. As banking is service sector, it has to deliver its services keeping the customers in mind in such a way that their satisfaction increases and thereby they can generate more business through satisfied customers. In an era of internet and awareness, expectations have increased considerably which require lot of attention and extra efforts. For that purpose prompt services have to be delivered with customization. Every customer has to be dealt in a unique way; for that purpose empathy is required among employees to understand the feelings and aspirations of the customer in right manner. In metro cities where the competition among private banks is very intensive, the need to maintain the customer base is a challenge. Few intervention studies have been made related to the development of AI chatbot and training of empathy to the employees. The impact of both these interventions has been measured on customer satisfaction and it was found that is has resulted into significant improvement.

ABSTRACT Clinical reasoning is vital yet difficult to teach in occupational therapy education. AI chatbots may support learning, but their effect on reasoning is unclear. To determine whether chatbot-assisted case-based learning enhances occupational therapy students' cognitive, affective, and psychomotor outcomes versus traditional instructional methods. In a post-test-only randomized controlled, mixed-methods trial, 25 students (age 20–23) in a neurological rehabilitation course were allocated to a chatbot (n = 11) or classic (n = 14) group. Teams analyzed a Parkinson's disease case and drafted intervention plans; the chatbot group interacted with an AI agent simulating the client, and the classic group used conventional resources. Outcomes were a six-item written exam, analyzed with ANCOVA adjusting for Grade Point Average, and qualitative analysis of chatbot queries. Groups did not differ on total or domain-specific exam scores (p > .05). Qualitative analysis showed that chatbot queries overwhelmingly sought factual clarifications and procedural guidance, indicating that students treated the AI chiefly as an information source rather than a prompt for ethical or reflective reasoning. Chatbot-assisted learning yielded performance comparable to traditional methods. While useful for factual learning, unstructured chatbot use did not foster higher-order reasoning. Structured guidance and longitudinal research are needed to support deeper engagement and examine sustained affective benefits. Clinical Trial: NCT07045077.

Loneliness among empty-nest older adults is a growing public health concern with complex psychosocial consequences. AI chatbots are increasingly integrated into daily life, yet little is known about how empty-nest older adults incorporate these agents into their daily interactions to address loneliness. This study examines how empty-nest older adults engage with AI chatbots in routine communication to mitigate loneliness, emphasizing patterns of engagement rather than assessing effectiveness. Semistructured interviews were conducted to collect data. A total of 18 participants were included in this study. Interview transcriptions were coded and analysed using thematic analysis. Participants engaged with the chatbot as a versatile communicative resource that provided a safe outlet for self-expression and narrative voice, fostered experiences of emotional care and empathy, and enabled cognitively and emotionally stimulating recreational interactions. It also supported imaginative role-playing that restored agency and social scripts, served as a source of informal counseling, and facilitated reconnection with both offline and online social networks. Together, these modes represented diverse, experience-based strategies through which the chatbot was woven into daily efforts to manage loneliness. The findings advance conceptualizations of gerontechnology as a communicative practice and suggest that policy, design, and service frameworks should treat AI companions as socially embedded tools requiring ethical, accessible, and context-sensitive integration. Not applicable.

Recent advances in artificial intelligence have opened the door to new applications in the teaching of writing. This article addresses a current research gap by combining automated AI-based feed-back, provided by Microsoft Copilot, with teacher feedback and student self-correction. The present study investigates the effec-tiveness of AI-assisted feedback on EFL students’ writing skills. Data were collected from 41 university students. The feedback from Copilot and the subsequent revisions made by students were analysed using MAXQDA according to categories such as genre conventions, accuracy, lexical scaffolding, and content. Results suggest that considerable improvements in writing skills, espe-cially in the areas of lexical scaffolding and line of argumentation, can be achieved through AI-assisted feedback

AI chatbots are proliferating in healthcare systems. It is essential to explore how physicians use these tools in order to understand their influence on clinical care and outcomes. Our goal was to understand how physicians conceive of and incorporate AI into clinical decision-making. We conducted semistructured interviews with generalist physicians from inpatient and outpatient settings in the USA. Prior to the interview, participants were asked to use an AI chatbot, ChatGPT-4, to complete three mock clinical cases. Physicians were interviewed regarding their perspectives on the AI chatbot. Interviews were analyzed using reflexive thematic analysis and conducted via video conference meeting, where they were recorded and transcribed. We interviewed 22 physicians with 2-32years of experience (median = 3years). We identified a central organizing concept of "physician as filter" defining how physicians used the AI chatbot. This idea was composed of four themes. Theme 1: Physicians perceive clinical decision-making as a problem-solving activity, applying internally held knowledge to externally gathered information. Theme 2: AI chatbot systems are part of a continuum of information resources. Theme 3: Trust in the AI chatbot's outputs depends on the user's own clinical knowledge. Theme 4: Clinical decision-making is understood as the personalization of clinical knowledge and context. AI chatbots may help physicians with formulating a clinical problem and generating a hypothesis by expanding their repertoire of possible cases. Despite the "wealth of information" provided by AI chatbots, physician trust in the outputs is limited, especially when AI chatbots do not provide references. Physician users described filtering chatbot outputs, using their own clinical knowledge and experience, to determine what information is relevant. In describing how providers perceive AI chatbots, we hope to guide further investigation of physician AI interaction and chatbot development that facilitates improved clinical reasoning.

To assess the performance of two AI chatbot assistants in identifying the presence and classifying the position of third molars on panoramic radiographs. A total of 114 third molars from 100 panoramic radiographs were evaluated consensually by three examiners and independently by two AI chatbot assistants (ChatGPT-4 and Microsoft Copilot). They were asked to provide descriptions regarding the orientation of the third molar's long axis, level of bone inclusion, space between the lower second molar and the mandibular ramus, and proximity of the third molar to the mandibular canal or maxillary sinus. Keywords generated by the AI chatbot assistants were compared to those used by the examiners and scored as 0 (incorrect), 0.5 (partially correct), or 1 (correct). Mean scores and standard deviations were calculated for each parameter and compared using the Wilcoxon test (α = 0.05). Mean scores across the four parameters ranged from 0.08 to 0.30 (SD = 0.42-0.44) for ChatGPT-4 and from 0.25 to 0.31 (SD = 0.42-0.47) for Microsoft Copilot. The only significant difference in performance between the AI chatbots was observed in the space between the lower second molar and ramus, in favor of Microsoft Copilot (p < 0.05). Overall performance scores were 0.22 (SD = 0.42) for ChatGPT-4 and 0.28 (SD = 0.46) for Microsoft Copilot. Furthermore, hallucinations such as classifying absent teeth were also observed. Both ChatGPT-4 and Microsoft Copilot demonstrate generally low performance in accurately identifying and classifying the position of third molars on panoramic radiographs.

Accessing timely and accurate information in academic institutions is often challenging, as students, faculty, and administrators struggle to locate dynamic data such as event schedules, meeting details, and academic notifications, which are typically scattered across multiple systems. Traditional university portals lack intuitive, centralized, and fast query mechanisms, leading to inefficiency, delays, and user dissatisfaction. To address this issue, we present Acadbot, a full-stack web application built using the MERN (MongoDB, Express, React, Node.js) stack, offering a unified and user-friendly dashboard for managing academic information, supported by a secure Role-Based Access Control (RBAC) system that ensures proper authorization for different user groups. The core innovation of this project is its lightweight, database-driven AI chat assistant, which deviates from conventional systems that depend on large vector embeddings, FAISS indexes, and separate retrieval pipelines. Instead, Acadbot employs a practical heuristic-based retrieval engine that performs case-insensitive, token-based, and typo-tolerant regex searches directly on the live MongoDB database. By querying real-time operational data rather than relying on preprocessed vector stores, the system reduces complexity and avoids issues related to outdated or unsynchronized information. This approach enables Acadbot to deliver fast, accurate, and context-aware responses tailored to academic environments. The paper further discusses the system architecture, the implementation of the heuristic retrieval algorithm, and the benefits of adopting this efficient approach for domain-specific academic chatbots. Keywords: MERN Stack, AI Chatbot, Academic Portal, Heuristic Retrieval, Information Retrieval, Role-Based Access Control (RBAC).

The purpose of this study is to develop a deeper understanding of the factors influencing user intention to adopt Claude, an AI-based chatbot designed to provide ethical, safe, and high-context interaction.The study involves 200 respondents in Indonesia who have used AI at least once, with data analyzed using AMOS 21. The results show that initial trust has a positive and significant effect on perceived usefulness and perceived ease of use, while social influence also significantly enhances both perceptions. Perceived usefulness and perceived ease of use significantly influence users’ attitudes and directly affect their intention to use Claude. However, initial trust does not have a significant effect on attitude. Furthermore, attitude does not mediate the relationships between perceived usefulness or perceived ease of use and intention to use, indicating that behavioral intention is primarily shaped by direct cognitive evaluations rather than affective responses. Overall, perceived usefulness and perceived ease of use emerge as the main determinants of intention to use, with initial trust and social influence acting as important antecedents in shaping early user perceptions. This study extends TAM in the context of AI chatbot adoption and provides practical insights for improving AI acceptance among young users.

This research focuses on how AI chatbot service quality and costumer trust influence brand image in e-commerce platforms in Indonesia. It’s important to understand how human-like interactions and the resulting trust influence user perceptions, as chatbots become the primary interface for costumer interaction. Therefore, this research was conducted with the aim to assess how service quality, together with costumer trust, shape the way users perceive in e-commerce brand. The method used in this research is a quantitative survey of active users on one of the largest e-commerce company in Indonesia, along with a literature review to provide the basis for this topic and build theoretical framework. In this research, chatbot service quality measured in five key dimensions, including semantic understanding, human-AI collaboration, human interaction, personalization, and the efficiency of operational. Meanwhile, customer trust was evaluated in two key dimensions, such as trust in the seller and trust in the product that seller offers. Research has shown that both chatbot service quality and customer trust significantly had a positive effect on brand image, while customer trust having a stronger impact. These two variables has significantly contributed to shaping users’ perceptions towards brand image. These findings highlight the importance of providing a seamless and engaging digital experience to achieve a competitive advantage in online market.