Chatbot Research Articles

ChatGPT: Technology Frontiers and Cybersecurity Challenges

This paper examines the evolution and application of OpenAI's advanced conversational AI, ChatGPT, particularly within the domain of cybersecurity. With an architecture built on the Transformer model, ChatGPT demonstrates significant capabilities in language understanding and generation. It leverages vast datasets, ranging from social media posts to technical documents, ensuring the model adapts to diverse fields and maintains compliance with privacy and security regulations. The paper explores ChatGPT's role in network security, highlighting its proficiency in threat detection, vulnerability assessment, and incident response, essential as regulations like GDPR and CCPA become more stringent. Furthermore, the study addresses potential security risks associated with AI, such as phishing and misinformation, and discusses mitigation strategies through advanced training techniques like adversarial training and multi-task learning. A novel variational autoencoder (VAE)-based method, T-VAE, is introduced, offering enhanced generalization capabilities across different tasks and scenarios. The findings suggest that while ChatGPT has made significant strides in cybersecurity applications, continuous improvements in model robustness and adaptability are necessary to mitigate emerging threats and adapt to evolving digital landscapes.

Consumer Propensity to Use Ai Chatbot in Purchase Decision Making from The Perspective of Valence Framework: The Role of Openness to Change and Compatibility

This research investigates consumers' inclination to utilize AI Chatbots for purchase decisions, employing the valence framework and examining the roles of Openness to Change and Compatibility. The study surveyed 320 chatbot users in the Sumbawa District. Findings reveal that Openness to Change significantly influences chatbot users' purchasing decisions within the valence framework context, encompassing both Perceived Benefit and Perceived Risk. This highlights the crucial role of Openness to Change in understanding consumer behavior, as it can substantially impact decisions regarding chatbot usage when considering perceived benefits and risks. The research also confirms the positive effects of chatbot utilization. By incorporating Openness to Change and Compatibility, the study offers a novel perspective on chatbot usage in purchasing decisions. This approach distinguishes the research, as it applies the valence framework (Perceived Benefit and Perceived Risk) to chatbot usage while introducing the additional dimensions of Openness to Change and Compatibility.

AI chatbots in programming education: guiding success or encouraging plagiarism

This study examines the impact of an AI programming assistant on students' exam scores and their tendency to accept incorrect AI-generated information. The customized AI programming assistant was developed by the authors using GPT based Large Language Model (LLM). A one group pretest–posttest quasi-experimental design was utilized to answer research questions. Students were asked to take identical programming exams twice: once without AI assistance and once with the option to use the AI assistant. Results showed that the students’ average exam scores significantly increased from 48.33 to 74.47 with a large effect size (d = 1.56) when they used the AI assistance. On the other hand, when student—AI interaction logs were analyzed for a specific question, it was found that AI generated incorrect answers to 36 students. Thirty-three of these students (92%) answered the question incorrectly. Even more interestingly, despite the AI-generated response containing an obvious error, 22 of them (61%) copied and pasted the AI's response directly into the answer field. Only 3 students (8%) ignored the incorrect response generated by the AI and answered the question correctly. A significant portion of students accepting incorrect information provided by AI underscores the need for careful integration of AI tools into learning environments. Moreover, our findings emphasize the importance of specially developed AI tools rather than free tools like ChatGPT in exploring the new type of interaction between students and AI.

Human vs. AI counseling: College students' perspectives

Transitioning to college life while navigating the complexities of emerging adulthood can be stressful. In some instances, it may even lead to the onset of mental health problems or the exacerbation of existing issues. While therapeutic resources are typically available in tertiary educational contexts, social stigma may lead to service underutilization. Additionally, high student-to-therapist ratios can create bottlenecks to access when such services are sought. Offering an adjunct to traditional campus counseling services, AI chatbots can potentially address such issues. Chatbots can provide flexible, accessible, anonymous, and cost-effective first-line support, improving access and extending traditional treatment methodologies. This study evaluates college students' perceptions (N = 224) of an AI chatbot (Pi) designed to emulate supportive and empathetic interactions characterized by active listening. Participants blindly assessed transcripts from active listening interactions between a client and Pi versus interactions between a client and a human counselor/therapist. The results indicate that participants could not distinguish between the human-human and human-AI counseling transcripts, answering correctly only 47.5% of the time. Moreover, participants gave higher quality ratings to the human-AI counseling transcripts than the human-human ones. These findings provide tentative support for the user-acceptability of relational AI chatbots during the counseling process's early phases (active listening and problem exploration).

Exploring EFL Students' Creativity and Engagement with AI Chatbot in Web-Based English Course

This research explores the role of AI-based chatbot tools in promoting creativity and engagement among English as a Foreign Language (EFL) students in web-based English material development course. A qualitative research design was employed, involving in-depth interviews and observation checklists. The research was conducted at the English Education Faculty in Parangtambung of Universitas Negeri Makassar, with data collection spanning from May 12, 2024, to June 9, 2024. Participants included five undergraduate students from the 6th semester based on their familiarity with AI chatbots. The subjects of this research were undergraduate students enrolled in the English web-based material development course. Specifically, five students with prior experience or familiarity with AI chatbots were chosen to provide detailed insights through interviews and observations. The findings indicate that AI chatbots significantly encourage creativity among EFL students by providing a safe space for language experimentation and immediate feedback. Students reported increased engagement and enjoyment in their learning process. The research concludes that while AI chatbots can effectively foster creativity and engagement, careful integration and continuous monitoring are necessary to maximize their educational benefits.

The Effect of AI Chatbots on Consumer Engagement and Satisfaction

The Effect of AI Chatbots on Consumer Engagement and Satisfaction

Exploring the Effect of Attachment on Technology Addiction to Generative AI Chatbots: A Structural Equation Modeling Analysis

With the advancement of artificial intelligence technology, generative AI chatbots (GAIC) such as ChatGPT, are integrating into various aspects of society and quietly changing people’s lives. However, although there is a plethora of research concerning social media usage and addiction, discussions about chatbots remain far from adequate. Investigating the use and potential technology addiction to generative AI chatbots (TAGAIC) holds both theoretical and practical significance. Drawing on attachment theory, this study aims to investigate the formative factors in TAGAIC. A structural equation model was used to analyze the data collected from a questionnaire survey of 364 GAIC users. Results reveal that technology addiction is positively influenced by emotional attachment but not by functional attachment. Besides, perceived anthropomorphism and perceived empathy have a positive effect on emotional attachment, while system quality and information quality have a positive effect on functional attachment. Limitations of the study were discussed.

Assessing AI chatbots efficacy in ophthalmic triage and referrals: A comparative study

To evaluate the efficacy of AI chatbots (OpenAI ChatGPT GPT-3.5, Google Bard, and WebMD) compared to human ophthalmology trainees in triage and referrals for common ophthalmic conditions. A single-center study was conducted at MKCG Medical College, Berhampur, Odisha, involving six ophthalmology trainees. The performance of AI chatbots was assessed based on diagnostic accuracy and triage categorization. Key performance indicators included the accuracy of the top three suggested diagnoses and concordance in recommendations for investigations and referrals. Physician respondents identified the correct diagnosis among the top three suggestions in 95% of cases. Google Bard achieved 90% accuracy, ChatGPT 85%, and WebMD 20%. High concordance was observed between physician and AI recommendations for investigations and referrals. AI chatbots demonstrate promising potential in supporting triage and referral decisions for ophthalmic conditions. While human expertise remains crucial, AI tools can augment diagnostic accuracy, improve efficiency, and enhance patient care. Future research should focus on refining AI algorithms, integrating clinical data, and exploring real-world implementation strategies.

Understanding anthropomorphic voice-AI chatbot continuance from a human-AI interaction perspective

ABSTRACT Although anthropomorphic AI technologies nowadays are significantly changing the human-AI interaction, the mechanism of how voice-AI chatbots’ anthropomorphism affects users’ continuance behaviour is unclear. To explore the role of human-AI interaction and privacy concerns in the continuance intention of anthropomorphic voice-AI chatbots, a research model, based on parasocial relationship theory, is developed. The research model was then empirically tested against a cross-sectional survey from 473 voice-AI chatbot users and two-wave longitudinal data collected from 271 voice-AI chatbot users. The Structural Equation Modelling (SEM) results indicate that voice-AI chatbots’ anthropomorphism affects continuance intention via both human-AI interaction fluency and human-AI rapport building. In particular, the impact of voice-AI chatbots’ anthropomorphism on voice-AI chatbots’ continuance intention is fully mediated by human-AI interaction fluency and human-AI rapport building. Moreover, the influence of human-AI interaction fluency on voice-AI chatbots’ continuance intention will decrease and the impact of human-AI rapport building on voice-AI chatbots’ continuance intention will increase when users’ privacy concerns are high. The findings provide new insights into AI chatbot research from a human-AI interaction perspective. Developers of voice AI chatbots could focus on anthropomorphism, interaction and user information collection strategies to increase user continuance intention.

Commanding and Requesting: Teachers’ Speech Acts in Indonesian Vocational English Schools

Effective communication in the classroom profoundly influences educational performance, particularly in language acquisition settings. This study investigates the employment of directive (commanding) and requestive (requesting) speech acts by English educators in Indonesian vocational high schools, a subject that remains under-examined. This research utilizes a qualitative case study design to examine the utilization of speech actions by teachers and their perceptions by students. Data were gathered by classroom observations, audio recordings, and semi-structured interviews with five English educators and five students from a vocational institution in Samarinda, Indonesia. The results indicate that directed speech acts are predominantly employed to uphold discipline and deliver explicit instructions, hence enhancing classroom management and concentration. In contrast, requestive speech acts foster a polite environment that promotes active student engagement and collaboration. Furthermore, educators deliberately integrate the Indonesian language to augment students' understanding and involvement. The study highlights the necessity of a judicious application of both commanding and requesting speech acts to facilitate effective teaching practices that integrate authority with mutual respect. These discoveries have considerable significance for teacher training programs, indicating that professional development should prioritize the incorporation of communication tactics that adjust to classroom dynamics and promote a good learning atmosphere. Utilizing multilingual methodologies and contextually relevant communication can enhance teacher-student interactions, hence improving student engagement and educational results.

Abstract 4120680: Language AI Chat BOTs as Pioneers in Cardiovascular Diagnosis? A Retrospective Analysis on Real-Time Patients in a Tertiary Care Centre

GPT-3 and GPT-4, show promise in assisting healthcare professionals with clinical questions. Their performance in real-time clinical scenarios, particularly with cardiovascular symptoms, remains underexplored. This study aims to evaluate their precision and reliability compared to physicians. Hypothesis: We hypothesize that board-certified emergency department attendings at Maimonides Medical Center exhibit higher accuracy and reliability than GPT-3.5 and GPT-4 in generating differential diagnoses based on history and physical examination for patients presenting to the emergency department. Methods: Patient data from Maimonides Medical Center's emergency department, collected from January 1, 2023, to April 30, 2023, was analyzed. Demographics, symptoms, medical history, and discharge diagnoses recorded by emergency room attendings were examined. ChatGPT-3.5 and GPT-4 generated differential diagnoses, which were compared with those by attending physicians. Accuracy was determined by comparing each rater's diagnoses with discharge diagnosis, calculating the proportion of correctly identified cases. Precision was assessed using Cohen's kappa coefficient and Intraclass Correlation Coefficient to measure agreement between raters. Results: Patient demographics showed mean age of 49.12 years, with 57.3% males and 42.7% females. Chief complaints included fever/sepsis (24.7%), gastrointestinal issues (17.7%), and cardiovascular problems (16.4%). Diagnostic accuracy against discharge diagnoses was highest for Chat GPT-4 (85.5%), followed by Chat GPT-3.5 (84.6%) and ED attendings (83%). Cohen’s kappa demonstrated moderate agreement (0.7) between AI models, with lower agreement observed for ED attendings. Stratified analysis revealed higher accuracy for gastrointestinal complaints with Chat GPT-4 (87.5%) and cardiovascular complaints with Chat GPT-3.5 (81.34%). Conclusion: Our study demonstrates that Chat GPT-4 and GPT-3.5 exhibit comparable diagnostic accuracy to attendings, highlighting their potential to aid decision-making in dynamic clinical settings. The stratified analysis revealed comparable reliability and precision of the AI chat bots for cardiovascular complaints which represents a significant proportion of the high risk patients presenting to the emergency department. This study contributes to integrating AI models into medical practice, enhancing efficiency and effectiveness in clinical decision-making

Enhancing Spanish Patient Education Materials: Comparing the Readability of Artificial Intelligence-Generated Spanish Patient Education Materials to the Society of Pediatric Dermatology Spanish Patient Brochures.

Patient education materials (PEMs) are crucial for improving patient adherence and outcomes; however, they may not beaccessibledue to high reading levels. Our study used seven readability measures to compare the readability of SpanishPEMsfromthe Society of Pediatric Dermatology (SPD) with those generated by Open-AI's ChatGPT 4.0 and Google Gemini. Our results showed that when prompted to produce material at a 6th grade level, both AI ChatBots generated significantly improved readability scores when compared to the SPD handouts. These findings suggest that AI-generated PEMs couldbetter meet readability standards and potentially improve patient outcomes, although further studies are needed to confirm this.

فاعلية توظيف العلاقات العامة لربورتات الدردشة في التعريف بالخدمات في المؤسسات الحكومية

The study aimed to describe the effectiveness of employing public relations for chat bots in defining services in government institutions, by knowing the manifestations of public relations practitioners' interest in knowing information about chat bots and employing them in defining services in government institutions, services and areas of use, as well as the benefits achieved and the obstacles they face in this field, reaching their suggestions and their evaluation of the impact of these applications on their professional competence, and the future of public relations in light of chat bots. The study used the descriptive approach, and among the tools, the interview was used, and a questionnaire on the reality of public relations practitioners' use of chat bots in defining services in government institutions. The study sample consisted of (240) employees in the Corporate Communications and Public Relations Department in government institutions. As for the results of the study, it showed great interest from public relations practitioners in government institutions in chat bots and their use in managing corporate communication, as their aspects of use varied between crisis management and meeting the needs of the public. These technologies have contributed to improving the professional efficiency of most of the respondents by enhancing daily performance, speed of accomplishment, planning and decision-making. However, users faced challenges such as the difficulty of robots understanding customer feelings and fear of losing jobs. They suggested linking promotion to their ability to use them and provide training and technical support. Despite the benefits of robots, there are still concerns about the future of the public relations profession in light of this technology.

Beyond Automation: A Rigorous Testing Framework for Reliable AI Chatbots in Life Insurance

AI-driven chatbots are transforming customer service in Life Insurance, offering policyholders instant support, streamlined inquiries, and personalized recommendations. However, deploying these chatbots effectively requires addressing unique challenges, including interpreting complex insurance terminology, ensuring regulatory compliance, and maintaining data security and user privacy. This research introduces a detailed testing framework specifically tailored to Life Insurance chatbots, covering functional, non-functional, AI-specific, and compliance testing to guarantee accuracy, reliability, and adherence to legal standards. The framework emphasizes essential practices for verifying natural language understanding, sensitive data handling, and empathetic responses for users navigating critical life events. This research highlights the critical role of targeted testing to deliver robust, user-centered chatbot solutions in the Life Insurance sector.

A fine-tuning enhanced RAG system with quantized influence measure as AI judge

This study presents an innovative enhancement to retrieval-augmented generation (RAG) systems by seamlessly integrating fine-tuned large language models (LLMs) with vector databases. This integration capitalizes on the combined strengths of structured data retrieval and the nuanced comprehension provided by advanced LLMs. Central to our approach are the LoRA and QLoRA methodologies, which stand at the forefront of model refinement through parameter-efficient fine-tuning and memory optimization. A novel feature of our research is the incorporation of user feedback directly into the training process, ensuring the model’s continuous adaptation to user expectations and thus, improving its performance and applicability. Additionally, we introduce a Quantized Influence Measure (QIM) as an innovative “AI Judge” mechanism to enhance the precision of result selection, further refining the system’s accuracy. Accompanied by an executive diagram and a detailed algorithm for fine-tuning QLoRA, our work provides a comprehensive framework for implementing these advancements within chatbot technologies. This research contributes significant insights into LLM optimization for specific uses and heralds new directions for further development in retrieval-augmented models. Through extensive experimentation and analysis, our findings lay a robust foundation for future advancements in chatbot technology and retrieval systems, marking a significant step forward in the creation of more sophisticated, precise, and user-centric conversational AI systems. We make the dataset, the data processing package huggify-data, the model, and the app publicly available for the community.

OpenAI ChatGPT vs Google Gemini: A study of AI chatbots’ writing quality evaluation and plagiarism checking

This study explores the writing quality of two AI chatbots, OpenAI ChatGPT and Google Gemini. The research assesses the quality of the generated texts based on five essay models using the T.E.R.A. software, focusing on ease of understanding, readability, and reading levels using the Flesch-Kincaid formula. Thirty essays were generated, 15 from each chatbot, and evaluated for plagiarism using two free detection tools—SmallSEOTools and Check-Plagiarism—as well as one paid tool, Turnitin. The findings revealed that both ChatGPT and Gemini performed well in terms of word concreteness but demonstrated weaknesses in narrativity. ChatGPT showed stronger performance in referential and deep cohesion, while Gemini excelled in narrativity, syntactic simplicity and word concreteness. However, a significant concern was the degree of plagiarism detected in texts from both AI tools, with ChatGPT's essays exhibiting a higher likelihood of plagiarism compared to Gemini’s. These findings highlight the potential limitations and risks associated with using AI-generated writing.

Response to comment on: can AI Chatbots accurately answer patient questions regarding vasectomies?

Response to comment on: can AI Chatbots accurately answer patient questions regarding vasectomies?

Next-Gen Patient Support: AI Chatbots in Healthcare

Next-Gen Patient Support: AI Chatbots in Healthcare

Utilising Artificial Intelligence (AI) in Vocabulary Learning by EFL Omani Students: The Effect of Age, Gender, and Level of Study

AI tools have enabled FLLs to navigate their journeys of learning languages. This poses several questions, particularly about the most common AI tools used in learning vocabulary and the attitudes of EFL Omani students toward using AI tools in learning English. A mixed-method research design was utilised, and the sampling included 236 respondents studying in the Sultanate of Oman. An SPSS version 29 was employed in analysing the quantitative data, whereas the qualitative data were analysed thematically. The qualitative data revealed that EFL Omani students depended heavily on Google Translation (44%) as the highest AI tool, followed by the Dictionary Application (32%), ChatGPT (22%), Chat Bot (17.40%), and Duolingo (15.70%). In addition, translating the meaning of a new word occupied the highest learning strategy (frequency: 141), followed by learning new vocabulary (frequency: 134), translating the meaning of a full sentence (frequency: 91), and learning the correct pronunciation of strange words (frequency: 90), whereas learning grammar, enhancing writing and reading skills had the lowest frequency. The quantitative data showed that the overall mean is (3.67), which reveals a high frequency of use of AI tools in learning vocabulary. The lowest mean (3.45) is associated with trusting the new vocabulary recommended by AI tools, whereas the positive effectiveness of AI tools has the highest mean (3.92). However, it was found that age, gender, and level of study do not affect EFL Omani students’ use of AI tools to learn vocabulary.

AI Chatbots: Fast Tracking Sustainability Report Analysis for Enhanced Decision Making

AI Chatbots: Fast Tracking Sustainability Report Analysis for Enhanced Decision Making