AI Chatbot Research Articles

Efficacy and Safety of Combination Therapy With Vaginal and Urethral Erbium-Doped Yttrium-Aluminum-Garnet (Er:YAG) Laser for Overactive Bladder With Urinary Incontinence.

This retrospective cohort study with propensity score (PS) matching aimed to evaluate the efficacy and safety of a combination therapy with vaginal and urethral erbium:yttrium aluminum garnet laser (VEL+UEL) (SP Dynamis; Fotona d.o.o., Ljubljana, Slovenia) in the treatment of overactive bladder with urinary incontinence (OAB-wet). The study included female OAB-wet patients aged 65 and above who were already taking OAB medication. Data obtained from electronic medical records were subjected to propensity score matching. All patients received instructions on pelvic floor exercises and were prescribed an appropriate dose of OAB medication. The VEL+UEL group (n=30) underwent three monthly laser sessions, while the control group (n=30) did not receive the treatment. Clinical outcomes were evaluated using the Overactive Bladder Symptom Score (OABSS), International Consultation on Incontinence Questionnaire-Short Form (ICIQ-SF), three-day urination diary, and Vaginal Health Index Score (VHIS). Medication usage and adverse events were also assessed. Statistical analysis and R code were performed using the AI chatbot GPT-4.0. The VEL+UEL group showed significant improvements in OABSS score, ICIQ-SF score, voided volume, daytime frequency, nocturia, and VHIS after 12 months of treatment (p<0.001). Notably, 13.3% of patients transitioned from OAB-wet to OAB-dry. In contrast, the control group did not exhibit significant changes. Medication use was significantly reduced in the VEL+UEL group compared to the control group (p<0.001). No long-term side effects were reported. Combination therapy with VEL+UEL demonstrated efficacy and safety in the treatment of OAB-wet. Improvements in OAB symptoms, voided volume, frequency, nocturia, and vaginal health were observed, with a subset of patients transitioning to OAB-dry. VEL+UEL therapy offers a potential treatment option for OAB-wet, reducing medication use and improving patient outcomes. Further research is warranted to investigate the mechanism, long-term effects, safety, and cost-effectiveness of VEL+UEL therapy.

Cheating in the age of generative AI: A high school survey study of cheating behaviors before and after the release of ChatGPT

The public release of ChatGPT and other generative AI chatbot technologies has been accompanied by questions about how academic integrity and student cheating behaviors will be impacted. We analyzed anonymous survey data from three high schools to see if self-reported cheating numbers changed following the introduction of ChatGPT and similar technologies. This survey data set is unique in that data on cheating had been collected with this set of schools both before and after November 2022, when ChatGPT was publicly released and drew attention to these educational concerns. The results suggested that cheating behaviors remained relatively stable after the introduction of this current generation of generative AI chatbot technology. However, some changes in reported behaviors differed depending on the type of cheating (social cheating, AI-related cheating, etc.). Additional survey questions about high school students’ AI chatbot usage and the perceived allowability of such technology revealed mixed opinions on the acceptability of using AI for various academic-related tasks. Most students did not think that using a chatbot to produce an entire paper or complete an entire assignment should be allowable. However, there was support for using AI chatbots to help students to start on assignments and papers and to help explain new concepts to them.

In-depth analysis of ChatGPT’s performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions

ChatGPT has garnered attention as a multifaceted AI chatbot with potential applications in medicine. Despite intriguing preliminary findings in areas such as clinical management and patient education, there remains a substantial knowledge gap in comprehensively understanding the chances and limitations of ChatGPT’s capabilities, especially in medical test-taking and education. A total of n = 2,729 USMLE Step 1 practice questions were extracted from the Amboss question bank. After excluding 352 image-based questions, a total of 2,377 text-based questions were further categorized and entered manually into ChatGPT, and its responses were recorded. ChatGPT’s overall performance was analyzed based on question difficulty, category, and content with regards to specific signal words and phrases. ChatGPT achieved an overall accuracy rate of 55.8% in a total number of n = 2,377 USMLE Step 1 preparation questions obtained from the Amboss online question bank. It demonstrated a significant inverse correlation between question difficulty and performance with rs = -0.306; p < 0.001, maintaining comparable accuracy to the human user peer group across different levels of question difficulty. Notably, ChatGPT outperformed in serology-related questions (61.1% vs. 53.8%; p = 0.005) but struggled with ECG-related content (42.9% vs. 55.6%; p = 0.021). ChatGPT achieved statistically significant worse performances in pathophysiology-related question stems. (Signal phrase = “what is the most likely/probable cause”). ChatGPT performed consistent across various question categories and difficulty levels. These findings emphasize the need for further investigations to explore the potential and limitations of ChatGPT in medical examination and education.

SUCCESS TRACK: Website for New Students with Personalized Skill Development

The research is designed to help new students entering campus by offering them skill development opportunities right from the start of their academic journey. The research provides a platform where students can choose a specific skill domain to improve upon. It also offers a personalized learning paths for them, packed with various resources. Additionally, a continuous assessment through tests, AI chat bot support, personalized student logins, and faculty admin access for efficient management is also offered. The goal of the research is to support students in enhancing their skills and succeeding academically.

Can Artificial Intelligence "Hold" a Dermoscope?-The Evaluation of an Artificial Intelligence Chatbot to Translate the Dermoscopic Language.

This survey represents the first endeavor to assess the clarity of the dermoscopic language by a chatbot, unveiling insights into the interplay between dermatologists and AI systems within the complexity of the dermoscopic language. Given the complex, descriptive, and metaphorical aspects of the dermoscopic language, subjective interpretations often emerge. The survey evaluated the completeness and diagnostic efficacy of chatbot-generated reports, focusing on their role in facilitating accurate diagnoses and educational opportunities for novice dermatologists. A total of 30 participants were presented with hypothetical dermoscopic descriptions of skin lesions, including dermoscopic descriptions of skin cancers such as BCC, SCC, and melanoma, skin cancer mimickers such as actinic and seborrheic keratosis, dermatofibroma, and atypical nevus, and inflammatory dermatosis such as psoriasis and alopecia areata. Each description was accompanied by specific clinical information, and the participants were tasked with assessing the differential diagnosis list generated by the AI chatbot in its initial response. In each scenario, the chatbot generated an extensive list of potential differential diagnoses, exhibiting lower performance in cases of SCC and inflammatory dermatoses, albeit without statistical significance, suggesting that the participants were equally satisfied with the responses provided. Scores decreased notably when practical descriptions of dermoscopic signs were provided. Answers to BCC scenario scores in the diagnosis category (2.9 ± 0.4) were higher than those with SCC (2.6 ± 0.66, p = 0.005) and inflammatory dermatoses (2.6 ± 0.67, p = 0). Similarly, in the teaching tool usefulness category, BCC-based chatbot differential diagnosis received higher scores (2.9 ± 0.4) compared to SCC (2.6 ± 0.67, p = 0.001) and inflammatory dermatoses (2.4 ± 0.81, p = 0). The abovementioned results underscore dermatologists' familiarity with BCC dermoscopic images while highlighting the challenges associated with interpreting rigorous dermoscopic images. Moreover, by incorporating patient characteristics such as age, phototype, or immune state, the differential diagnosis list in each case was customized to include lesion types appropriate for each category, illustrating the AI's flexibility in evaluating diagnoses and highlighting its value as a resource for dermatologists.

Reliability and readability analysis of ChatGPT-4 and Google Bard as a patient information source for the most commonly applied radionuclide treatments in cancer patients

PurposeSearching for online health information is a popular approach employed by patients to enhance their knowledge for their diseases. Recently developed AI chatbots are probably the easiest way in this regard. The purpose of the study is to analyze the reliability and readability of AI chatbot responses in terms of the most commonly applied radionuclide treatments in cancer patients. MethodsBasic patient questions, thirty about RAI, PRRT and TARE treatments and twenty-nine about PSMA-TRT, were asked one by one to GPT-4 and Bard on January 2024. The reliability and readability of the responses were assessed by using DISCERN scale, Flesch Reading Ease(FRE) and Flesch-Kincaid Reading Grade Level(FKRGL). ResultsThe mean (SD) FKRGL scores for the responses of GPT-4 and Google Bard about RAI, PSMA-TRT, PRRT and TARE treatmens were 14.57 (1.19), 14.65 (1.38), 14.25 (1.10), 14.38 (1.2) and 11.49 (1.59), 12.42 (1.71), 11.35 (1.80), 13.01 (1.97), respectively. In terms of readability the FRKGL scores of the responses of GPT-4 and Google Bard about RAI, PSMA-TRT, PRRT and TARE treatments were above the general public reading grade level. The mean (SD) DISCERN scores assesses by nuclear medicine phsician for the responses of GPT-4 and Bard about RAI, PSMA-TRT, PRRT and TARE treatments were 47.86 (5.09), 48.48 (4.22), 46.76 (4.09), 48.33 (5.15) and 51.50 (5.64), 53.44 (5.42), 53 (6.36), 49.43 (5.32), respectively. Based on mean DISCERN scores, the reliability of the responses of GPT-4 and Google Bard about RAI, PSMA-TRT, PRRT, and TARE treatments ranged from fair to good. The inter-rater reliability correlation coefficient of DISCERN scores assessed by GPT-4, Bard and nuclear medicine physician for the responses of GPT-4 about RAI, PSMA-TRT, PRRT and TARE treatments were 0.512(95% CI 0.296: 0.704), 0.695(95% CI 0.518: 0.829), 0.687(95% CI 0.511: 0.823) and 0.649 (95% CI 0.462: 0.798), respectively (p < 0.01). The inter-rater reliability correlation coefficient of DISCERN scores assessed by GPT-4, Bard and nuclear medicine physician for the responses of Bard about RAI, PSMA-TRT, PRRT and TARE treatments were 0.753(95% CI 0.602: 0.863), 0.812(95% CI 0.686: 0.899), 0.804(95% CI 0.677: 0.894) and 0.671 (95% CI 0.489: 0.812), respectively (p < 0.01). The inter-rater reliability for the responses of Bard and GPT-4 about RAİ, PSMA-TRT, PRRT and TARE treatments were moderate to good. Further, consulting to the nuclear medicine physician was rarely emphasized both in GPT-4 and Google Bard and references were included in some responses of Google Bard, but there were no references in GPT-4. ConclusionAlthough the information provided by AI chatbots may be acceptable in medical terms, it can not be easy to read for the general public, which may prevent it from being understandable. Effective prompts using 'prompt engineering' may refine the responses in a more comprehensible manner. Since radionuclide treatments are specific to nuclear medicine expertise, nuclear medicine physician need to be stated as a consultant in responses in order to guide patients and caregivers to obtain accurate medical advice. Referencing is significant in terms of confidence and satisfaction of patients and caregivers seeking information.

HealthSquare: A Survey of Deep Learning Based Healthcare Platform

The multi-health diagnosis web application HealthSquare represents a pioneering endeavor in healthcare technology by integrating advanced AI models for comprehensive health analysis. The system comprises multiple components, including two image processing models for fracture detection from X-ray reports and brain tumor identification from MRI scans. Additionally, GCP’s Vertex AI is leveraged for blood &amp; thyroid report analysis to predict &amp; provide descriptive diagnosis. Moreover, the platform enables users to create accounts for secure storage of medical reports, akin to a specialized digital locker tailored specifically for healthcare documents. Furthermore, an AI-driven chat bot offers real-time health- related guidance and recommendations to users based on their queries. The integration of these components aims to redefine healthcare diagnostics by providing users with accessible, accurate, and personalized health analysis tools. Utilizing advanced image processing techniques, AI-driven analyses, and secure user accounts, the project strives to revolutionize healthcare by offering a comprehensive and user-centric approach to medical diagnosis and health management. Keywords: AI Integration, Fracture Detection, Brain Tumor Identification, Thyroid Detection, Blood Analysis, Secure Medical Report Storage, AI Chat Bot.

AI chatbot distractions and academic triumphs: a mediation approach with self-control and coping skills

Research aims: This study investigates self-control and coping skills in academic performance moderated by AI Chatbot addiction.Design/Methodology/Approach: This study used an online survey and archival method and included 153 accounting student respondents as the final sample. Structural Equation Modelling using Smart-PLS was employed to estimate the relationship between variables.Research findings: The findings underscore the significant impact of self-control in mitigating addictive tendencies, highlighting the susceptibility of individuals with lower self-control to develop addictive behaviors toward AI Chatbots. In comparison, coping skills were not found to have a substantial effect on reducing AI Chatbot addiction.Theoretical contribution/Originality: This research demonstrates that self-control and coping skills play a crucial role in controlling the dependence on AI-based chatbots, ultimately contributing to a better understanding of the relationship between these psychological abilities and managing AI addiction in university accounting students (Chassignol et al., 2018; Sollosy McInerney, 2022).Practitioner/Policy implication: The findings have implications for chatbot designers and developers. Understanding the potential for addictive behavior allows for the implementation of behavior detection and prevention mechanisms within chatbot designs.Research limitation/Implication: This study overlooked diverse forms of self-control and coping skills, along with other factors that contribute to AI Chatbot addiction. Recommending the exploration of various self-control strategies and coping skills could be a valuable opportunity for future research.

Say what you want: Evaluation and engagement with YouTube broadcasts on ChatGPT

ChatGPT caused a worldwide sensation upon its launch, as evidenced by the extensive coverage across traditional and new media. This paper delves into the diverse evaluative discourses about this AI chatbot both in YouTube news videos (originally, television broadcasts) and in user comments facilitated by YouTube’s interactivity. The qualitative-quantitative discourse analysis probes diversified evaluations within YouTube broadcast talk, together with their impact on viewers’ perceptions of the broadcasts’ stance and viewers’ evaluations of ChatGPT and the broadcasts, as reflected by user comments. The findings present balanced effects, speaking to polarised opinions and mixed feelings about this AI development, but point to a potential boomerang effect in users’ evaluation of the new AI bot relative to the broadcasts considered to be biased. The study also reports low user engagement with the broadcasts. This challenges the notion of user engagement with broadcast content as lying at the heart of user interactivity on YouTube.

Understanding User Preferences in Developing a Mental Healthcare AI Chatbot: A Conjoint Analysis Approach

The global population is experiencing a significant rise in cases of depressive disorders, which have been exacerbated by the COVID-19 pandemic. However, having limited resources and fear of social stigma have discouraged individuals from seeking professional psychological counseling or visiting hospitals. In response to this issue, psychiatrists have attempted the use of chatbots as a therapeutic aid. Therefore, in this study, users’ choice data about the mental healthcare AI chatbot are collected through conjoint analysis, and the collected data is analyzed using the mixed logit method to derive users’ preferences for the mental healthcare AI chatbot. Findings highlight a consistent preference among users for certain factors in both psychological counseling chatbots and traditional psychological counseling. At first, the findings indicate that users place the highest priority on pricing and the ability to connect with a professional counselor. Furthermore, users prefer chatbots that have a more human-like appearance and characteristics. By incorporating these preferences, chatbot developers can create a more user-centric mental healthcare AI chatbot.

Design of an AI Chatbot Using Generative AI to Access Local Database

The "College Chatbot" project aims to create an advanced conversational agent tailored for college-related inquiries. This innovative chatbot incorporates a versatile interface, capable of seamlessly processing both text and voice inputs, enhancing user accessibility. Its distinctive feature includes multilingual output capabilities, enabling responses in local languages to cater to a diverse user base. The primary function of the chatbot is to comprehensively address a wide array of college-related queries, providing students and users with accurate and timely information on various aspects of college life, academic affairs, and related topics. By combining a user-friendly interface with linguistic flexibility, the College Chatbot seeks to revolutionize the way students interact with and retrieve information from their educational institutions. Keywords- AI chatbot, Generative AI, Local database, Natural Language processing, Data Integrarion,User Intraction, Query mechanism, Model training.

Research on Influencing Factors of AI Chat Robot on Customer Satisfaction of Online Shopping Platform

Based on the technology acceptance model, this study deeply investigates the factors influencing customer satisfaction of AI Chatbot, and portrays the relationships between different latent variables from both TAM and external factors to reveal the information quality, usability, self-efficacy, perceived enjoyment, subjective norms, perceived ease of use, perceived usefulness and customer satisfaction. A total of 481 valid questionnaires were obtained through online questionnaire distribution and offline interview research, and the samples were analyzed by SPSS software for reliability and heterogeneity, and then the SEM model path analysis was conducted by Amos software to derive the direct or indirect relationships among the variables. Main research conclusions include:(1) information quality, usability, self-efficacy, perceived enjoyment have a direct impact on customers' perceived ease of use (2) subjective norms can positively affect customers' perceived usefulness; (3) perceived ease of use and perceived usefulness have a direct positive impact on customers' satisfaction. Last, this study further discusses the research results, elaborates the theoretical significance and practical significance of this study, and finally puts forward the limitations and looks forward to future studies.

Online Medicine Application with Personalized Blockchain Wallet and AI-Based Doctor Consultation System

The "Online Medicine Application with Personalized Blockchain Wallet and AI-based Doctor Consultancy System" presents a visionary approach to address the evolving healthcare landscape by integrating cutting-edge technologies. This initiative encompasses an intuitive online medical application facilitating seamless healthcare service access, alongside a secure and personalized blockchain wallet for confidential health record management. Additionally, it features an AI-driven doctor consultancy system for intelligent diagnosis and treatment recommendations. Emphasizing digital transformation, accessibility, and data security, the project aims to enhance healthcare convenience and patient-centricity. Successful implementation promises to revolutionize healthcare delivery, empowering individuals while addressing regulatory challenges. This report delineates the project methodology, utilized technologies, system architecture, data privacy measures, implementation phases, and testing processes. Moreover, it discusses user training, support strategies, deployment plans, and future directions. By amalgamating these components, the project endeavours to redefine healthcare accessibility and quality, transforming the delivery and experience of healthcare services. Keywords: Blockchain Healthcare, Medical Records Security, Medication Catalog, Personalized Blockchain Wallet, AI Chatbot, Smart Contracts, Patient Privacy

Mental Health Analysis AI Chatbot

The project work is a practical experience of the knowledge one has. The documentation leads a way to the concept to present the thinking and the upgradation of various techniques into the project. This project entitled “Mental Health Analysis AI Chatbot” is a practical project based on some trends of computer science. Every day the world is searching new techniques in the field of computer science to upgrade human limitations into machines to get more and more accurate and meaningful data. More and more mental health issues such as depression are getting known and recognized by our society today. However, not all of them can receive appropriate treatment. There are many of us still facing the problem of getting the appropriate mental health services every day. We cannot deny the fact that not everyone can get mental healthcare services as they might face some difficulties such as financial problems. Therefore, we may look for new solutions to fix this mental health issue. This demand for solving this issue has led to the proposal of technology as a solution. Chatbot, also known as a conversational agent which can participate in the conversation might be considered one of the solutions too. By mimicking the conversation between human counselor and patient, it can provide counselor service to the patient at some point. However, to further improve the quality of the counselor service, the improvement of the chatbot has to be carried out. By using deep learning, this proposed chatbot can recognize the meaning of the conversation and give a relevant response.

Towards algorithm auditing: managing legal, ethical and technological risks of AI, ML and associated algorithms.

-Business reliance on algorithms is becoming ubiquitous, and companies are increasingly concerned about their algorithms causing major financial or reputational damage. High-profile cases include Google's AI algorithm for photo classification mistakenly labelling a black couple as gorillas in 2015 (Gebru 2020 In The Oxford handbook of ethics of AI, pp. 251-269), Microsoft's AI chatbot Tay that spread racist, sexist and antisemitic speech on Twitter (now X) (Wolf et al. 2017 ACM Sigcas Comput. Soc. 47, 54-64 (doi:10.1145/3144592.3144598)), and Amazon's AI recruiting tool being scrapped after showing bias against women. In response, governments are legislating and imposing bans, regulators fining companies and the judiciary discussing potentially making algorithms artificial 'persons' in law. As with financial audits, governments, business and society will require algorithm audits; formal assurance that algorithms are legal, ethical and safe. A new industry is envisaged: Auditing and Assurance of Algorithms (cf. data privacy), with the remit to professionalize and industrialize AI, ML and associated algorithms. The stakeholders range from those working on policy/regulation to industry practitioners and developers. We also anticipate the nature and scope of the auditing levels and framework presented will inform those interested in systems of governance and compliance with regulation/standards. Our goal in this article is to survey the key areas necessary to perform auditing and assurance and instigate the debate in this novel area of research and practice.

Chat Kanoon: A Novel Approach to Legal Assistance in India

This paper presents ChatKanoon, an innovative multilingual AI chatbot tailored for the Indian legal system. Utilising advanced language models like GPT-4 and Llama2 70B, ChatKanoon employs instructional techniques rather than traditional model fine-tuning, to provide contextually relevant legal advice. This approach addresses critical challenges in India's legal sector, including limited access to legal information, high service costs, and the scarcity of specialised guidance. ChatKanoon's development involved using a diverse array of legal documents and case laws, which enabled the chatbot to deliver precise and reliable legal information. The paper describes the application of instructional techniques in guiding language models, the process of dataset utilisation, and the development of an intuitive chatbot interface. ChatKanoon is positioned as a tool to democratise legal information, making it more accessible and affordable, thereby enhancing the efficiency of legal procedures in India. The paper concludes by discussing the current limitations and future potential of ChatKanoon, along with the broader impact of AI-driven legal assistance tools in developing countries. ChatKanoon exemplifies the transformative role of AI in the legal domain, with the potential to revolutionise legal aid in India and beyond.

Exploring AI Chatbot Development for Gen-Z: A Study on First-Time and Experienced Voters in Pemilu

Artificial intelligence (AI) chatbots have been utilized as interactive learning platforms for higher education. Gen-Z was a generation that quickly adopted the latest technology. Several Gen-Z students participated in the Pemilu (general elections in Indonesia) for the first time in 2024. Therefore, this research aimed to develop an AI chatbot to give information about Pemilu to Gen-Z voters. The researcher developed the AI chatbot with several steps: data collecting, training, evaluating, refining, and analyzing conversation data. A group of 100 Gen-Z students took part in testing the AI chatbot. The researcher discovered that it was essential to keep refining the AI chatbot by improving the datasets and putting more context in it. Next, the researcher asserted that experienced Gen-Z voters asked more questions, as they have prior knowledge of experiencing the previous elections. Most of the experienced Gen-Z voters asked advanced questions, while most of the first-time Gen-Z voters asked basic questions. Moreover, the AI chatbot was a suitable learning platform for Gen-Z as they used metacognitive strategies to experiment with their questions to get the correct information from the AI chatbot. That action automatically helped the AI chatbot to improve its performance as part of the training step. Abstrak Artificial intelligence (AI) chatbots telah digunakan sebagai platform pembelajaran interaktif pada level pendidikan tinggi. Gen-Z adalah generasi yang cepat mengadopsi teknologi. Beberapa siswa dari kalangan Gen-Z akan berpartisipasi dalam Pemilu untuk pertama kali pada tahun 2024. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan AI chatbot yang dapat memberikan informasi kepada Gen-Z tentang Pemilu. Peneliti mengembangkan AI chatbot melalui beberapa langkah: data collecting, training, evaluating, refining dan analyzing data percakapan. Sebanyak 100 orang mahasiswa Gen-Z berpartisipasi dalam proses testing chatbot. Peneliti menyimpulkan bahwa sangatlah penting untuk tetap melakukan proses refining dengan cara memperbaiki datasets dan menaruh lebih banyak konteks ke dalamnya. Peneliti juga menemukan bahwa experienced voters melontarkan pertanyaan lebih banyak daripada first-time voters. Kemudian, experienced voters juga menanyakan topik yang lebih advanced karena mereka sudah mempunyai pengalaman mengikuti Pemilu, sedangkan first-time voters hanya menanyakan pertanyaan dasar tentang Pemilu. Selain itu, AI chatbots adalah platform yang cocok untuk Gen-Z karena mereka cenderung menggunakan stratgegi metacognitive untuk terus bereksperimen dengan pertanyaan - pertanyaan agar mendapatkan jawaban yang tepat dari chatbot. Hal ini secara otomatis juga akan meningkatkan performa dari chatbot sebagai bagian dari proses training AI chatbot.

Interactive AI Chatbot for Mental Illness

In today's increasingly technological world, mental health awareness is paramount, with the intersection of technology and wellness offering innovative solutions to alleviation of depression symptoms, attrition, and loss of follow-up in mental health treatment. To start a good life healthcare is more important. Mental health problems becoming more common, there's a need for easy-to-access support. Our chatbot uses smart technology to understand what users are feeling, offer kind responses. It's built using advanced computer learning to get better at recognizing and dealing with different mental health concerns. In this application implement natural language processing (NLP) and speech recognition. The application includes a robust authentication system for user security, featuring traditional methods like username/password verification, alongside a graphical password authentication system. Users can select a random image during registration, which is then split into shares for secure storage. The chatbot analyzes user queries to recommend tailored stress-relief strategies, including mindfulness exercises, relaxation techniques, and personalized yoga poses displayed with accompanying images and instructions. The backend manages user data, recommendation algorithms, and integration with external services, while the frontend offers intuitive interfaces for seamless user interaction. Thorough testing ensures functionality, usability, and security before deployment, with continuous improvement based on user feedback and technological advancements driving the project evolution.

Developing a Retrieval Augmented Generation (RAG) Chatbot App Using Adaptive Large Language Models (LLM) and LangChain Framework

CARA BURGAN, Dept of Computer Sciences, Mathematics, and Engineering, Shepherd University, Shepherdstown, WV, 25443, JOSIAH KOWALSKI, Dept of Computer Sciences, Mathematics, and Engineering, Shepherd University, Shepherdstown, WV, 25443, and WEIDONG LIAO (Faculty Advisor), Dept of Computer Sciences, Mathematics, and Engineering, Shepherd University, Shepherdstown, WV, 25443. Developing a Retrieval Augmented Generation (RAG) Chatbot App Using Adaptive Large Language Models (LLM) and LangChain Framework RamChat is an AI chatbot designed to assist Shepherd University students in navigating the student handbook. Developed in Python, it utilizes both API-based and local Large Language Models (LLMs) for natural language processing (NLP), alongside a vector store system. Our aim is to create a high-quality chatbot app tailored for student use. We began by researching existing chatbot platforms and created a vector store with embeddings from OpenAI's text-embedding-3-small model, trained on the Shepherd University handbook. Testing each LLM helped assess answer types and accuracy. Development involved debugging and optimizing RamChat's code, including replacing OpenAI's davinci-002 model with gemma, a local LLM based on Google's Gemini model. Ollama framework aids in automatic LLM selection based on user prompts. Our conference presentation will detail RamChat's development, methodology, challenges, and insights. RamChat represents an innovative application of AI to enhance the Shepherd University student experience.

Higher Education Faculty Perceptions of ChatGPT and the Influencing Factors: A Sentiment Analysis of X

ChatGPT, an AI chatbot developed by OpenAI, was released in November 2022, sparking a significant surge in global awareness and utilization of generative AI across various domains. Although recent studies have acknowledged the significance of ChatGPT in the education sector, they have yet to focus on exploring faculty attitudes toward ChatGPT. We gathered a comprehensive corpus of tweets containing “#ChatGPT” and “#highered” between November 30th, 2022, and April 30th, 2023. We analyzed data by triangulating VADER, NRC lexicon, and ground coding. Findings suggest that 40% of the expressed sentiments were positive, 51% were neutral, and 9% were negative. The study also revealed the diverse range of emotions held by higher education faculty regarding ChatGPT, with trust and joy being the most prevalent positive sentiments and fear and anger being the most prevalent negative sentiments. This study shed light on faculty members’ perceptions of ChatGPT, contributing to a better understanding of the impact, emotions, and incorporation of ChatGPT in the higher education sector.