Chatbot Research Articles

Conversational AI: Designing Intelligent Chatbots and Virtual Assistants

Conversational AI has revolutionized the way humans interact with machines. By leveraging advances in Natural Language Processing (NLP) and Machine Learning (ML), intelligent Chatbots and virtual assistants have become integral tools across various sectors. This paper explores the design principles, technological frameworks, and application areas of conversational AI, focusing on the challenges and future directions of this rapidly evolving field.

Impact of Human-Like Empathy of AI Chatbots and Privacy Concerns on Consumer Complaint Behavior in E-Commerce

Impact of Human-Like Empathy of AI Chatbots and Privacy Concerns on Consumer Complaint Behavior in E-Commerce

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 & thyroid report analysis to predict & 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.

A Study on Social Media Strategies Om Online Shopping Cart

The study examines the impact of social media strategies on online shopping cart abandonment Using a sample 245 online shoppers , we analyze the effectiveness of various social media strategies in reducing cart abandonment rates. we employ u-test ,h-test, and correlation analysis to evaluate the relationship between social media engagement and cart abandonment. our findings suggest that certain social media strategies significantly influence online shopping behavior , providing valuable insights for e-commerce businesses. Future flow technologies refers to a range of emerging technologies that are expected to shape the future of online shopping. These may include artificial intelligence (AI) for personalized shopping experiences, augmented reality (AR) for virtual try- ons , and chat bots for customer service. These technologies aim to enhance user experience, increase conversion rates, and reduce cart abandonment by providing more engaging and efficient shopping experiences.

Streamlining College Inquiries: Developing an Intelligent Chatbot for Accessing Course, Fee, and Admission Details

In the past, students faced the arduous task of physically visiting colleges to inquire about courses, fee structures, admission processes, and other relevant information. Recognizing the inefficiency of this traditional approach, we propose the development of a College Enquiry Chatbot—a Python-based web application designed to provide comprehensive information to users about college-related queries. Leveraging machine learning techniques, this chatbot aims to streamline the inquiry process, offering prompt and accurate responses to user inquiries. Keywords: Chatbot, Python, Chatter Bot, Django.

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.

Towards Building a Chatbot-Based First Aid Service in Arabic Language

In this paper, we introduce a modern standard Arabic (MSA) conversational AI in the field of first aid to assist anyone facing an emergency case. The proposed chatbot -based model not only provide adequate medical assistance, but also engage in empathetic interactions with users. Due to the lack of a reliable dataset that fits our purpose, we collect and construct a dataset of 374 records covering 55 first aid topic. Our chatbot architecture relies fine tuning pretrained language models in its intent classification and employs textual similarity to match user queries to records from the dataset. We evaluate the proposed model based using both a quantitative approach, through performance metrics of different modules, and a qualitative approach using a questionnaire.

Testing Three Modalities - Voice Assistant, Chat Bot and Mobile App - to Assist Older African American/Black adults in Seeking Information on Alzheimer and related Dementias: Wizard of Oz Usability study. (Preprint)

Testing Three Modalities - Voice Assistant, Chat Bot and Mobile App - to Assist Older African American/Black adults in Seeking Information on Alzheimer and related Dementias: Wizard of Oz Usability study. (Preprint)

Evaluation of AI ChatBots for the Creation of Patient-Informed Consent Sheets

Introduction: Large language models (LLMs), such as ChatGPT, are a topic of major public interest, and their potential benefits and threats are a subject of discussion. The potential contribution of these models to health care is widely discussed. However, few studies to date have examined LLMs. For example, the potential use of LLMs in (individualized) informed consent remains unclear. Methods: We analyzed the performance of the LLMs ChatGPT 3.5, ChatGPT 4.0, and Gemini with regard to their ability to create an information sheet for six basic anesthesiologic procedures in response to corresponding questions. We performed multiple attempts to create forms for anesthesia and analyzed the results checklists based on existing standard sheets. Results: None of the LLMs tested were able to create a legally compliant information sheet for any basic anesthesiologic procedure. Overall, fewer than one-third of the risks, procedural descriptions, and preparations listed were covered by the LLMs. Conclusions: There are clear limitations of current LLMs in terms of practical application. Advantages in the generation of patient-adapted risk stratification within individual informed consent forms are not available at the moment, although the potential for further development is difficult to predict.

ChatGPT in Education

AI chatbots, e.g. ChatGPT, are becoming increasingly popular in education as a means to enhance student learning experiences and improve teaching efficiency. This study utilizes NVivo 12 Plus to examine the role of AI chatbots in education, ethical considerations, and sentimental analysis regarding the utilization of ChatGPT in education. ChatGPT has revolutionized education, but their use raises ethical concerns. They can enhance language learning, but may lead to plagiarism and information overload. Students may not develop discrimination skills and may rely on ChatGPT, leading to concerns about academic dishonesty and a failure to develop cognitive and analytical skills. The use of ChatGPT in clinical education also raises accountability and liability concerns regarding the use of patient information for educational purposes. Guidelines should be established to ensure privacy rights are upheld. Finally, the positive sentiment category was populated by predominantly positive sentiments, followed by neutral and negative sentiments. Future research on ChatGPT in education should focus on its application effectiveness in various educational settings and ethical considerations.

GenAI and me: the hidden work of building and maintaining an augmentative partnership

AbstractIt has been argued that emergent AI systems should be viewed as working partners rather than tools. Building on this perspective, this study investigates the process through which academics develop a working partnership with generative AI chatbots using a relationship lens and collaborative autoethnographic methods. Based on a collaborative autoethnographic analysis of our experiences of working with AI, we identify five stages of relationship development in building a successful working partnership with generative AI: Playing Around, Infatuation, Committing, Frustration, and Enlightenment and Readjustment. In reporting each stage, we provide vignettes to illustrate the emotional and cognitive challenges and rewards involved, the developing skills, and the experienced anthropomorphic dimension of this emerging relationship. Drawing on prior theory, we identify and examine three types of work that are required in developing this working partnership: articulation work, relationship work, and identity work. We analyse how each type of work unfolds with the stages of relationship development and consider implications for research and practice.

Performance of artificial intelligence chatbots in interpreting clinical images of pressure injuries.

To evaluate the accuracy of AI chatbots in staging pressure injuries according to the National Pressure Injury Advisory Panel (NPIAP) Staging through clinical image interpretation, a cross-sectional design was conducted to assess five leading publicly available AI chatbots. As a result, three chatbots were unable to interpret the clinical images, whereas GPT-4 Turbo achieved a high accuracy rate (83.0%) in staging pressure injuries, notably outperforming BingAI Creative mode (24.0%) with statistical significance (p < 0.001). GPT-4 Turbo accurately identified Stages 1 (p < 0.001), 3 (p = 0.001), and 4 (p < 0.001) pressure injuries, and suspected deep tissue injuries (p < 0.001), while BingAI demonstrated significantly lower accuracy across all stages. The findings highlight the potential of AI chatbots, especially GPT-4 Turbo, in accurately diagnosing images and aiding the subsequent management of pressure injuries.

Enhancing Chatbot Intelligence Through Narrative Memory Structures

Through the use of narrative memory structures—a cutting-edge technique intended to provide chatbots context awareness and conversational coherence—we sought to improve the intelligence of chatbots. We carefully designed our process with the goal of immediately incorporating narrative data into the chatbot's memory architecture. In order to find narrative patterns, this required evaluating and classifying previous exchanges. The narrative patterns were then saved and used to guide the chatbot's answers. The incorporation of narrative memory structures into the chatbot resulted in a significant improvement in conversational coherence and relevance, as per our study's key findings. Through the use of its narrative memory, which stores earlier encounters, the chatbot shown an impressive capacity to sustain the conversation's flow and provide more contextually relevant replies. In addition, the chatbot demonstrated improved understanding of human intentions, correctly identifying underlying motives and preferences. In addition, comments produced by integrating narrative memory structures were highly customized in addition to being accurate. By utilizing the extensive history of previous exchanges, the chatbot was able to customize replies to each user's unique situation, building a closer relationship and rapport with them. All things considered; our study highlights how narrative memory processes can revolutionize chatbot intelligence. We can improve chatbots' conversational capabilities and enable more meaningful human-computer interactions by giving them the capacity to extract narrative information from previous conversations. This opens the door to a new era of chatbot designs that put the needs of users, contextuality, and empathy first, changing the game for conversational AI in the process.

CHATBOT USING LARGE LANGUAGE MODEL

The concept of Natural Language Processing has seen a remarkable advancement in the recent years. This remarkable advancement was particularly with the development of Large Language Models (LLM). Large Language Models are used to develop a human like conversations. This LLM is a part of Natural Language Processing which focuses on enabling computers to understand, interpret, and generate human language. The existing system of chatbots does not generate human like responses. The proposed system of chatbots uses the power of Large Language Models to generate more human like responses, providing the conversation in a natural way. By genereating human like respones, it will be in a natural way for the user. To enhance user experience, the chatbot uses a dynamic learning mechanism, by which it continuously adapt to user preferences and evolving conversational patterns. This system uses feedbacks from the users to refine its responses everytime.Moreover, the chatbot is designed with a multi-turn conversational context awareness, allowing it to maintain coherence and relevance throughout extended dialogues.The effectiveness of the proposed chatbot is evaluated through user testing, comparing its performance against traditional rule-based chatbots and existing conversational agents. This report explains about the usage of Large Language Models in the design and implementation of conversational chatbots. The outcomes of this research contribute to the advancement of intelligent chatbot systems, demonstrating the potential of large language models to significantly enhance conversational AI applications.

Defining responsible use of AI chatbots in social care for older adults.

Defining responsible use of AI chatbots in social care for older adults.

Assessing the Suitability of Artificial Intelligence-Based Chatbots as Counseling Agents for Patients with Brain Tumor: A Comprehensive Survey Analysis

The internet, particularly social media, has become a popular resource for learning about health and investigating one's own health conditions. The development of AI chatbots has been fueled by the increasing availability of digital health data and advances in natural language processing techniques. While these chatbots are more accessible than before, they sometimes fail to provide accurate information. We used representative chatbots currently available (ChatGPT-3.5, Bing Chat, and Google Bard) to answer questions commonly asked by brain tumor patients. The simulated situations with questions were made and selected by the brain tumor committee. These questions are commonly asked by brain tumor patients. The goal of the study was introduced to each chatbot, the situation was explained, and questions were asked. All responses were collected without modification. The answers were shown to the committee members, and they were asked to judge the responses while blinded to the type of chatbot. There was no significant difference in accuracy and communication ability among the three groups (p=0.253, 0.090, respectively). For empathy, Bing Chat and Google Bard were superior to ChatGPT (p=0.004, 0.002, respectively). The purpose of this study was not to assess or verify the relative superiority of each chatbot. Instead, the aim was to identify the shortcomings and changes needed if AI chatbots are to be used for patient medical purposes. AI-based chatbots are a convenient way for patients and the general public to access medical information. Under such circumstances, medical professionals must ensure that the information provided to chatbot users is accurate and safe.

The impact of a chatbot working as an assistant in a course for supporting student learning and engagement

AbstractNowadays, many digital learning tools can be integrated into a course to enhance the teaching–learning process. It is a fact that technology is changing how students learn and how professors teach. The growing utilization of AI chatbots in education to support students' learning underscores the importance of identifying critical aspects related to students' acceptance of this technology. Teachers require a deeper understanding of how students perceive and respond to chatbot assistance, as well as methods to measure levels of satisfaction, engagement, and knowledge acquired while using these technological tools. The aim of this study was, on the one hand, to illustrate the integration of a chatbot into a course to assist students in solving specific learning activities. On the other hand, it aimed to analyze the correlation between the factors influencing university students' intention to use chatbots and their perceived usefulness. It is noteworthy that the learning activity integrated two technologies: an Integrated Development Environment and a chatbot, offering additional educational value to students. The Technology Acceptance Model was used to measure the students' perceived usefulness and attitude toward this digital learning tool. The findings of this study provided insights to faculty on how to integrate and use chatbots to enhance students' engagement and motivation. The results revealed that the perceived usefulness of chatbots does, in fact, influence students' intention to use them. Most of the students expressed satisfaction with having a chatbot to assist them in solving exercises. Students highlighted that one of the most significant benefits was the 24/7 chatbot's support availability and its user‐friendly interface.

Making the Case for Audience Design in Conversational AI: Users’ Pragmatic Strategies and Rapport Expectations in Interaction with a Task-Oriented Chatbot

Abstract With chatbots becoming more and more prevalent in commercial and service contexts, they need to be designed to provide equitable access to services for all user groups. This paper argues that insights into users’ pragmatic strategies and rapport expectations can inform the audience design of chatbots and ensure that all users can equally benefit from the services they facilitate. The argument is underpinned by the analysis of simulated user interactions with a chatbot facilitating health appointment bookings, users’ introspective comments on their interactions, and users’ qualitative survey comments. The study shows that users’ pragmatic strategies show considerable variation. It also shows the negative impact of user experiences when the chatbot’s language and interaction patterns do not align with users’ rapport expectations. In closing, the paper uses these findings to define audience design for chatbots and discuss how audience design can be realized and supported by research.

COLLEGE ENQUIRY CHAT-BOT SYSTEM

Nowadays, many people are using smartphone with many new applications i.e. technology is growing day by day. Today Artificial Intelligence is playing a major role in a variety of fields ranging from industries in product manufacturing, to customer care in public relations. As there are many online Artificial Intelligence (AI) systems or chat bots which are in existence that help people solve their problems. So, we are going to implement a virtual assistant based on AI that can solve any college related query. This will work as a College Oriented Intelligence machine. This virtual machine will respond the queries of students on college related issues. A chat bot has information stored in its database to identify the sentences and making a decision itself as response to answer a given question. The college enquiry chat bot will be built using algorithm that analyses queries and understand user’s message Chatbots are conversational systems that can do chat interactions with human automatically. It is developed to be virtual assistant, making entertainment for people, helping for answering the questions, getting driving directions, serving as human partner in smart homes etc. Most of the chatbots utilize the algorithms of artificial intelligence (AI) in order to get the required responses. In this paper, we provide the design of a University Chatbot that provides an efficient and accurate answer for any user questions about university information. This is the first University Chatbot for inquiring about school information in Myanmar Language based on Artificial Intelligence Markup Language and uses Pandora bots as the interpreter. This paper introduces approach made for improving the efficiency of the chatbot or artificial conversational entity used in various commercial and banking sector. Humanizing is to improving the response generation ability of the chatbot. Key Words: Artificial Intelligence, Database. Intelligence Machine.

Language-adaptive artificial intelligence: assessing CHATGPT'S answer to frequently asked questions on total hip arthroplasty questions.

ChatGPT is reported to be an acceptable tool to answer a majority of frequently asked patient questions. ChatGPT also converses in other languages including Urdu, which offers immense potential for the education of Pakistani patients. Therefore, this study evaluated ChatGPT's Urdu answers to the ten most frequently asked questions on Total Hip Arthroplasty, which were then rated by an expert. Out of 10 answers in English, 9 (90%) were satisfactory requiring minimal clarification and 1 (10%) was satisfactory requiring moderate clarification. In both Roman and Nastaliq script Urdu, 1 (10%) answer was satisfactory requiring moderate clarification, while 9 (90%) were unsatisfactory requiring substantial clarification. In conclusion, as opposed to ChatGPT English responses, Urdu responses were much less rigorous, generic, and lacked scientific rigor. We have a long way to go before Pakistani patients with limited English language skills could benefit from AI chatbots like ChatGPT.