Chatbot Systems Research Articles

Assessing Performance of Cloud-based Heterogeneous Chatbot Systems.

Cloud-based heterogeneous chatbot systems represent a significant advancement in automating diverse tasks across various platforms, including customer service, healthcare, and education. These systems are designed with multi-modal capabilities, allowing them to interact via text, voice, and visual interfaces, and are built on a cloud infrastructure that ensures scalability and reliability. The cloud-based architecture allows dynamic resource allocation, enabling the system to handle high volumes of traffic without compromising performance. These chatbots also benefit from global availability, as cloud regions distributed across the world ensure low latency and high availability.The integration of advanced AI and NLP models, such as GPT and BERT, enhances the chatbot's response accuracy and contextual understanding, making interactions more precise and human-like. Moreover, the cloud infrastructure supports continuous learning through machine learning models that refine chatbot performance over time. With multitenant capabilities, these chatbots can cater to different users or organizations, providing tailored services while ensuring that performance are not affected. Additionally, their ability to integrate with external enterprise systems, like CRMs or ERPs, allows for real-time data exchange and task automation.In terms of security, cloud-based chatbots benefit from encryption protocols and compliance with industry regulations, ensuring safe handling of sensitive data, particularly in sectors like healthcare and finance. Despite the advantages, challenges such as network dependency and cost management need careful consideration, as performance can be affected by poor connectivity or high processing costs, especially when using complex AI models. Nonetheless, cloud-based heterogeneous chatbots excel in delivering scalable, reliable, and intelligent interactions, adapting to growing user demands and a wide range of applications.

Xeinabot: A Spoken Intelligent Agent approach Using Hidden Markov Model with Chatbot Technology in Android Environmen

The present study describes the designing and its execution of xeinabot, a public domains spoken smart agent in an Android system. The primary goal of this work is to design and construct a personal agent that combines chatbot technology and statistical methods for speech search. The former uses Hidden Markove System Algorithmic procedures and the N-gram technique for Automatically Speech Recognition, while the latter relies on chatbot systems for Speech Recognizing and uses Multinomial Naïve Bays Method for classification and brute force search for matching patterns. The main objective of this strategy is to create an agent that convinces people into thinking they are speaking with a human when, in reality, they are speaking with a machine. utilizing chatbot technology to make advantage. After evaluating roughly 500 phrases on various subjects, the evaluation findings show very good results and, in the majority of circumstances, the agent behaves like a person. The success task (correct voice recognition and speech understanding) amounts to 86.6%.

Xeinabot: A Spoken Intelligent Agent approach Using Hidden Markov Model with Chatbot Technology in Android Environmen

The present study describes the designing and its execution of xeinabot, a public domains spoken smart agent in an Android system. The primary goal of this work is to design and construct a personal agent that combines chatbot technology and statistical methods for speech search. The former uses Hidden Markove System Algorithmic procedures and the N-gram technique for Automatically Speech Recognition, while the latter relies on chatbot systems for Speech Recognizing and uses Multinomial Naïve Bays Method for classification and brute force search for matching patterns. The main objective of this strategy is to create an agent that convinces people into thinking they are speaking with a human when, in reality, they are speaking with a machine. utilizing chatbot technology to make advantage. After evaluating roughly 500 phrases on various subjects, the evaluation findings show very good results and, in the majority of circumstances, the agent behaves like a person. The success task (correct voice recognition and speech understanding) amounts to 86.6%.

Commercial chatbot monitoring: Approaches focused on automated conversation analysis

Purpose of the study: The purpose of this study is to review and analyze current automated techniques for monitoring chatbot conversations in the field of Conversational Artificial Intelligence. It aims to highlight the challenges and limitations of these techniques and provide insights into various metrics used to measure chatbot performance, with the goal of enhancing it. Methodology: The study employs a comprehensive literature review of existing automated techniques for monitoring chatbot conversations. Then, focusing on state-of-the-art approaches, the study introduces a division into numerical metrics (performance statistics and user engagement) and linguistic metrics (conversation analysis). Within conversation analysis, which is crucial for improving chatbot responses and accurately recognizing user intentions, the study identifies and presents three leading methods. Main Findings: The paper highlights that, while current chatbot numerical conversation metrics allow for continuous monitoring and enhancement of chatbot performance, there is still room for improvement in the automated linguistic analysis of chatbot conversations. Furthermore, monitoring chatbot conversations in an automatic way in order to implement adequate corrective actions, is an essential task for refining chatbot efficiency through continuous learning and adaptation. Applications of the study: The findings of this study have practical applications for businesses employing chatbots. By understanding the potential of current automated monitoring techniques and addressing their limitations, commercial chatbot systems can be improved for the benefit of customer satisfaction. Novelty/Originality of the study: The paper provides readers with the novel knowledge necessary to understand key metrics used to measure chatbot conversations from both numerical and linguistic perspectives. It adds value by guiding readers on how monitoring numerical metrics helps analyze chatbot interactions and explains how the automated linguistic analysis of chatbot conversation content is utilized in leading approaches.

Assessing Generative Pretrained Transformers (GPT) in Clinical Decision-Making: Comparative Analysis of GPT-3.5 and GPT-4.

Artificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement. This study aims to analyze the performance of ChatGPT-3.5 and ChatGPT-4 in addressing complex clinical and ethical dilemmas, and to illustrate their potential role in health care decision-making while comparing seniors' and residents' ratings, and specific question types. A total of 4 specialized physicians formulated 176 real-world clinical questions. A total of 8 senior physicians and residents assessed responses from GPT-3.5 and GPT-4 on a 1-5 scale across 5 categories: accuracy, relevance, clarity, utility, and comprehensiveness. Evaluations were conducted within internal medicine, emergency medicine, and ethics. Comparisons were made globally, between seniors and residents, and across classifications. Both GPT models received high mean scores (4.4, SD 0.8 for GPT-4 and 4.1, SD 1.0 for GPT-3.5). GPT-4 outperformed GPT-3.5 across all rating dimensions, with seniors consistently rating responses higher than residents for both models. Specifically, seniors rated GPT-4 as more beneficial and complete (mean 4.6 vs 4.0 and 4.6 vs 4.1, respectively; P<.001), and GPT-3.5 similarly (mean 4.1 vs 3.7 and 3.9 vs 3.5, respectively; P<.001). Ethical queries received the highest ratings for both models, with mean scores reflecting consistency across accuracy and completeness criteria. Distinctions among question types were significant, particularly for the GPT-4 mean scores in completeness across emergency, internal, and ethical questions (4.2, SD 1.0; 4.3, SD 0.8; and 4.5, SD 0.7, respectively; P<.001), and for GPT-3.5's accuracy, beneficial, and completeness dimensions. ChatGPT's potential to assist physicians with medical issues is promising, with prospects to enhance diagnostics, treatments, and ethics. While integration into clinical workflows may be valuable, it must complement, not replace, human expertise. Continued research is essential to ensure safe and effective implementation in clinical environments.

Leveraging LLM: Implementing an Advanced AI Chatbot for Healthcare

Using the application of Large Language Models (LLMs) in healthcare settings, mainly focusing on addressing general illness inquiries through chatbot interfaces. Leveraging the capabilities of LLMs, explore their potential to provide accurate and contextually relevant responses to users seeking information about common health concerns. LLM have the capacity continuously learn and improve from user interaction. Through benchmarking experiments, this paper evaluates the accuracy (61%) of LLM-based chatbots in understanding and responding to user queries related to general illnesses. The findings demonstrate the performance of LLMs against established benchmarks, shedding light on their efficacy in healthcare applications. By examining the intersection of LLM technology and healthcare, this research contributes to advancing the development of intelligent chatbot systems capable of providing reliable and informative support to individuals seeking medical guidance for general health issues.

Predicting the use of chatbot systems in education: a comparative approach using PLS-SEM and machine learning algorithms

Adopting innovations in educational practice is a challenging task. In order to promote the use of technological innovations, acceptance of the technology by potential users is a prerequisite. Indeed, understanding the various factors that influence technology acceptance is critical for technology acceptance research. The use and acceptance of chatbots in education as a technological innovation is a topic that needs to be investigated. Chatbots, which offer close to human interaction between the user and technology through text and voice, can provide significant benefits in educational environments. The UTAUT2 model (extending UTAUT), which is widely used to evaluate technology acceptance, can serve as a framework for evaluating the acceptance and use of chatbots. This study aims to predict factors influencing students' use of chatbots in education within the UTAUT2 framework. PLS-SEM and machine learning tested the model, involving 926 students. According to the findings of the study, behavioral intentions were influenced by various factors including performance expectations and attitudes. Facilitating conditions and intentions significantly impacted chatbot usage time. Moderator effects were observed with age, gender, and usage experience affecting behavioral intentions. Support vector machine and logistic regression showed high prediction accuracies for behavioral intentions and usage time, respectively. These results provide insights for chatbot designers to meet user needs in educational settings.

The Chatbot Systems for Mathematics Education using Knowledge Graphs and Named Entity Recognition

The development of chatbot systems for mathematics courses in elementary school has gained significant attention due to their potential to enhance the learning experience. This study proposes a novel approach that combines knowledge graph (KG) and Named Entity Recognition (NER) methods using Neo4j and SpaCy within the Rasa Open-Source v3.0 platform as chatbot frameworks. The knowledge graphs represent mathematical concepts and their relationships, enabling the chatbot to provide accurate and relevant responses to user queries. The NER SpaCy is employed to identify and extract mathematical entities from user inputs, ensuring a precise understanding of the context. The integrations of Neo4j and NER using SpaCy with Rasa Open-Source v3.0 facilitate efficient information retrieval and improve the conversational abilities of the chatbot. Experimental results demonstrate the effectiveness of the proposed approach, showcasing its potential as an educational tool for fifth-grade students in elementary schools.

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.

Narrative literature review: Efficiency enhancement - user trust in chatbots as a tool for improving service quality by humans

Chatbots have become efficient and reliable tools for instant and real-time information dissemination. Despite their effectiveness, user trust in chatbot systems remains relatively low. A holistic approach is necessary, integrating user emotional experiences, trust-building strategies, and continuous technological refinement to maximize chatbot benefits across various sectors. This research explores the potential for selective information dissemination based on user preferences using chatbots combined with artificial intelligence. Through a narrative approach, the study reviews literature and analyzes eight articles related to chatbots' application in information dissemination. The results indicate that chatbots are efficient in providing information and can be customized for various needs, such as population services, reminder notifications, and book processing. Chatbots have the potential to enhance services and can be integrated into information systems to improve service quality. However, challenges such as reliance on high-quality data and machine learning, difficulties in understanding non-formal language or slang, and limitations in handling complex questions need to be addressed for chatbots to reach their full potential.

AI Enabled Chatbot

Abstract: As technology continues its rapid evolution, the integration of Artificial Intelligence (AI) into chatbot systems emerges as a pivotal frontier in reshaping human-computer interaction. This research paper embarks on a comprehensive exploration of the intricate synergy between AI technologies and chatbot development, with a primary focus on elevating user interactions to unprecedented levels of sophistication and intuitiveness. By delving into a nuanced understanding of methodologies, technologies, and challenges, this study aims to provide a holistic perspective on the present state and future potential of AIenabled chatbots. The journey begins with a retrospective analysis of the evolution of chatbots, tracing their trajectory from rulebased systems to the forefront of AI-driven conversational agents. The advent of AI, particularly Natural Language Processing (NLP) and machine learning algorithms, has ushered in a new era, enabling chatbots to not only comprehend but also respond intelligently, mirroring the complexities of human language.

Business chatbots with deep learning technologies: state-of-the-art, taxonomies, and future research directions

With the support of advanced hardware and software technology, Artificial Intelligence (AI) techniques, especially the increasing number of deep learning algorithms, have spawned the popularization of online intelligent services and accelerated the contemporary development and applications of chatbot systems. The promise of providing 24/7 uninterrupted business services and minimizing workforce costs has made business chatbots a hot topic due to the impact of the pandemic. It has attracted considerable attention from academic researchers and business practitioners. However, a thorough technical review of advanced chatbot technologies and their relevance and applications to various business domains is rare in the literature. The main contribution of this review article is the critical analysis of various chatbot development approaches and the underlying deep learning computational methods in the context of some business applications. We first conceptualize current business chatbot architectures and illustrate the technical characteristics of two common structures. Next, we explore the mainstream deep learning technologies in chatbot design from the perspective of computational methods and usages. Then, we propose a new framework to classify chatbot construction architectures and differentiate the traditional retrieval-based and generation-based chatbots in terms of the modern pipeline and end-to-end structures. Finally, we highlight future research directions for business chatbots to enable researchers to devote their efforts to the most promising research topics and commercial scenarios and for practitioners to benefit from realizing the trend in business chatbot development and applications.

Accuracy and Bias in Artificial Intelligence Chatbot Recommendations for Oculoplastic Surgeons.

Purpose The purpose of this study is to assess the accuracy of and bias in recommendations for oculoplastic surgeons from three artificial intelligence (AI) chatbot systems. Methods ChatGPT, Microsoft Bing Balanced, and Google Bard were asked for recommendations for oculoplastic surgeons practicing in 20 cities with the highest population in the United States. Three prompts were used: "can you help me find (an oculoplastic surgeon)/(a doctor who does eyelid lifts)/(an oculofacial plastic surgeon) in (city)." Results A total of 672 suggestions were made between (oculoplastic surgeon; doctor who does eyelid lifts; oculofacial plastic surgeon); 19.8% suggestions were excluded, leaving 539 suggested physicians. Of these, 64.1% were oculoplastics specialists (of which 70.1% were American Society of Ophthalmic Plastic and Reconstructive Surgery (ASOPRS) members); 16.1% were general plastic surgery trained, 9.0% were ENT trained, 8.8% were ophthalmology but not oculoplastics trained, and 1.9% were trained in another specialty. 27.7% of recommendations across all AI systems were female. Conclusions Among the chatbot systems tested, there were high rates of inaccuracy: up to 38% of recommended surgeons were nonexistent or not practicing in the city requested, and 35.9% of those recommended as oculoplastic/oculofacial plastic surgeons were not oculoplastics specialists. Choice of prompt affected the result, with requests for "a doctor who does eyelid lifts"resulting in more plastic surgeons and ENTs and fewer oculoplastic surgeons. It is important to identify inaccuracies and biases in recommendations provided by AI systems as more patients may start using them to choose a surgeon.

Conversational AI: An Explication of Few-Shot Learning Problem in Transformers-Based Chatbot Systems

With the recent advancements in conversational artificial intelligence (AI), the practical applications of chatbots have risen significantly in diverse domains such as healthcare, education, e-government, customer support systems, social platforms, and entertainment. The chatbot converses with humans in natural language and responds to their queries with precise and relevant answers. The relevant literature presents several methods for intent classification and slot mapping for chatbot question answering. However, the existing chatbot architectures still suffer from few-shot learning problem (imbalance ratio of class labels over samples) and ineffective dialog management to retain the context and slots mapping. This study aims to introduce the architecture of chatbot by focusing few-shot learning problem and context management in dialog-based conversations. First, to mitigate the few-shot learning problem with chatbots, we propose a novel hybrid intent and slots transformers (HIST) model. The HIST chatbot architecture utilizes transformers and self-attention mechanisms along with bigated recurrent unit and combines conditional random field algorithms for intent classification and slot extraction. Second, to address dialog management, we introduce a hybrid interaction strategy for slots mapping and effective conversational context management. To validate the proposed model’s effectiveness, comprehensive empirical analysis is carried out using three benchmark datasets including airline travel information system (ATIS), banking77, and conversational language interface for natural conversation 150 (CLINC150). The results show that HIST outperforms against the state-of-the-art existing methods with a clear margin and obtained an accuracy of 94.89% and 96.17% for intent classification and slots extraction, respectively. The empirical results confirm the effectiveness of the HIST chatbot for resolving the few-shot learning problem with effective dialog management in chatbot systems.

Role of AI Chatbots in Revolutionizing Gaming Experiences - A Survey

This paper investigates the integration of artificial intelligence (AI) chatbots into video games to enhance player experiences. In the realm of modern entertainment, video games often grapple with the constraint of linear storytelling, limiting replayability and the diversity of player interactions. Addressing this challenge, the study advocates for the adoption of AI chatbots, offering a detailed analysis of their features in comparison to traditional chatbot systems. The literature review explores recent research on AI chatbots in gaming, emphasizing their impact on transforming storytelling and fostering stronger connections with players. Ethical considerations related to data access and job displacement concerns are highlighted, emphasizing the necessity for player-centric development. Through a combination of comprehensive literature review and practical analysis of free and open-source games, the research assesses key features, including game type, engine, platform, AI capabilities, player engagement, NPC (non-playable character) behavior, visuals, and identified issues. The comparative analysis distinguishes the strengths and weaknesses of AI chatbots and traditional counterparts in gaming, providing valuable insights for developers aiming to create more immersive and dynamic gaming experiences.

Effectiveness of designing a knowledge-based artificial intelligence chatbot system into a nursing training program: A quasi-experimental design

BackgroundChatbots have gained popularity in the healthcare industry due to their ability to provide prompt and accurate responses to a wide range of inquiries. This has been particularly beneficial for nurses who often require quick access to information and may have questions related to patient care. PurposeTo evaluate the effectiveness of designing a knowledge-based artificial intelligence chatbot system for a nursing training program. MethodsThe study utilized a Quasi-experimental design and collected data from a purposive sample of 73 nurses using Google Forms. The tools used in the study included 1) a structured questionnaire for nurses (a) Demographic data (b) Nurses' knowledge regarding chatbots, 2) Nurses' knowledge about artificial intelligence, 3) Nurses' perception of the application of chatbots in nursing, and 4) Nurses' opinions about the use of nursing chatbots or traditional methods of education. ResultsThere was a highly statistically significant improvement in nurses' knowledge-based chatbot systems post-intervention (p = 0.001). ConclusionIntegrating an artificial intelligence chatbot system into a nursing training program provides nurses with easy access to reliable and evidence-based knowledge. The chatbot offers immediate answers, explanations, and up-to-date resources, empowering nurses to make informed decisions, stay updated, and served as a communication platform connecting nurses through a common language and enhance their practice. RecommendationIncorporating a knowledge-based chatbot system into a nursing training program. Furthermore, further research should be conducted to explore the long-term impact of chatbot systems on nursing practices and education.

A systematic review of artificial intelligence-powered (AI-powered) chatbot intervention for managing chronic illness

Background Utilizing artificial intelligence (AI) in chatbots, especially for chronic diseases, has become increasingly prevalent. These AI-powered chatbots serve as crucial tools for enhancing patient communication, addressing the rising prevalence of chronic conditions, and meeting the growing demand for supportive healthcare applications. However, there is a notable gap in comprehensive reviews evaluating the impact of AI-powered chatbot interventions in healthcare within academic literature. This study aimed to assess user satisfaction, intervention efficacy, and the specific characteristics and AI architectures of chatbot systems designed for chronic diseases. Method A thorough exploration of the existing literature was undertaken by employing diverse databases such as PubMed MEDLINE, CINAHL, EMBASE, PsycINFO, ACM Digital Library and Scopus. The studies incorporated in this analysis encompassed primary research that employed chatbots or other forms of AI architecture in the context of preventing, treating or rehabilitating chronic diseases. The assessment of bias risk was conducted using Risk of 2.0 Tools. Results Seven hundred and eighty-four results were obtained, and subsequently, eight studies were found to align with the inclusion criteria. The intervention methods encompassed health education (n = 3), behaviour change theory (n = 1), stress and coping (n = 1), cognitive behavioural therapy (n = 2) and self-care behaviour (n = 1). The research provided valuable insights into the effectiveness and user-friendliness of AI-powered chatbots in handling various chronic conditions. Overall, users showed favourable acceptance of these chatbots for self-managing chronic illnesses. Conclusions The reviewed studies suggest promising acceptance of AI-powered chatbots for self-managing chronic conditions. However, limited evidence on their efficacy due to insufficient technical documentation calls for future studies to provide detailed descriptions and prioritize patient safety. These chatbots employ natural language processing and multimodal interaction. Subsequent research should focus on evidence-based evaluations, facilitating comparisons across diverse chronic health conditions.

“More than Words”: A Legal Approach to the Risks of Commercial Chatbots Powered by Generative Artificial Intelligence

Abstract The recent commercial release of a new generation of chatbot systems, particularly those leveraging Transformer-based large language models (LLMs) such as ChatGPT, has caught the world by surprise and sparked debate about their potential consequences for society. While concerns about the existential threat posed by these technologies are often discussed, it is crucial to shift our focus towards the more immediate risks associated with their deployment. Such risks are further compounded by the lack of proactive measures addressing users’ literacy and the for-profit model via which these chatbots are distributed. Drawing on research in computer science and other fields, this paper looks at the immediate risks triggered by these products and reflects on the role of law within a broader policy directed at steering generative artificial intelligence technology towards the common good. It also reviews the relevant amendments proposed by the European Parliament to the European Commission’s proposal for an AI Act.

Enhancing E-commerce Chatbots with Falcon-7B and 16-bit Full Quantization

E-commerce chatbots play a crucial role in customer service but often struggle with understanding complex queries. This study introduces a breakthrough approach leveraging the Falcon-7B model, a state-of-the-art Large Language Model (LLM) with 7 billion parameters. Trained on a vast dataset of 1,500 billion tokens from RefinedWeb and curated corpora, the Falcon-7B model excels in natural language understanding and generation. Notably, its 16-bit full quantization transformer ensures efficient computation without compromising scalability or performance. By harnessing cutting-edge machine learning techniques, our method aims to redefine e-commerce chatbot systems, providing businesses with a robust solution for delivering personalized customer experiences.

A Survey of Health Care Chatbot for Patient Support

This literature survey delves into the evolving realm of healthcare chatbots, analyzing a variety of research papers on AI chatbot systems. The papers cover diverse objectives, methodologies, and applications within healthcare, including microservice architectures for chronic patient support, disease prediction, herbal remedies, and mental health support. Common threads across the papers include the adoption of natural language processing, machine learning, and AI markup languages. Ethical considerations, such as data privacy and consent, are identified as crucial aspects. Some papers focus on specific medical domains, while others propose comprehensive frameworks integrating IoT and health knowledge graphs. The survey highlights challenges like unified semantic approaches for patient data and underscores the ongoing need for research to address gaps, enhance chatbot intelligence, and ensure ethical deployment in real-world healthcare scenarios