Educational Chatbot Research Articles

Influences Personalisation and Student Engagement in the AI Era: Exploring Effects and Influences

The study is based on a conceptual model to examine the integration of artificial intelligence (AI) technologies in education and their impact on student engagement. This model structures the analysis around several axes: AI technologies, including intelligent tutoring systems (ITS), adaptive learning platforms, and educational chatbots, play a key role in personalizing learning paths, making pedagogical support more accessible, and adapting content to students' specific needs. Student engagement is thus assessed through the personalization of pathways and the accessibility of support, while taking into account individual moderating factors such as learning styles, self-motivation, and prior experience with AI technologies, which influence the effectiveness of these tools. In addition, the study examines contextual conditions, including the importance of adequate technological infrastructure and teacher training, which are essential for the successful integration of AI technologies into pedagogical practices. This conceptual model guides the study in evaluating the assumptions made, providing an in-depth understanding of the interactions between these variables and making recommendations to optimize the use of AI technologies in education.

Exploring How Education Can Leverage Artificial Intelligence for Social Good

Artificial intelligence (AI) is rapidly transforming society and industries, presenting both opportunities and ethical challenges. AI enables machines to perform tasks traditionally done by humans, such as natural language processing, pattern recognition, decision-making, and problem-solving (Brookings, 2023). In education, AI enhances teaching methodologies, student assessment, and administrative tasks through tools like intelligent tutoring systems, adaptive learning platforms, and educational chatbots. These tools offer customised learning experiences, immediate feedback, and data-driven insights. This research aims to investigate how AI can be leveraged within education to promote social good by identifying how familiar educators and students are with AI tools, identify how educators and students perceive the role of AI in education and what are the current applications of AI technologies in educational settings and how widely are they used. Finally, discuss the opportunities and ethical considerations of integrating AI in education. AI technologies can address critical social challenges such as inequality, accessibility, and personalised learning. According to Luckin et al. (2016), "AI can provide tailored educational experiences that adapt to individual learning needs, thus promoting equity in education." This exploratory research begins with an overview of AI's role and tools in education, followed by a discussion of the challenges, opportunities, and ethical considerations associated with AI integration. Understandings are drawn from educator’s response to a questionnaire and a focus group with first year and final-year third level students. This qualitative data, analysed using NVivo software, reveals key themes and significant findings on effectively utilising AI in education.

Exploring the Effectiveness of Advanced Chatbots in Educational Settings: A Mixed-Methods Study in Statistics

The Generative Pre-trained Transformer (GPT) is a highly advanced natural language processing model. This model can generate conversation-style responses to user input. The rapid rise of GPT has transformed academic domains, with studies exploring the potential of chatbots in education. This research investigates the effectiveness of ChatGPT 3.5, ChatGPT 4.0 by OpenAI, and Chatbot Bing by Microsoft in solving statistical exam-type problems in the educational setting. In addition to quantifying the errors made by these chatbots, this study seeks to understand the causes of these errors to provide recommendations. A mixed-methods approach was employed to achieve this goal, including quantitative and qualitative analyses (Grounded Theory with semi-structured interviews). The quantitative stage involves statistical problem-solving exercises for undergraduate engineering students, revealing error rates based on the reason for the error, statistical fields, sub-statistics fields, and exercise types. The quantitative analysis provided crucial information necessary to proceed with the qualitative study. The qualitative stage employs semi-structured interviews with selected chatbots; this includes confrontation between them that generates agreement, disagreement, and differing viewpoints. On some occasions, chatbots tend to maintain rigid positions, lacking the ability to adapt or acknowledge errors. This inflexibility may affect their effectiveness. The findings contribute to understanding the integration of AI tools in education, offering insights for future implementations and emphasizing the need for critical evaluation and responsible use.

Unveiling the core constructs: A statistical approach to evaluating user experience with Chatbots in higher education (A case study from a university in Ecuador)

Introduction: Chatbots are increasingly utilized in education, offering real-time, personalized communication. While research has explored technical aspects of chatbots, user experience remains under-investigated. This study examines a model for evaluating user experience and satisfaction with chatbots in higher education. Methodology: A four-factor model (information quality, system quality, chatbot experience, user satisfaction) was proposed based on prior research. An alternative two-factor model emerged through exploratory factor analysis, focusing on “Chatbot Response Quality” and “User Experience and Satisfaction with the Chatbot.” Surveys were distributed to students and faculty at a university in Ecuador to collect data. Confirmatory factor analysis validated both models. Results: The two-factor model explained a significantly greater proportion of the data’s variance (55.2%) compared to the four-factor model (46.4%). Conclusion: This study suggests that a simpler model focusing on chatbot response quality and user experience is more effective for evaluating chatbots in education. Future research can explore methods to optimize these factors and improve the learning experience for students.

The Impact of AI-Assisted Teaching on Students' Learning and Psychology

The integration of artificial intelligence (AI) in education has garnered significant attention, yet its implications on student outcomes require further exploration. This paper analyzes the impact of AI-assisted teaching on students' learning and psychological well-being. Through a comprehensive review of existing AI applications in education, including intelligent tutoring systems and educational chatbots, the study examines how these technologies influence academic performance and psychological health. The findings indicate that AI-assisted teaching enhances learning outcomes by providing personalized educational experiences and fostering student engagement. Furthermore, AI systems contribute positively to students' psychological well-being by offering timely emotional support and personalized stress management strategies. However, challenges such as technological limitations, resistance to change, and privacy concerns persist. Based on these insights, the paper suggests actionable recommendations for the effective integration of AI in education, emphasizing the need for robust infrastructure, continuous educator training, and ethical considerations to maximize benefits while mitigating potential risks.

Drivers of Chatbot Adoption among K–12 Teachers in Saudi Arabia

The aim of the current study was to identify the factors influencing teachers’ acceptance of using chatbots in education. To achieve this, we employed the descriptive method, applying the conceptual framework of the unified theory of acceptance and use of technology (UTAUT2) to a sample of 406 teachers from the Eastern Province in Saudi Arabia. By applying structural equation modelling (SEM), the research results revealed that the most influential factors of chatbot acceptance among Saudi teachers were artificial intelligence literacy, followed by hedonic motivation, and then social influence. Meanwhile, performance expectancy, effort expectancy, and facilitating conditions were not significant indicators of teachers’ acceptance of using chatbots in education. In light of these findings, we recommend the following actions: focusing on artificial intelligence literacy for teachers, holding specialised workshops on chatbot applications in education, enhancing teachers’ motivation to use chatbots, and forming professional communities for teachers to exchange experiences and knowledge.

AI chatbots in programming education: Students’ use in a scientific computing course and consequences for learning

Teaching and learning in higher education require adaptation following students' inevitable use of AI chatbots. This study contributes to the empirical literature on students' use of AI chatbots and how they influence learning. The aim of this study is to identify how to adapt programming education in higher engineering education. A mixed-methods case study was conducted of a scientific computing course in a Mechanical Engineering Master's program at a Eindhoven University of Technology in the Netherlands. Data consisted of 29 student questionnaires, a semi-structured group interview with three students, a semi-structured interview with the teacher, and 29 students' grades. Results show that students used ChatGPT for error checking and debugging of code, increasing conceptual understanding, generating, and optimizing solution code, explaining code, and solving mathematical problems. While students reported advantages of using ChatGPT, the teacher expressed concerns over declining code quality and student learning. Furthermore, both students and teacher perceived a negative influence from ChatGPT usage on pair programming, and consequently on student collaboration. The findings suggest that learning objectives should be formulated in more detail, to highlight essential programming skills, and be expanded to include the use of AI tools. Complex programming assignments remain appropriate in programming education, but pair programming as a didactic approach should be reconsidered in light of the growing use of AI Chatbots.

THE EMERGING FUTURE OF AI CHATBOTS IN HIGHER EDUCATION

Incorporating Artificial Intelligence (AI) chatbots within Higher Education Institutions (HEIs) is revolutionizing the educational domain, presenting new avenues for improved student support and administrative effectiveness. This research delves into the prospective impacts of AI chatbots in HEIs, focusing on their influence on teaching, learning, and research activities. Adopting a Narrative Literature Review (NLR) approach, the study compiles and synthesizes existing research on the role of AI chatbots in higher education, drawing from a wide range of academic sources and scholarly literature. The results underscore the significant potential of AI chatbots to streamline administrative functions, enrich student learning experiences, and facilitate research endeavours. Nonetheless, challenges such as concerns over academic integrity, difficulties in accurately interpreting user inputs, and the need for appropriate resource allocation present substantial barriers to the successful adoption of AI chatbots in HEIs. The study emphasizes the critical need for proactive strategies to address ethical issues, ensure comprehensive training for all stakeholders, and formulate clear guidelines for the responsible deployment of AI chatbots in higher education. By overcoming these challenges and capitalizing on the advantages of AI technologies, HEIs can fully exploit the capabilities of AI chatbots, thereby fostering a more efficient, effective, inclusive, and forward-thinking educational environment.

How educational chatbots support self-regulated learning? A systematic review of the literature

How educational chatbots support self-regulated learning? A systematic review of the literature

Can rule-based educational chatbots be an acceptable alternative for students in higher education?

Can rule-based educational chatbots be an acceptable alternative for students in higher education?

Generative AI chatbots in higher education: a review of an emerging research area

Generative AI chatbots in higher education: a review of an emerging research area

Towards effective teaching assistants: From intent-based chatbots to LLM-powered teaching assistants

As chatbot technology undergoes a transformative phase in the era of artificial intelligence (AI), the integration of advanced AI models emerges as a focal point for reshaping conversational agents within the education sector. This paper explores the evolution of educational chatbot development, specifically focusing on building a teaching assistant for Data Mining and Text Analytics courses at the University of Leeds. The primary objective is to investigate and compare traditional intent-based chatbot approaches with the advanced retrieval-augmented generation (RAG) method, aiming to improve the efficiency and adaptability of teaching assistants in higher education. The study begins with the development of an Amazon Alexa teaching skill, assessing the efficacy of traditional chatbot development in higher education. To enrich the chatbot knowledge base, the research then employs an automated question–answer generation (QAG) approach using the QG Lumos Learning tool to extract contextually grounded question–answer datasets from course materials. Subsequently, the RAG-based system is proposed, leveraging LangChain with the OpenAI GPT-3.5 Turbo model. Findings highlight limitations in intent-based approaches, emphasising the need for more adaptive solutions. The proposed RAG-based teaching assistant demonstrates significant improvements in efficiently handling diverse queries, representing a paradigm shift in educational chatbot capabilities. These findings provide an in-depth understanding of the development phase, specifically illustrating the impact on chatbot performance by contrasting traditional methods with large language model-based approaches. The study contributes valuable perspectives on enhancing adaptability and effectiveness in AI-powered educational tools, providing essential considerations for future developments in the field.

Perceptions and Use of AI Chatbots among Students in Higher Education: A Scoping Review of Empirical Studies

With the recent arrival of publicly available AI chatbots like ChatGPT, Copilot, Gemini, and Claude follows a need for knowledge about how students in higher education perceive and use these tools, and what this might mean for their learning processes. This scoping review analyzes 24 empirical articles published between 1 January 2022 and 5 September 2023 on students’ perceptions and use of AI chatbots in higher education. The articles were reviewed using a five-stage scoping review methodology. The findings underscore a global research interest in how students engage with AI chatbots, which is especially pronounced in Asia. The studies span diverse disciplines, with a predominance in science, technology, engineering, and mathematics disciplines. The empirical findings reveal that students perceive AI chatbots as highly useful and motivating as personal task assistants and for getting immediate feedback and help with writing, coding, and academic tasks. However, students are concerned about the accuracy and reliability of the responses from the chatbots, as well as potential negative impacts on their learning processes, critical thinking, discipline, and creativity. The purpose-driven use of AI chatbots among students and their potentially positive influence on motivation and learning processes offer insights for educators and policymakers. Our research concludes that while positive attitudes, perceptions, and critical use prevail, addressing students’ concerns is crucial for responsible AI integration in higher education.

Merevolusi Pendidikan dengan Kecerdasan Buatan Chatbots: Meningkatkan Pembelajaran dan Penilaian

This study explores the integration of AI chatbots in education to enhance learning and assessment. Focusing on their implementation in classroom teaching and small-scale scientific inquiry activities, the research aims to improve interactions between teachers and students by introducing new learning topics, methods, and providing feedback. The study involved 18 participants 11 fifth-grade and 7 sixth-grade students from a university-run science talent program. Findings highlight benefits such as increased engagement, personalized learning experiences, and automated assessment capabilities. Examples from language learning, mental health support, and academic advising illustrate chatbots' versatility in education. Overall, AI chatbots have the potential to transform education by offering tailored learning experiences, enhancing student engagement, and facilitating efficient assessment. The study suggests further exploration of chatbots' role in promoting student initiative within scientific inquiry learning.

Educational chatbot development informed by clinical simulations

ABSTRACT This manuscript introduces an innovative approach to developing educational chatbots informed by clinical simulations to enhance learning experiences. With the rapid interaction of generative AI in education, this work provides a structured process to creating chatbots that simulate interactions for educational purposes. The four development phases, Conceptualization, Protocol Design, Technical Design, and Trials and Revisions are grounded in the foundational practices of clinical simulations. This approach bridges gaps between theory and practical application of emerging technologies while emphasizing the role of humans at the center of AI-enhanced learning. In addition to technical guidance, pedagogical strategies for introducing chatbots to students are provided. This comprehensive framework can provide educators with tools to create and implement dynamic learning tools to create more personalized and immersive experiences.

Large Language Model‐Based Chatbots in Higher Education

Large language models (LLMs) are artificial intelligence (AI) platforms capable of analyzing and mimicking natural language processing. Leveraging deep learning, LLM capabilities have been advanced significantly, giving rise to generative chatbots such as Generative Pre‐trained Transformer (GPT). GPT‐1 was initially released by OpenAI in 2018. ChatGPT's release in 2022 marked a global record of speed in technology uptake, attracting more than 100 million users in two months. Consequently, the utility of LLMs in fields including engineering, healthcare, and education has been explored. The potential of LLM‐based chatbots in higher education has sparked significant interest and ignited debates. LLMs can offer personalized learning experiences and advance asynchronized learning, potentially revolutionizing higher education, but can also undermine academic integrity. Although concerns regarding AI‐generated output accuracy, the spread of misinformation, propagation of biases, and other legal and ethical issues have not been fully addressed yet, several strategies have been implemented to mitigate these limitations. Here, the development of LLMs, properties of LLM‐based chatbots, and potential applications of LLM‐based chatbots in higher education are discussed. Current challenges and concerns associated with AI‐based learning platforms are outlined. The potentials of LLM‐based chatbot use in the context of learning experiences in higher education settings are explored.

Building and using chatbots in the process of self-studying physics to improve the quality of learners' knowledge

The adoption of chatbots in education is steadily increasing, offering a myriad of benefits to learners engaging in self-directed study. However, the reliability of information provided by chatbots poses certain obstacles, particularly in subjects with high academic content such as physics. This study proposes a five-step process for constructing chatbots, enabling educators to independently develop chatbots to support self-learning among students. This process focuses on enabling chatbots to autonomously respond to physics-related inquiries, a capability often lacking in pre-built chatbots. A new chatbot for physics lessons on the conservation of energy law was developed by applying this methodology. To assess the feasibility and effectiveness of the developed chatbot, we conducted a pedagogical experimental study involving 100 tenth grade students divided into control and experimental groups. To ensure comparability between the groups, students were selected based on their physics grades and teacher feedback. Experimental data was collected through online feedback forms and a 45-minute physics test, processed using statistical techniques. The results indicate a high level of readiness among participants to utilize chatbots for self-learning and acknowledge their beneficial impact. Furthermore, students' knowledge quality improved with chatbot usage, affirming the feasibility and effectiveness of incorporating chatbots into physics education. These findings also validate the proposed five-step chatbot development process as rational and applicable.

Interactions with educational chatbots: the impact of induced emotions and students’ learning motivation

Educational chatbots (EC) have shown their promise in providing instructional support. However, limited studies directly explored the impact of EC on learners’ emotional responses. This study investigated the induced emotions from interacting with micro-learning EC and how they impact learning motivation. In this context, the EC interactions encompassed greetings, biology learning content delivery, self-evaluation, and feedback. This study employed a between-subject experimental design involving 62 college students. Participants were randomly assigned to either the Metacognitive EC group, receiving metacognitive feedback, or the Neutral EC group, receiving neutral feedback. The results of T-tests demonstrated significant differences in specific induced emotions between the two groups while some similarities exist. Importantly, it unveiled that both Metacognitive EC and Neutral EC interactions evoked a spectrum of positive, negative, and ambivalent emotions, in which positive emotions surpassed the induced negative emotions. In general, metacognitive feedback induced fewer negative emotions than neutral feedback. PLS analysis supported the relationships between induced emotions and intrinsic motivation, with positive emotion, ambivalent emotions, and negative emotions influencing interest motivation, which, in turn, shaped other motivational components, including perceived competence, perceived value, and perceived pressure. However, the influence of positive emotion on interest was weaker in the Metacognitive than in the Neutral EC. In conclusion, the study revealed how induced emotions impact motivations and showed that the presence of metacognitive feedback reduced negative emotions and promoted motivation. These findings highlight the need for positive emotion element design and appropriate feedback that will impact learning motivations during educational chatbot interactions.

Understanding AI Chatbot adoption in education: PLS-SEM analysis of user behavior factors

The integration of Artificial Intelligence (AI) into education is a recent development, with chatbots emerging as a noteworthy addition to this transformative landscape. As online learning platforms rapidly advance, students need to adapt swiftly to excel in this dynamic environment. Consequently, understanding the acceptance of chatbots, particularly those employing Large Language Models (LLM) such as Chat Generative Pretrained Transformer (ChatGPT), Google Bard, and other interactive AI technologies, is of paramount importance. Investigating how students accept and view chatbots is essential to directing their incorporation into Industry 4.0 and enabling a smooth transition to Industry 5.0's customized and human-centered methodology. However, existing research on chatbots in education has overlooked key behavior-related aspects, such as Optimism, Innovativeness, Discomfort, Insecurity, Transparency, Ethics, Interaction, Engagement, and Accuracy, creating a significant literature gap. To address this gap, this study employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to investigate the determinant of chatbots adoption in education among students, considering the Technology Readiness Index and Technology Acceptance Model. Utilizing a five-point Likert scale for data collection, we gathered a total of 185 responses, which were analyzed using R-Studio software. We established 12 hypotheses to achieve its objectives. The results showed that Optimism and Innovativeness are positively associated with Perceived Ease of Use and Perceived Usefulness. Conversely, Discomfort and Insecurity negatively impact Perceived Ease of Use, with only Insecurity negatively affecting Perceived Usefulness. Furthermore, Perceived Ease of Use, Perceived Usefulness, Interaction and Engagement, Accuracy, and Responsiveness all significantly contribute to the Intention to Use, whereas Transparency and Ethics have a negative impact on Intention to Use. Finally, Intention to Use mediates the relationships between Interaction, Engagement, Accuracy, Responsiveness, Transparency, Ethics, and Perception of Decision Making. These findings provide insights for future technology designers, elucidating critical user behavior factors influencing chatbots adoption and utilization in educational contexts.

EduChatbot: Implementing educational Chatbot for assisting the teaching-learning process by NLP-based hybrid heuristic adopted deep learning framework

Purpose A new Chatbot system is implemented to provide both voice-based and textual-based communication to address student queries without any delay. Initially, the input texts are gathered from the chat and then the gathered text is fed to pre-processing techniques like tokenization, stemming of words and removal of stop words. Then, the pre-processed data are given to the Natural Learning Process (NLP) for extracting the features, where the XLnet and Bidirectional Encoder Representations from Transformers (BERT) are utilized to extract the features. From these extracted features, the target-based fused feature pools are obtained. Then, the intent detection is carried out to extract the answers related to the user queries via Enhanced 1D-Convolutional Neural Networks with Long Short Term Memory (E1DCNN-LSTM) where the parameters are optimized using Position Averaging of Binary Emperor Penguin Optimizer with Colony Predation Algorithm (PA-BEPOCPA). Finally, the answers are extracted based on the intent of a particular student’s teaching materials like video, image or text. The implementation results are analyzed through different recently developed Chatbot detection models to validate the effectiveness of the newly developed model.Design/methodology/approach A smart model for the NLP is developed to help education-related institutions for an easy way of interaction between students and teachers with high prediction of accurate data for the given query. This research work aims to design a new educational Chatbot to assist the teaching-learning process with the NLP. The input data are gathered from the user through chats and given to the pre-processing stage, where tokenization, steaming of words and removal of stop words are used. The output data from the pre-processing stage is given to the feature extraction phase where XLnet and BERT are used. In this feature extraction, the optimal features are extracted using hybrid PA-BEPOCPA to maximize the correlation coefficient. The features from XLnet and features from BERT were given to target-based features fused pool to produce optimal features. Here, the best features are optimally selected using developed PA-BEPOCPA for maximizing the correlation among coefficients. The output of selected features is given to E1DCNN-LSTM for implementation of educational Chatbot with high accuracy and precision.Findings The investigation result shows that the implemented model achieves maximum accuracy of 57% more than Bidirectional long short-term memory (BiLSTM), 58% more than One Dimansional Convolutional Neural Network (1DCNN), 59% more than LSTM and 62% more than Ensemble for the given dataset.Originality/value The prediction accuracy was high in this proposed deep learning-based educational Chatbot system when compared with various baseline works.