Role of AI chatbots in education: systematic literature review Full Text

The language proficiency of the students aligned with the upper intermediate (B2) and advanced (C1) levels as defined by the Common European Framework of Reference for Languages (CEFR), while some participants were at the native speaker (C2) level. In our study, the primary focus was on evaluating language teacher candidates’ perceptions of AICs in language learning, rather than assessing language learning outcomes. Considering that the majority of participants possessed an upper intermediate (B2-C1) or advanced (C2) proficiency level, the distinction between native and non-native speakers was not deemed a crucial factor for this research.

LL provided a concise overview of the existing literature and formulated the methodology. All three authors collaborated on the selection of the final paper collection and contributed to crafting the conclusion. In the education industry, chatbots can be properly tailored to provide answers to students even before they inquire. AI Chatbots for education make learning more dynamic and lessen a student’s uncertainty about various study areas by providing the answers they need.

Appendix a aconcept map of chatbots in education

Another advantage of the virtual support in the learning medium is that it provides learning modules, exams, and quizzes in the same way that a classroom does, with the added benefit of collecting and submitting these tests to the teachers. These educational applications attract quite a number of users because they are intuitive with a fun user interface that is way better than looking at traditional textbooks. Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly

interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the

most exciting work published in the various research areas of the journal. This combination of features positions ChatBot as a leading choice for businesses looking to enhance their customer service experience while maintaining data integrity and operational efficiency.

This can also be a type of temperature check for any common misunderstandings or concerns among learners. A scripted chatbot, also called a rule-based chatbot, can engage in conversations by following a decision tree that has been mapped out by the chatbot designer, and follow an if/then logic. In contrast, NLP chatbots, which use Artificial Intelligence, make sense of what the person writes and respond accordingly (NLP stands for Natural Language Processing). Based on my initial explorations of the current capabilities and limitations of both types of chatbots, I opted for scripted chatbots. The COVID-19 pandemic pushed educators and students out of their classrooms en masse.

Popular Articles

Table 7 provides a summary of the primary advantages and drawbacks of each AIC, along with their correlation to the items in the CHISM model, which are indicated in parentheses. Natural Conversational Interaction (#7NCI) pertains to the chatbot’s ability to emulate the natural flow and dynamics of human conversation. It involves several key elements, such as maintaining a contextually relevant conversation, understanding and responding appropriately to user inputs, demonstrating empathy, and adapting the language style and tone to suit the learner’s preferences. The goal is to create a conversation that not only provides informative and accurate responses but also engages users in a manner that simulates a human-to-human interaction. None of the AICs reached the desired level of conversational naturalness, as participants found their responses predictable and lacking the adaptability seen in human tutors.

However, Bitrix24’s complex navigation and interface present a steep learning curve, and its support is limited to live chat and email, which might be challenging for users seeking more extensive assistance. Drift’s playbooks create conversational flows that are easy to set up and customize, effectively capturing and qualifying leads. The chatbot’s ability to segment leads and deliver relevant content personalizes each interaction. The chatbot automates routine tasks, freeing up your team to handle more complex issues, and offers 24/7 support to address customer queries promptly.

Intelligent Tutoring Systems are defined as computerized learning environments that incorporate computational models (Graesser et al., 2001) and provide feedback based on learning progress. Educational technologies specifically focused on feedback for help-seekers, comparable to raising hands in the classroom, are Dialogue Systems and Pedagogical Conversational Agents (Lester et al., 1997). These technologies can simulate conversational partners and provide feedback through natural language (McLoughlin and Oliver, 1998). When interacting with students, chatbots have taken various roles such as teaching agents, peer agents, teachable agents, and motivational agents (Chhibber & Law, 2019; Baylor, 2011; Kerry et al., 2008).

This cost-effective approach ensures that educational resources are utilized efficiently, ultimately contributing to more accessible and affordable education for all. Multilingual chatbots act as friendly language ambassadors, breaking down barriers for students from diverse linguistic backgrounds. Their ability to communicate in various languages fosters inclusivity, ensuring that all students can learn and engage effectively, irrespective of their native language. Through this multilingual support, chatbots promote a more interconnected and enriching educational experience for a globally diverse student body.

Receiving less attention than these chatbots, but in many ways equally disruptive (if not more), are specific-purpose AI tools and functionalities that are starting to be embedded into everyday workflows and applications. Also of importance are private LLMs that can securely leverage institutional data for AI-informed insights and actions. This study aims to investigate the effects of ECs for an Instructional Design course that applies team-based project towards learning outcomes, namely learning performance, perception of learning, need for cognition, motivation, creative self-efficacy, and teamwork. Learning performance is defined as the students’ combined scores accumulated from the project-based learning activities in this study.

The first set was what we called “signals” or “changes” that were occurring outside of our campuses. At the time, these signals included technology advancements such as big data, cloud computing, and universal connectivity, along with other changes such as how people consumed information and interacted with technology. Copyright © 2021 Wollny, Schneider, Di Mitri, Weidlich, Rittberger and Drachsler. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Criteria were determined to ensure the studies chosen are relevant to the research question (content, timeline) and maintain a certain level of quality (literature type) and consistency (language, subject area). It’s not just for students; the virtual chat tool can also be used for faculty evaluations. Businesses are transforming their customer interactions with service chatbots which offer efficient, personalized, and innovative experiences. Bitrix24 is a comprehensive solution for ecommerce businesses, offering a wide array of tools, including an online store builder, product lists, and inventory management. Its free plan supports unlimited users and includes a chatbot builder, making it a cost-effective option for businesses of all sizes. HubSpot offers a dynamic and user-friendly AI chatbot software experience, ideal for businesses seeking accessible and affordable customer service solutions.

• Unsurprisingly, most chatbots were web-based, probably because the web-based applications are operating system independent, do not require downloading, installing, or updating.
• Chatbots serve as valuable assistants, optimizing resource allocation in educational institutions.
• Rapid developments in artificial intelligence (AI) represent a significant opportunity to enhance and magnify the effect of Dx projects.
• The solution may be situated in developing code-free chatbots (Luo & Gonda, 2019), especially via MIM (Smutny & Schreiberova, 2020).
• A chatbot lets you cut the wait time and interact with your customers immediately.
• The matching could be done using pattern matching as discussed in (Benotti et al., 2017; Clarizia et al., 2018) or simply by relying on a specific conversational tool such as Dialogflow Footnote 9 as in (Mendez et al., 2020; Lee et al., 2020; Ondáš et al., 2019).

According to Schmulian and Coetzee (2019), there is still scarcity in mobile-based chatbot application in the educational domain, and while ECs in MIM has been gaining momentum, it has not instigated studies to address its implementation. Furthermore, there are also limited studies in strategies that can be used to improvise ECs role as an engaging pedagogical communication agent (Chaves & Gerosa, 2021). Besides, it was stipulated that students’ expectations and the current reality of simplistic bots may not be aligned as Miller (2016) claims that ANI’s limitation has delimited chatbots towards a simplistic menu prompt interaction. Only one study pointed to high usefulness and subjective satisfaction (Lee et al., 2020), while the others reported low to moderate subjective satisfaction (Table 13).

However, the research that emerged from all European universities combined was the highest in the number of articles (19 articles). Asian universities have contributed 10 articles, while American universities contributed 9 articles. Finally, universities from Africa and Australia contributed 4 articles (2 articles each). Only a few studies partially tackled the principles guiding the design of the chatbots. For instance, Martha and Santoso (2019) discussed one aspect of the design (the chatbot’s visual appearance). This study focuses on the conceptual principles that led to the chatbot’s design.

Chatbots powered by artificial intelligence (AI) are an exciting educational development. They can handle various tasks, including but not limited to assisting students, offering information about the institution, aiding employees, being available at all hours, documenting client inquiries, etc. A chatbot powered by artificial intelligence (AI) can perform so many tasks that it may as well be magical. Because of this, users who interact with AI chatbots often report feeling confused and even scared.

• In this section, we present the results of the reviewed articles, focusing on our research questions, particularly with regard to ChatGPT.
• I borrowed the term “proudly artificial” from Lauren Kunze, the CEO of the chatbot platform Pandorabots.
• Later in 2001 ActiveBuddy, Inc. developed the chatbot SmarterChild that operated on instant messaging platforms such as AOL Instant Messenger and MSN Messenger (Hoffer et al., 2001).
• Moreover, it can be a platform to provide standard information such as rubrics, learning resources, and contents (Cunningham-Nelson et al., 2019).
• Winkler and Söllner (2018) reviewed 80 articles to analyze recent trends in educational chatbots.

This kind of availability ensures that learners and educators can access essential information and support whenever they need it, fostering a seamless and uninterrupted learning experience. Chatbots have introduced significant challenges to academic integrity in education. As chatbots become more accessible to everyday users, educators benefits of chatbots in education have expressed concerns about students using them to generate answers to questions on tests and assignments. Because chatbots are designed to understand and produce natural language input, they can respond to questions in ways that make it difficult to distinguish chatbot-generated content from student-generated responses.