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

Only two studies presented a teachable agent, and another two studies presented a motivational agent. Teaching agents gave students tutorials or asked them to watch videos with follow-up discussions. Peer agents allowed students to ask for help on demand, for instance, by looking terms up, while teachable agents initiated the conversation with a simple topic, then asked the students questions to learn. Motivational agents reacted to the students’ learning with various emotions, including empathy and approval. Shows an overview of the platforms the educational chatbots operate on.

Carnegie Mellon University has developed an AI tutor called ALEKS (Assessment and Learning in Knowledge Spaces) that provides personalized learning experiences for students. The purpose of this work was to conduct a systematic review of the educational chatbots to understand their fields of applications, platforms, interaction styles, design principles, empirical evidence, and limitations. Table 10 shows the details of the experiments the surveyed studies had used.

This implementation will ease data collection for reference and networking purposes. Using such models, institutions can engage with graduates, fostering a sense of community. The e-learning showed the need for exceptional support, especially in the wake of COVID-19.

You can use generative AI chatbots to support teaching and learning in many ways. Here we will guide you through exploring various use cases and examples. We also encourage you to access and use chatbots to complete some provided sample tasks. There are dozens of platforms that allow teachers to create free chatbots for specific messaging apps. To make your bot more accessible to students, choose the platform that can connect to several communication channels at once. Snatchbot, for example, can be used on Facebook Messenger, Slack, WeChat, Skype, and it can be easily deployed on the university or school website, by pasting a small code snippet onto the desired page.

Within just eight months of its launch in 2022, it has already amassed over 100 million users, setting new records for user and traffic growth. ChatGPT stands out among AI-powered chatbots used in education due to its advanced natural language processing capabilities and sophisticated language generation, enabling more natural and human-like conversations. It excels at capturing and retaining contextual information throughout interactions, leading to more coherent and contextually relevant conversations. Unlike some educational chatbots that follow predetermined paths or rely on predefined scripts, ChatGPT is capable of engaging in open-ended dialogue and adapting to various user inputs. Much more than a customer service add-on, chatbots in education are revolutionizing communication channels, streamlining inquiries and personalizing the learning experience for users.

Each has some unique characteristics and nuanced differences in how developers built and trained them, though these differences are not significant for our purposes as educators. We encourage you to try accessing these chatbots as you explore their capabilities. Answers to the questions the chatbot can answer can often be found on a school or university website but not with ease. “Those answers are probably on 50 different pages that you’d have to mine through,” Bills says.

How long does it take to build a chatbot? What is the process like?

Chatbot adoption is especially crucial in online classes that include many students where individual support from educators to students is challenging (Winkler & Söllner, 2018). Chatbot interaction is achieved by applying text, speech, graphics, haptics, gestures, and other modes of communication to assist learners in performing educational tasks. From the viewpoint of educators, integrating AI chatbots in education brings significant advantages. Educators can improve their pedagogy by leveraging AI chatbots to augment their instruction and offer personalized support to students. By customizing educational content and generating prompts for open-ended questions aligned with specific learning objectives, teachers can cater to individual student needs and enhance the learning experience. Additionally, educators can use AI chatbots to create tailored learning materials and activities to accommodate students’ unique interests and learning styles.

The data is captured digitally in a format that can be analyzed manually or by using algorithms that can detect themes, patterns, and connections. In effect the teacher can “interact” with and learn from multiple learners at the same time (in theory an infinite number of them). Tutoring, which focuses on skill-building in small groups or one-on-one settings, can benefit learning (Kraft, Schueler, Loeb, & Robinson, 2021).

With BotCopy, you are able to create a free trial for 500 engagements before you have to choose a plan. This will give you time to test it out and find if this is something you want to pay for. Feedback chatbots also chatbot for education afford a more informal, collegial environment for sharing concerns and successes in a course. This can be helpful when asking for feedback about more delicate topics like points of confusion or a sense of belonging.

Personalized learning at scale with the help of chatbots

Exploring the long-term effects, optimal integration strategies, and addressing ethical considerations should take the forefront in research initiatives. The teaching agents presented in the different studies used various approaches. In some cases, the teaching agent started the conversation by asking the students to watch educational videos (Qin et al., 2020) followed by a discussion about the videos. In other cases, the teaching agent started the conversation by asking students to reflect on past learning (Song et al., 2017). Other studies discussed a scenario-based approach to teaching with teaching agents (Latham et al., 2011; D’mello & Graesser, 2013). The teaching agent simply mimics a tutor by presenting scenarios to be discussed with students.

For institutions already familiar with the conversational sales and support landscapes, harnessing the potential of chatbots could catapult their educational services to the next level. Here, you’ll find the benefits, use cases, design principles and best practices for chatbots in the education sector, predominantly for institutions or services focused on B2C interaction. Whether you are just beginning to consider a chatbot for education or are looking to optimize an existing one, this article is for you. It is evident that chatbot technology has a significant impact on overall learning outcomes. Specifically, chatbots have demonstrated significant enhancements in learning achievement, explicit reasoning, and knowledge retention. The integration of chatbots in education offers benefits such as immediate assistance, quick access to information, enhanced learning outcomes, and improved educational experiences.

The integration of artificial intelligence (AI) chatbots in education has the potential to revolutionize how students learn and interact with information. One significant advantage of AI chatbots in education is their ability to provide personalized and engaging learning experiences. By tailoring their interactions to individual students’ needs and preferences, chatbots offer customized feedback and instructional support, ultimately enhancing student engagement and information retention. However, there are potential difficulties in fully replicating the human educator experience with chatbots.

Most researchers (25 articles; 69.44%) developed chatbots that operate on the web (Fig. 5). For example, KEMTbot (Ondáš et al., 2019) is a chatbot system that provides information about the department, its staff, and their offices. Other chatbots acted as intelligent tutoring systems, such as Oscar (Latham et al., 2011), used for teaching computer science topics. Moreover, other web-based chatbots such as EnglishBot (Ruan et al., 2021) help students learn a foreign language.

However, a few participants pointed out that it was sufficient for them to learn with a human partner. Moreover, it has been found that teaching agents use various techniques to engage students. Other teaching agents provide adaptive feedback (Wambsganss et al., 2021). By far, the majority (20; 55.55%) of the presented chatbots play the role of a teaching agent, while 13 studies (36.11%) discussed chatbots that are peer agents. Only two studies used chatbots as teachable agents, and two studies used them as motivational agents. Shows that ten (27.77%) articles presented general-purpose educational chatbots that were used in various educational contexts such as online courses (Song et al., 2017; Benedetto & Cremonesi, 2019; Tegos et al., 2020).

A systematic review follows a rigorous methodology, including predefined search criteria and systematic screening processes, to ensure the inclusion of relevant studies. You can foun additiona information about ai customer service and artificial intelligence and NLP. This comprehensive approach ensures that a wide range of research is considered, minimizing the risk of bias and providing a comprehensive overview of the impact of AI in education. Firstly, we define the research questions and corresponding search strategies and then we filter the search results based on predefined inclusion and exclusion criteria. Secondly, we study selected articles and synthesize results and lastly, we report and discuss the findings. They ensure a more interactive and effective student learning method and alleviate teachers’ workload. From homework assistance and personalized tutoring to administrative tasks and language learning, chatbots can potentially revolutionize the educational landscape.

The more informal environment and gradual, directed questioning via turns of conversation can establish a more personable channel through which to share insights. Users are responsible for how they use the content generated by chatbots when interacting with it. They should ensure that the information they provide and how they use the model aligns with ethical standards and legal obligations. Chatbots’ expertise is based on the training data it has received (although they do have the ability to “learn” with exposure to new information), and they may not possess the depth of knowledge in specialized or niche areas. In such cases, subject matter experts should be consulted for accurate and comprehensive information.

The versatility of chatbots allows for a range of applications in educational services. Adeel Akram, Senior Account Executive for respond.io, highlights the prominent use cases he encountered in the education field. Understanding why chatbots are critical in an educational context is the first step in realizing their value proposition. Roleplay enables users to hone their conversational abilities by engaging with virtual characters. Lerners get the opportunity to simulate diverse scenarios, such as planning future vacations, ordering coffee at a Parisian café, shopping for furniture, or inviting a friend for a hike.

This led to an explosion of chatbots on the platform, enabling tasks like customer support, news delivery, and e-commerce (Holotescu, 2016). Google Duplex, introduced in May 2018, was able to make phone calls and carry out conversations on behalf of users. It showcased the potential of chatbots to handle complex, real-time interactions in a human-like manner (Dinh & Thai, 2018; Kietzmann et al., 2018). While chatbots serve as valuable educational tools, they cannot replace teachers entirely.

Businesses are adopting artificial intelligence and investing more and more in it for automating different business processes like customer support, marketing, sales, customer engagement and overall customer experience. In the context of chatbots for education, effectiveness is commonly measured by the reduction in response times, improvement in student satisfaction scores and the volume of successfully resolved queries. Look for features such as natural language processing, integration capabilities with school databases, scalability, and the ability to handle a wide range of queries. While the benefits of chatbots in education are significant, there are challenges to consider. Before you start designing your chatbot, you need to have a clear understanding of your audience. Understanding your users is vital to designing a chatbot that they will engage with.

Further, none of the articles discussed or assessed a distinct personality of the chatbots though research shows that chatbot personality affects users’ subjective satisfaction. Concerning the evaluation methods used to establish the validity of the approach, slightly more than a third of the chatbots used experiment with mostly significant results. The remaining chatbots were evaluated with evaluation studies (27.77%), questionnaires (27.77%), and focus groups (8.33%). The findings point to improved learning, high usefulness, and subjective satisfaction.

ChatGPT, developed by OpenAI, uses the Generative Pre-training Transformer (GPT) large language model. As of July 2023, it is free to those who sign up for an account using an email address, Google, Microsoft, or Apple account. It’s important to remember that all chatbots are not created equal and can’t do everything. The chatbot is the brainchild of the newly combined professional development mega organization created by the merger of the International Society for Technology in Education and ASCD. Keep up with the developing industry and launch the first chatbot on your school website now!

By asking or responding to a set of questions, the students can learn through repetition as well as accompanying explanations. The chatbot will not tire as students use it repeatedly, and is available as a practice partner at any time of day or night. This affords learners agency to learn at their own pace and through their own content focus. Additionally, chatbots can adapt and modify over time to shape to the learner’s pathway. But, like most powerful technologies, the use of chatbots offers challenges as well as opportunities.

Considering this, the University of Murcia in Spain used an AI chat assistant that successfully addressed more than 38,708 inquiries with an accuracy rate of 91%. For instance, if trainees were absent, the bot could send notes of lectures or essential reminders, to keep them informed while they’re not present. This efficiency contributes to a more enriching learning experience, consequently attracting more students.

Chatbots emerge as crucial tools for efficiently managing inquiries and standing out in the competitive field », he added. For education services looking to expand their reach and enrollments, chatbots are effective lead generators. By handling inquiries and routing promising leads to human reps, chatbots streamline the admissions process and boost conversion rates. According to the survey conducted among 1,000 secondary school attendees, 67% of learners admitted using AI tools. What’s more interesting is that 42% of those surveyed apply this technology in math, while 41% use it for writing essays. Ivy Tech Community College in Indiana developed a machine learning algorithm to identify at-risk students.

By taking over these tasks, chatbots will allow teachers to concentrate on establishing a stronger relationship with students. They will have the opportunity to provide them with personal guidance and enhance the curriculum with their own research interests. This way, teachers will also be able to provide better-quality mentorship. Consequently, this will be especially helpful for students with learning disabilities. With its human-like writing abilities and OpenAI’s other recent release, DALL-E 2, it generates images on demand and uses large language models trained on huge amounts of data. The same is true of rivals such as Claude from Anthropic and Bard from Google.

Dr. Miller served for fifteen years at the US Food and Drug Administration (FDA) in a number of posts, including as the founding director of the Office of Biotechnology. However, like most powerful technologies, the use of chatbots offers challenges and opportunities. We discuss strategies to minimize the former and accentuate the latter. Users should prioritize the privacy and data protection of individuals when using chatbots. They should avoid sharing sensitive personal information and refrain from using the model to extract or manipulate personal data without proper consent. Here, we discuss some of the advantages, opportunities, and challenges of chatbots in primary, secondary, and higher education.

• Recently, chatbots have been utilized in various fields (Ramesh et al., 2017).
• Through intelligent tutoring systems, these models analyze responses, learning patterns, and overall performance, fostering tailored teaching.
• It has been scientifically proven that not everyone understands and learns in the same way.
• This platform uses AI to personalize the learning experience for each student.

Considering Microsoft’s extensive integration efforts of ChatGPT into its products (Rudolph et al., 2023; Warren, 2023), it is likely that ChatGPT will become widespread soon. Educational institutions may need to rapidly adapt their policies and practices to guide and support students in using educational chatbots safely and constructively manner (Baidoo-Anu & Owusu Ansah, 2023). Educators and researchers must continue to explore the potential benefits and limitations of this technology to fully realize its potential. Existing literature review studies attempted to summarize current efforts to apply chatbot technology in education. For example, Winkler and Söllner (2018) focused on chatbots used for improving learning outcomes. On the other hand, Cunningham-Nelson et al. (2019) discussed how chatbots could be applied to enhance the student’s learning experience.

Juji automatically aggregates and analyzes demographics data and visualizes the summary. So you can get a quick glance on where users came from and when they interacted with the chatbot. Use Juji API to integrate a chatbot with an learning platform or a learning app. I should clarify that d.bot — named after its home base, the d.school — is just one member of my bottery (‘bottery’ is a neologism to refer to a group of bots, like a pack of wolves, or a flock of birds). Over the past year I’ve designed several chatbots that serve different purposes and also have different voices and personalities. Carlson, from the Lansing School District, was not overly familiar with AI technology before her district started working with AllHere, but she says chatbots are more common in our lives than we realize — think Siri and Alexa.

So I’m currently working on what I call a “cobot” — a hybrid between a rule-based and an NLP bot chatbot — that can collaborate with humans when they need it and as they pursue their own goals. You can picture it as a sidekick in your pocket, one that has been trained at the d.school, has “learned” a large number of design methods, and is always available to offer its knowledge to you. In addition, the responses of the learner not only determine the chatbot’s responses, but provide data for the teacher to get to know the learner better. This allows the teacher to tweak the chatbot’s design to improve the experience.

The approach authors use often relies on a general knowledge base not tied to a specific field. Hobert and Meyer von Wolff (2019), Pérez et al. (2020), and Hwang and Chang (2021) examined the evaluation methods used to assess the effectiveness of educational chatbots. The authors identified that several evaluation methods such as surveys, experiments, and evaluation studies measure acceptance, motivation, and usability. Chatbots have been utilized in education as conversational pedagogical agents since the early 1970s (Laurillard, 2013).

While chatting with bots, students will have the chance to explain their claims. On the other hand, the bot can be trained to ask additional questions based on their previous answers. Education chatbots are interactive artificial intelligence (AI) applications utilized by EdTech companies, universities, schools, and other educational institutions. They serve as virtual assistants, aiding in student instruction, paper assessments, data retrieval for both students and alumni, curriculum updates, and coordinating admission processes.

Institutional staff, especially teachers, are often overburdened and exhausted, working beyond their office hours just to deliver excellent learning experiences to their students. Repetitive tasks can easily be carried out using chatbots as teachers’ assistants. With artificial intelligence, chatbots can assist teachers in justifying their work without exhausting them too much. This, in turn, allows https://chat.openai.com/ teachers to devote more time and attention to designing exciting lessons and providing learners with the personalized attention they deserve. AI chatbots equipped with sentiment analysis capabilities can play a pivotal role in assisting teachers. By comprehending student sentiments, these chatbots help educators modify and enhance their teaching practices, creating better learning experiences.

Here chatbots play an important role, as they can track progress, ensuring continuous interaction through personalized content and suggestions. Since pupils seek dynamic learning opportunities, such tools facilitate student engagement by imitating social media and instant messaging channels. One of the significant advantages of chatbots in education industry is their ability to offer immediate feedback. This quick response mechanism is capable of asking about specific aspects of the session or course. Such programs gather comments on various subjects like study material, teaching approaches, assignments, and more.

As technology continues to evolve, we can expect even more innovative and impactful education chatbot examples in the future. If you would like more visual formatting and branding control, you can add a third party tool such as BotCopy. BotCopy has some cost per engagement, depending on which plan is chosen.

• Today, technologies like conversational AI and natural language processing (NLP) continue to help educators and students world over teach and learn better.
• Other chatbots acted as intelligent tutoring systems, such as Oscar (Latham et al., 2011), used for teaching computer science topics.
• The Explain My Answer option provides learners with an opportunity to delve deeper into their responses.
• We also discussed and clarified all doubts and gray areas after analyzing each selected article.
• Likewise, bots can collect inputs from all involved participants after each interaction or event.
• We offer this activity for you to self-assess and reflect on what you learned in this module.

Navigating the expansive world of educational chatbots reveals a realm where technology meets academia, fostering student engagement, and offering support. These AI-driven programs, tailored for educational settings, aim to provide enriched learning experiences. It’s incredible, but chatbots have been used in education since the early 1970s. In terms of application, chatbots Chat PG are primarily used in education to teach various subjects, including but not limited to mathematics, computer science, foreign languages, and engineering. While many chatbots follow predetermined conversational paths, some employ personalized learning approaches tailored to individual student needs, incorporating experiential and collaborative learning principles.

In recent years, chatbots have emerged as powerful tools in various industries, including education. By leveraging artificial intelligence development solutions, they are transforming the way students learn and interact with educational content.educational content. None of the articles explicitly relied on usability heuristics and guidelines in designing the chatbots, though some authors stressed a few usability principles such as consistency and subjective satisfaction.

If you are ready to explore chatbots’ potential in the education sector, consider trying respond.io, a platform that revolutionizes customer communication. Education businesses like E4CC, Qobolak and CUHK have already seen success with respond.io. Developing a chatbot for educational services is as much about the frontend design as it is about the backend logic. By answering prospective students’ queries on courses, admissions, and the application process, chatbots simplify and speed up the enrolment process. “With many institutions offering similar programs, such as the numerous universities in Malaysia presenting executive MBAs (Master of Business Administration), acquiring customers becomes a challenge.

Sign in to a Microsoft Edge account to allow longer conversations with Bing Chat. The process of organizing your knowledge, teaching it to someone, and responding to that person reinforces your own learning on that topic (Carey, 2015). You can incorporate this technique into your course in a number of ways. Note that AI chatbots can serve as a convenient stand-in for a student.

This article on Chatbots Magazine, written by the creators of Hubert, has pointed out six ways how Artificial Intelligence and chatbots can improve education, and we will list the three most important ones. Today, there are many similar partnerships between corporations and educational institutions that try to make the institutional learning transparent and more efficient. In 2016, Bill Gates has announced that the Bill and Melissa Gates Foundation will invest more than $240 million dollars in a tech project.

Additionally, Wollny et al. (2021) argued that educational chatbots make education more available and easily accessible. Nonetheless, the existing review studies have not concentrated on the chatbot interaction type and style, the principles used to design the chatbots, and the evidence for using chatbots in an educational setting. When you think of advancements in technology, edtech might not be the first thing that pops into your head. But during the COVID-19 pandemic, edtech became a true lifeline for education by making it accessible and easy to use despite there being numerous physical restrictions. Today, technologies like conversational AI and natural language processing (NLP) continue to help educators and students world over teach and learn better. Believe it or not, the education sector is now among the top users of chatbots and other smart AI tools like ChatGPT.

Pounce provides various essential functions, including sending reminders, furnishing relevant enrollment details, gathering survey data, and delivering round-the-clock support. The primary objective behind Pounce’s introduction was to streamline the admission process. Georgia State University has effectively implemented a personalized communication system. They introduced Pounce, a bespoke smart assistant created to actively engage admitted students. While AI models offer numerous benefits, these limitations highlight the importance of continuous improvements.

For example, instead of asking « How do I write a course syllabus? », you might instead say “I am a university instructor developing a new introductory course on genetics. Can you assist me in developing a useful and clear syllabus for first-year students? Bard, a generative AI chatbot developed by Google, relies on the Pathways Language Model (PaLM) large language model. If you’d like to access this tool, please use your personal Google Account. While many different chatbots and LLMs exist, we choose to highlight four prominent chatbots currently available for free.

Two recent articles in the journal Nature described its application to weather forecasting. While using questionnaires as an evaluation method, the studies identified high subjective satisfaction, usefulness, and perceived usability. The questionnaires used mostly Likert scale closed-ended questions, but a few questionnaires also used open-ended questions. Concerning the platform, chatbots can be deployed via messaging apps such as Telegram, Facebook Messenger, and Slack (Car et al., 2020), standalone web or phone applications, or integrated into smart devices such as television sets.

This constant accessibility allows learners to seek support, access resources, and engage in activities at their convenience. There’s a lot of fascinating research in the area of human-robot collaboration and human-robot teams. The ability to transfer skills and knowledge that you learned to a new situation involves abstract thinking, problem-solving, and self-awareness.

AI implementation caters to inquiries promptly, providing instant solutions. Supplying robust aid through digital tools enhances the institution’s reputation, especially in the rapidly growing e-learning market. Overloaded due to tight scheduling and plenty of daily duties, educators often face challenges.