Interacting with educational chatbots: A systematic review Education and Information Technologies

AI and chatbots have a huge potential to transform the way students interact with learning. They promise to forever change the learning landscape by offering highly personalized experiences for students through tailored lessons. With a one-time investment, educators can leverage a self-improving algorithm to design online courses and study resources that go beyond the one-size-fits-all approach, dismantling the age-old education structures. Chatbots will be virtual assistants that offer instant help and answer questions whenever students get stuck understanding a concept.

Striking a balance between these advantages and concerns is crucial for responsible integration in education. To summarize, the journey through educational chatbots has uncovered a field of possibilities. These AI tools amplify engagement, offer personalized content, and ensure uninterrupted support.

By reminding students to repeat their learning at spaced intervals, chatbots can help cement the lesson in their minds and improve long-term retention. The availability of distance learning and online courses means that people can learn alongside working and don’t have to commute long distances or take a break from family life to learn new skills. This growth demands that educational institutions offering online learning provide excellent student support alongside it. Queries before, during, and after enrollments must be received efficiently and solved instantly. Chatbots for education deliver intelligent support and provide on-the-spot-solutions to alleviate doubts, provide additional information and strengthen the relationship between students and the institution.

The future of AI and chatbots in education

It’s not easy for an instructor to resolve doubts and engage with every student during lectures. You can combine the power of chatbots with a Higher Education CRM (Customer Relationship Management) that can set up robust automations to nudge a student to complete their applications. Bots can handle a wide array of admission-related tasks, from answering admission queries, explaining the admission process, and assisting with form fill-up to sorting and managing the received application data. AI chatbots can further assist in circulating personalized assignments, class updates, reminders, and gathering feedback, ensuring smooth class management.

Only four chatbots (11.11%) used a user-driven style where the user was in control of the conversation. A user-driven interaction was mainly utilized for chatbots teaching a foreign language. In terms of the educational role, slightly more than half of the studies used teaching agents, while 13 studies (36.11%) used peer agents. 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.

These use cases will provide an understanding of how the theoretical constructs of AI chatbots transition into practical scenarios, ultimately helping to realize the tremendous potential they carry. Therefore, the readily available support channels ensure that users have a reliable backup in case of any hindrances, thereby ensuring a smooth and consistent user experience. Their ability to emulate human-like conversation further increases student interaction and engagement. Since it can understand the context of a conversation, it can better replicate a human-like interaction, making the learning session more engaging for the students. By analyzing individual learning data, AI chatbots can create a unique learning path for each student, thereby promoting a highly customized and adaptive learning environment. This blog post focuses on the transformative influence of AI chatbots in the educational landscape.

Chatbot for Education: Benefits, Challenges and Opportunities

Finally, it is crucial to choose a chatbot solution that provides AI capabilities. An AI-powered https://chat.openai.com/ can adapt and learn from user interactions, ensuring every conversation becomes more meaningful and personalized over time. This is a significant advantage as institutions can better meet the needs of students, faculty, and staff. In today’s fast-paced education environment, students and faculty alike demand instant access to information, resources, and assistance. An educational institution chatbot can provide just that, offering 24/7 support to both groups.

For example, the authors in (Fryer et al., 2017) used Cleverbot, a chatbot designed to learn from its past conversations with humans. User-driven chatbots fit language learning as students may benefit from an unguided conversation. The authors in (Ruan et al., 2021) used a similar approach where students freely speak a foreign language.

AI chatbots, with their interactive and personalized nature, significantly boost student engagement. Moreover, these chatbots are operational 24/7, ensuring that students, teachers, or parents can receive necessary information or assistance anytime they require. Conversational AI is revolutionizing the way businesses communicate with their customers and everyone is loving this new way. 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.

Intelligent chatbots for learning institutions may also pave the way for the development of intelligent tutoring systems, which can provide targeted and adaptive feedback to students. This can promote self-directed learning and enhance the overall learning experience. Furthermore, chatbots can support the development of skills that are increasingly important in today’s digital economy, such as critical thinking, collaboration, and problem-solving.

Considering this section, platforms or channels where chatbot dialogues take place play a significant role in creating a user-friendly, intuitive, and accessible interface for users to interact with the chatbot. Moreover, bots’ immediate doubt resolution and personalized attention maintain an engaging and adaptive learning atmosphere for students. Moreover, with continuous student interaction, the machine learning model continually improves, making the bot smarter and more efficient. Therefore, the feedback provided is highly personalized and pertinent to the student’s learning track.

• Zoomers grow up on smartphones and tablets, so technology is integral to all aspects of learning, from creating and delivering course materials to how these materials are absorbed and memorized.
• A few other subjects were targeted by the educational chatbots, such as engineering (Mendez et al., 2020), religious education (Alobaidi et al., 2013), psychology (Hayashi, 2013), and mathematics (Rodrigo et al., 2012).
• EdWeek reports that, according to Impact Research, nearly 50% of teachers utilized ChatGPT for lesson planning and generated creative ideas for their classes.
• It is also essential to ensure that confidential data is encrypted for added security.

By employing NLP, an AI chatbot can effectively analyze and understand the user’s input, thereby generating appropriate and relevant responses. Educational institutions found AI a perfect ally in a domain where personalization and active engagement are pivotal. AI and machine learning have Chat PG seen a surge in usage across various sectors, with a notable impact on education. Understanding student sentiments during and after the sessions is very important for teachers. If students end up being confused and unclear about the topic, all the efforts made by the teachers go in vain.

What are educational chatbots?

Believe it or not, the education sector is now among the top users of chatbots and other smart AI tools like ChatGPT. While the identified limitations are relevant, this study identifies limitations from other perspectives such as the design of the chatbots and the student experience with the educational chatbots. To sum up, Table 2 shows some gaps that this study aims at bridging to reflect on educational chatbots in the literature. Educational chatbots are computer programs powered by state-of-the-art generative AI technology. They can simulate human-like conversations and provide detailed answers on a wide range of topics. Besides, a chatbot for education acts as a virtual assistant to help teachers and students perform various tasks with ease.

Testing can involve manual and user testing, in which students and faculty provide feedback on their experience with the chatbot. Refining the chatbot based on user feedback and data analysis can help improve its effectiveness and user satisfaction. By automating routine tasks and inquiries, institutions can allocate resources to more complex issues and support students and faculty more effectively.

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. While they can provide customized instruction, chatbots may not match human instructors’ emotional support and mentorship. Understanding the importance of human engagement and expertise in education is crucial. They offer students guidance, motivation, and emotional support—elements that AI cannot completely replicate. Overall, the impact of AI chatbots on the educational landscape is transformative.

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). In the future, we will see more innovative applications of a chatbot for education.

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. Pérez et al. (2020) identified various technologies used to implement chatbots such as Dialogflow Footnote 4, FreeLing (Padró and Stanilovsky, 2012), and ChatFuel Footnote 5. The study investigated the effect of the technologies used on performance and quality of chatbots. The chatbot should reflect the institution’s values and brand and be designed to communicate in a way that resonates with the target audience.

User-driven conversations are powered by AI and thus allow for a flexible dialogue as the user chooses the types of questions they ask and thus can deviate from the chatbot’s script. One-way user-driven chatbots use machine learning to understand what the user is saying (Dutta, 2017), and the responses are selected from a set of premade answers. You can foun additiona information about ai customer service and artificial intelligence and NLP. In contrast, two-way user-driven chatbots build accurate answers word by word to users (Winkler & Söllner, 2018). Such chatbots can learn from previous user input in similar contexts (De Angeli & Brahnam, 2008). AI chatbots can personalize the support experience for each user based on their unique preferences and behavior.

It is vital to ensure that chatbots prioritize student welfare and promote inclusivity and diversity. Let’s look at how Georgia State uses higher education chatbots to personalize student communication at scale. Pounce was designed to help students by sending timely reminders and relevant information about enrollment tasks, collecting key survey data, and instantly resolving student inquiries on around the clock. As Conversational AI and Generative AI continue to advance, chatbots in education will become even more intuitive and interactive. They will play an increasingly vital role in personalized learning, adapting to individual student preferences and learning styles. Moreover, chatbots will foster seamless communication between educators, students, and parents, promoting better engagement and learning outcomes.

When the user provides answers compatible with the flow, the interaction feels smooth. Capacity is an AI-powered support automation platform that offers a low-code platform accessible through conversational AI. It connects your entire tech stack to provide answers to questions, automate repetitive support tasks, and build solutions to any business challenge. Once the chatbot is developed, it must be tested thoroughly to identify and address any issues or errors.

The team can then take data-driven decisions by identifying trends, optimizing recruitment strategies, and allocating resources effectively. And although the chatbot might be communicating at scale, for a student it feels like the chatbot is especially there to help him move along the admissions journey. This personalized approach enhances the overall user experience and fosters a stronger connection with potential students. In this article, we discuss how you can leverage chatbots to improve university enrollments, automate administrative tasks, and personalize student interactions. AI chatbot’s data analytics capabilities allow teachers to monitor students’ progress closely. Teachers can get in-depth insights about each student’s strengths, weaknesses, learning pace, and areas of struggle, enabling them to adjust teaching methods, study materials and exercise difficulty accordingly.

However, this situation presents a unique opportunity, accompanied by unprecedented challenges. Consequently, it has prompted a significant surge in research, aiming to explore the impact of chatbots on education. For these and other geopolitical reasons, ChatGPT is banned in countries with strict internet censorship policies, like North Korea, Iran, Syria, Russia, and China.

AI aids researchers in developing systems that can collect student feedback by measuring how much students are able to understand the study material and be attentive during a study session. The way AI technology is booming in every sphere of life, the day when chatbot for educational institutions quality education will be more easily accessible is not far. By leveraging this valuable feedback, teachers can continuously improve their teaching methods, ensuring that students grasp concepts effectively and ultimately succeed in their academic pursuits.

This method encourages students to ask questions and actively participate in processes comfortably. As a result, it significantly increases concentration level and comprehensive understanding. Educational chatbots serve as personal assistants, offering individual guidance to everyone. Through intelligent tutoring systems, these models analyze responses, learning patterns, and overall performance, fostering tailored teaching. Bots are particularly beneficial for neurodivergent people, as they address individual comprehension disabilities and adapt study plans accordingly. In the fast-paced educational environment, providing instant assistance is crucial.

In comparison, chatbots used to teach languages received less attention from the community (6 articles; 16.66%;). Interestingly, researchers used a variety of interactive media such as voice (Ayedoun et al., 2017; Ruan et al., 2021), video (Griol et al., 2014), and speech recognition (Ayedoun et al., 2017; Ruan et al., 2019). 3 is more than 36 (the number of selected articles) as the authors of a single article could work in institutions located in different countries. The vast majority of selected articles were written or co-written by researchers from American universities. 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.

This proactive chatbot not only answers queries but engages users by providing advice and resources and encouraging the exploration of interests and opportunities. It showcases AI chatbots’ potential in navigating diverse educational needs and tasks, ultimately contributing to a more dynamic, personalized, efficient, and immersive educational experience. With AI chatbots, the tutoring process has become more focused, personalized, and flexible, reshaping the educational tutoring landscape. A prominent advantage of educational chatbots is their one-to-one tutoring capacity. This personalized learning journey leads to improved comprehension, increased motivation, reduced learning anxiety, and overall improved learning experience. Some studies mentioned limitations such as inadequate or insufficient dataset training, lack of user-centered design, students losing interest in the chatbot over time, and some distractions.

AI-powered chatbots are designed to mimic human conversation using text or voice interaction, providing information in a conversational manner. Chatbots’ history dates back to the 1960s and over the decades chatbots have evolved significantly, driven by advancements in technology and the growing demand for automated communication systems. Created by Joseph Weizenbaum at MIT in 1966, ELIZA was one of the earliest chatbot programs (Weizenbaum, 1966). Another early example of a chatbot was PARRY, implemented in 1972 by psychiatrist Kenneth Colby at Stanford University (Colby, 1981). It engaged in text-based conversations and demonstrated the ability to exhibit delusional behavior, offering insights into natural language processing and AI.

• By offering immediate assistance, chatbots can ensure that students do not fall behind in their courses due to unanswered questions or concerns.
• It can assist in tutoring, evaluate a student’s proficiency in a subject, provide remedial actions, and offer personalized feedback.
• Only two studies used chatbots as teachable agents, and two studies used them as motivational agents.

This AI chatbot for higher education addresses inquiries about various aspects from the admission process to daily academic life. These range from guidance on bike parking or locating specific classrooms to offering support during times of loneliness or illness. Cara also provides insights into what’s bugging students and helps them engage with the university.

Additionally, tutoring chatbots provide personalized learning experiences, attracting more applicants to educational institutions. Moreover, they contribute to higher learner retention rates, thereby amplifying the success of establishments. Educational chatbot software has the potential to significantly impact student success. By providing personalized learning paths and constant feedback, chatbots can improve student engagement and motivation while also addressing individual needs and learning styles.

In today’s digitally driven world, technological advancements continue to reshape various industries, and higher education is no exception. The initiative underscores the Cabinet Office’s commitment to leveraging AI for accessible and equal educational opportunities. Coupling these tasks with the AI chatbot’s round-the-clock availability, the overall efficiency and effectiveness of the admission process remarkably increase. The bots serve as an enabler, aiding teachers in the challenging task of imparting education.

Examples include Georgia Tech’s adaptive learning platform and Stanford’s Artificial Intelligence Lab. Conversational AI is also making its mark, with chatbots becoming commonplace on online platforms to create interactive and engaging learning experiences. Zoomers grow up on smartphones and tablets, so technology is integral to all aspects of learning, from creating and delivering course materials to how these materials are absorbed and memorized. CSUNny was and is monitored by humans and can direct students to those humans to answer questions it cannot. But one special power of chatbots seems to be that they’re close enough to human to forge a bond with students, yet not human enough to make them uncomfortable. Furthermore, chatbots can help create adaptive assessments that adjust to a student’s level of understanding.