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

The is one of the top chatbot platforms that was awarded the Loebner Prize five times, more than any other program. You can use the mobile invitations to create mobile-specific rules, customize design, and features. The chatbot platform comes with an SDK tool to put chats on iOS and Android apps. It’s straightforward to use so you can customize your bot to your website’s needs. You can design pre-configured workflows, business FAQs, and other conversation paths quickly with no programming knowledge.

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. Once the chatbot is developed, it must be tested thoroughly to identify and address any issues or errors.

Similar articles

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. 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). 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. Let’s look at how Georgia State uses higher education chatbots to personalize student communication at scale.

They can be used for self-quizzing to reinforce knowledge and prepare for exams. Furthermore, these chatbots facilitate flexible personalized learning, tailoring their teaching strategies to suit each student’s unique needs. Their interactive and conversational nature enhances student engagement and motivation, making learning more enjoyable and personalized. Overall, students appreciate the capabilities of AI chatbots and find them helpful for their studies and skill development, recognizing that they complement human intelligence rather than replace it. As technology continues to advance, AI-powered educational chatbots are expected to become more sophisticated, providing accurate information and offering even more individualized and engaging learning experiences.

The choice of Spain and the Czech Republic was primarily based on convenience sampling. The two researchers involved in this study are also lecturers at universities in these respective countries, which facilitated access to a suitable participant pool. Additionally, the decision to include these two different educational settings aimed to test the applicability and effectiveness of AICs across varied contexts.

Interactive learning chatbots can offer quizzes, exercises, and educational games, providing an engaging learning environment. This paper will help to better understand how educational chatbots can be effectively utilized to enhance education and address the specific needs and challenges of students and educators. 7, most of the articles (88.88%) used the chatbot-driven interaction style where the chatbot controls the conversation. 52.77% of the articles used flow-based chatbots where the user had to follow a specific learning path predetermined by the chatbot. Notable examples are explained in (Rodrigo et al., 2012; Griol et al., 2014), where the authors presented a chatbot that asks students questions and provides them with options to choose from. Other authors, such as (Daud et al., 2020), used a slightly different approach where the chatbot guides the learners to select the topic they would like to learn.

It engaged in text-based conversations and demonstrated the ability to exhibit delusional behavior, offering insights into natural language processing and AI. 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). SmarterChild was a chatbot that could carry on conversations with users about a variety of topics.

In comparison, the authors in (Tegos et al., 2020) rely on a slightly different approach where the students chat together about a specific programming concept. The chatbot intervenes to evoke curiosity or draw students’ attention to an interesting, related idea. These bots engage students in real-time conversations to support their learning process. They can simulate a classroom experience, delivering personalized learning content, and adapting to individual student needs.

Striking a balance between these advantages and concerns is crucial for responsible integration in education. 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.

Using previous interactions, the bots can also be trained to run guided conversations. All in all, key pillars of AI chatbots include natural language processing, interactive platforms, and accessible support channels. SchoolMessenger is an online education communication platform with a large user base. It designed an AI chatbot that allows parents to get information about their child’s attendance, schedules, or academic progress.

Chatbots for education work collaboratively with teachers, optimizing the online learning process and creating an enriched educational ecosystem. AI chatbots offer a multitude of applications in education, transforming the learning experience. They can act as virtual tutors, providing personalized learning paths and assisting students with queries on academic subjects. Additionally, chatbots streamline chatbot for educational institutions administrative tasks, such as admissions and enrollment processes, automating repetitive tasks and reducing response times for improved efficiency. With the integration of Conversational AI and Generative AI, chatbots enhance communication, offer 24/7 support, and cater to the unique needs of each student. Chatbots can help educational institutions in data collection and analysis in various ways.

Participants and context

Read till the end and witness how companies, including Duolingo, leverage innovative technology to make learning accessible to everyone. So, it is better to design and prioritize the chatbot for education accordingly. Including friendly conversations and entering, related questions will help receive better feedback and work for the desired results. As an example of an evaluation study, the researchers in (Ruan et al., 2019) assessed students’ reactions and behavior while using ‘BookBuddy,’ a chatbot that helps students read books. The researchers recorded the facial expressions of the participants using webcams.

The research highlights the critical link between student engagement and academic achievement, emphasizing the importance of a positive connection to learning. The exponential growth of distance and online courses has made it easier to study alongside work commitments, eliminating the need for long commutes or family interruptions. Read on to learn about the benefits of using chatbots for the education industry. After all, you’ve got to wrap your head around not only chatbot apps or builders but also social messaging platforms, chatbot analytics, and Natural Language Processing (NLP) or Machine Learning (ML). This no-code chatbot platform helps you with qualified lead generation by deploying a bot, asking questions, and automatically passing the lead to the sales team for a follow-up. Drift is the best AI platform for B2B businesses that can engage customers by conversational marketing.

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. 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. Promptly addressing students’ doubts and concerns, chatbots enable teachers to provide immediate clarifications, fostering a more conducive and effective learning environment.

The future of AI and chatbots in education

It uses natural language processing (NLP) technology to break down the sentences into smaller components understandable for machines. This way, the system can analyze the meaning of the input and generate responses. The software also uses machine learning to recognize previously analyzed patterns and learn over time. This AI chatbot can support extended messaging sessions, allowing customers to continue conversations over time without losing context.

• In 2019, the education industry was among the top five industries profiting from chatbots, highlighting its proactive approach to technology adoption and its transformative impact on education.
• The future of chatbots in education is optimistic, driven by current trends such as natural language processing and machine learning capabilities in advanced tools such as ChatBot.
• Using such models, institutions can engage with graduates, fostering a sense of community.
• A notable example of a study using questionnaires is ‘Rexy,’ a configurable educational chatbot discussed in (Benedetto & Cremonesi, 2019).
• By digitizing enrollment processes and simplifying communication channels, bots reduce the workload for staff.

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). Many brands are successfully using AI chatbots for education in course examinations and assessments. However, these tests require regular syllabus updates to maintain the course’ quality and standards. Keeping your students engaged is the only way to make your students trust and follow you. Students these days look for several courses before going for one and so it is essential to provide them with the best. Even if you are providing the best quality education, they need regular interaction and activities to keep them engaged and tied with the institute.

Cost savings achieved through chatbot-assisted tasks

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. In this section, we present the results of the reviewed articles, focusing on our research questions, particularly with regard to ChatGPT. ChatGPT, as one of the latest AI-powered chatbots, has gained significant attention for its potential applications in education. You can foun additiona information about ai customer service and artificial intelligence and NLP. 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.

An intuitive and user-friendly interface enriches the overall user experience and encourages interaction (Chocarro et al., 2021; Yang, 2022). Additionally, the incorporation of engaging multimedia content, including videos, images, and other emerging technologies, can also increase users‘ attention and engagement (Jang et al., 2021; Kim et al., 2019). 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. The students found the tool helpful and efficient, albeit they wanted more features such as more information about courses and departments. In comparison, 88% of the students in (Daud et al., 2020) found the tool highly useful.

This study, however, uses different classifications (e.g., “teaching agent”, “peer agent”, “motivational agent”) supported by the literature in Chhibber and Law (2019), Baylor (2011), and Kerlyl et al. (2006). Other studies such as (Okonkwo and Ade-Ibijola, 2021; Pérez et al., 2020) partially covered this dimension by mentioning that chatbots can be teaching or service-oriented. The chatbot used pattern matching to emulate a psychotherapist conversing with a human patient.

Using the chatbot has helped us capture more leads, engage more users, and communicate more effectively. Educational bots leverage the power of generative AI to provide comprehensive responses on a range of topics. You can ask any kind of question, moderate your input, and get detailed answers instantly. Roleplay enables users to hone their conversational abilities by engaging with virtual characters.

Educational chatbots are conversational bots with specialized training, which educational institutions and companies specifically use for the client and student interaction. The AI chatbot for education is transforming the way Ed-tech companies and institutions are sharing necessary information and leading conversations. For the interaction, detailed instructions were provided via Moodle, with the aim not to measure the participants’ English learning progress, but to enable critical analysis of each AIC as future educators. This assessment was aligned with the CHISM scale, which was completed in a post-survey. A minimum interaction of three hours per week with each AIC, or 48 h over a month across all AICs, was requested from each participant. Some studies have emphasized that interactions with AICs can seem detached and lack the human element (Rapp et al., 2021).

This can help you use it to its full potential when making, deploying, and utilizing the bot. Its Product Recommendation Quiz is used by Shopify on the official Shopify Hardware store. It is also GDPR & CCPA compliant to ensure you provide visitors with choice on their data collection.

Using such models, institutions can engage with graduates, fostering a sense of community. 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. Digital assistants address queries and exchange information regarding lectures, assignments, or events. Furthermore, institutions leveraging chatbots witness higher conversion rates, thereby contributing to overall success.

Chatbots, also known as conversational agents, enable the interaction of humans with computers through natural language, by applying the technology of natural language processing (NLP) (Bradeško & Mladenić, 2012). In fact, the size of the chatbot market worldwide is expected to be 1.23 billion dollars in 2025 (Kaczorowska-Spychalska, 2019). In the US alone, the chatbot industry was valued at 113 million US dollars and is expected to reach 994.5 million US dollars in 2024 Footnote 1. Chatbots can assist student support services teams by providing instant responses to frequently asked questions. 57% of people expect the same response times during business and non-business hours.

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. In terms of the medium of interaction, chatbots can be text-based, voice-based, and embodied.

Once you start a conversation with the system, it will remember the topic and use the previous messages for context. You can also store chats on the left-hand side of the screen and jump between them or share a particularly interesting conversation with others. Unlike ChatGPT, Jasper pulls knowledge straight from Google to ensure that it provides you the most accurate information.

Among them, ChatGPT and Google Bard are among the most profound AI-powered chatbots. It was first announced in November 2022 and is available to the general public. ChatGPT’s rival Google Bard chatbot, developed by Google AI, was first announced in May 2023. Both Google Bard and ChatGPT are sizable language model chatbots that undergo training on extensive datasets of text and code. They possess the ability to generate text, create diverse creative content, and provide informative answers to questions, although their accuracy may not always be perfect.

For instance, Mondly’s reliance on pre-programmed responses and Buddy.ai’s focus on repetitive drills for children limit dynamic conversation, resulting in lower satisfaction in maintaining contextually relevant dialogues. Although Andy scores slightly higher, it still reveals a need for more adaptable conversation styles for advanced learners. The satisfaction levels in the LEX dimension may also depend on the chatbots‘ design relative to students‘ levels, with significant differences observed among the four AICs.

This data can be used to improve marketing strategies, enhance products or services, and make informed business decisions. Meritto’ Integrated Admission Assistant, Niaa engages with prospects in a conversational manner and responds to their queries through various mediums like videos, images, documents, carousels or cards. Niaa is based on Natural Language Processing (NLP) and has the power to know a prospect’s intent through their consolidated chat history. Furthermore, it helps in bridging the gap between a prospect and a counsellor by providing the “Request a Call Back” button. Meritto’s Integrated Admission Assistant, also known as NIAA, is a top-tier chatbot designed specifically for educational organizations. NIAA converses with prospects in a natural, interactive manner, responding to their inquiries using various mediums such as videos, images, documents, and card-style information.

For queries about part-time opportunities, student organizations, etc, a chatbot can guide students to the right resources and offer support for various non-academic matters. 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. Institutional staff, especially teachers, are often overburdened and exhausted, working beyond their office hours just to deliver excellent learning experiences to their students.

The AI bot also provides access to specific learning resources and fosters a sense of community among students. The first major use case of chatbots for educational institutions is course management. The Explain My Answer option provides learners with an opportunity to delve deeper into their responses. By selecting a button following specific exercise types, users engage in a chat with Duo, receiving a concise explanation about their answers. Through AI and ML capabilities, bots help to access relevant materials and submit tasks.