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

Chatbot guides students to learn and reflect

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. I believe the most powerful learning moments happen beyond the walls of the classroom and outside of the time boxes of our course schedules.

Chatbot technology has evolved rapidly over the last 60 years, partly thanks to modern advances in Natural Language Processing (NLP) and Machine Learning (ML) and the availability of Large Language Models (LLMs). Today chatbots can understand natural language, respond to user input, and provide feedback in the form of text or audio (text-based and voice-enabled). They can offer learners the possibility to engage in simulated conversational interactions in a non-judgmental environment (El Shazly, 2021; Skjuve et al., 2021). For these reasons, chatbots are being increasingly used as virtual tutors to facilitate the development of language skills and communicative competence in the target language (Huang et al., 2022; Hwang & Chang, 2021; Zhang et al., 2023). 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).

Then, chatbots use this data to compose an entirely personalized learning program that focuses on troubling subjects. Their job is also to follow the students’ advancement from the first to the last lesson, check their assumptions, and guide them through the curriculum. Once the chatbot is developed, it must be tested thoroughly to identify and address any issues or errors. Testing can involve manual and user testing, in which students and faculty provide feedback on their experience with the chatbot.

Analyzing the implications of AI chatbots

This website is using a security service to protect itself from online attacks. There are several actions that could trigger this block including submitting a certain word or phrase, a SQL command or malformed data. Overall, more than 8-in-10 from each sample think technology in education has had a positive impact.

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. 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.

Looking ahead, allowing students to select specific design aspects of AICs, similar to choosing linguistic features such as target level or accent, could be a crucial step in creating a more adaptive and personalized learning experience. 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). Teaching agents play the role of human teachers and can present instructions, illustrate examples, ask questions (Wambsganss et al., 2020), and provide immediate feedback (Kulik & Fletcher, 2016). On the other hand, peer agents serve as learning mates for students to encourage peer-to-peer interactions. Nevertheless, peer agents can still guide the students along a learning path. Students typically initiate the conversation with peer agents to look up certain definitions or ask for an explanation of a specific topic.

Nevertheless, because the tool did not produce answers to some questions, some students decided to abandon it and instead use standard search engines to find answers. 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.

Learn more

Similar success was found by Georgia State University, one of the first institutions to use a chatbot with the stated goal of reducing summer melt by staying in contact with students when they were away from campus. Pounce, Georgia State’s chatbot, reduced summer melt by 22 percent and has continued to evolve since then. In 2021, Pounce was offered to a group of political science students to remind them of upcoming exams, assignment deadlines and more. Students who used the chatbot received better grades and were more likely to pass than those who did not. Check out these higher education IT leaders, authors, podcasters, creators and social media personalities who are helping drive online conversation.

• This personalized approach enhances the overall user experience and fosters a stronger connection with potential students.
• 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.
• 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.
• In this study, we carefully look at the interaction style in terms of who is in control of the conversation, i.e., the chatbot or the user.

Among educators and learners, there is a notable trend—while learners are excited about chatbot integration, educators’ perceptions are particularly critical. 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.

There are also dozens of simpler bots and Artificial Intelligence apps, used in various schools and colleges. Students who attend the same class have different skills, interests, and abilities. Unfortunately, even some of the most expensive schools and colleges in the world are not able to provide this type of service. That is why chatbots are the most logical and affordable alternative for personal learning.

Deliberate practice, such as role-playing, can help you develop these transfer skills. AI chatbots can help with developing scenarios, role-playing a situation, and providing feedback. You can foun additiona information about ai customer service and artificial intelligence and NLP. For example, you might prompt the chatbot to create a realistic ethical dilemma that applies to the discipline education chatbot or to role-play as a patient or client in a relevant scenario. One of the most popular use cases for chatbots in education is helping with homework. These chatbots help students understand complex topics, provide step-by-step solutions, and offer tips for completing assignments.

Smith, the bioscience professor, is also experimenting with ChatGPT assignments. The hand-wringing around it reminds him of the anxiety many teachers experienced a couple of years ago during the pandemic. With students stuck at home, teachers had to find ways to set assignments where solutions were not too easy to Google.

The study was conducted independently and without financial support from any source. The authors have no financial interests or affiliations that could have influenced the design, execution, analysis, or reporting of the research. 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.

Study Limitations

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. Concerning the design principles behind the chatbots, slightly less than a third of the chatbots used personalized learning, which tailored the educational content based on learning weaknesses, style, and needs. Other chatbots used experiential learning (13.88%), social dialog (11.11%), collaborative learning (11.11%), affective learning (5.55%), learning by teaching (5.55%), and scaffolding (2.77%). Another example is the study presented in (Ondáš et al., 2019), where the authors evaluated various aspects of a chatbot used in the education process, including helpfulness, whether users wanted more features in the chatbot, and subjective satisfaction.

They also act as study companions, offering explanations and clarifications on various subjects. 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. Also, AI chatbots contribute to skills development by suggesting syntactic and grammatical corrections to enhance writing skills, providing problem-solving guidance, and facilitating group discussions and debates with real-time feedback. 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.

The Perfect Duo for your Admissions Teams—Education Chatbot + CRM

The third area explores how AICs’ design can positively affect language learning outcomes. Modern AICs usually include an interface with multimedia content, real-time feedback, and social media integration (Haristiani & Rifa’I, 2020). They also employ advanced speech technologies to ensure accessible and humanlike dialogues (Petrović & Jovanović, 2021). Additionally, AICs today can also incorporate emerging technologies like AR and VR, and gamification elements, to enhance learner motivation and engagement (Kim et al., 2019).

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 Chat GPT focuses on the conceptual principles that led to the chatbot’s design. Okonkwo and Ade-Ibijola (2021) discussed challenges and limitations of chatbots including ethical, programming, and maintenance issues.

Over the past year I’ve designed several chatbots that serve different purposes and also have different voices and personalities. Most learning happens in the 99.9% of our lives when we are not in a classroom. The COVID-19 pandemic pushed educators and students out of their classrooms en masse.

At last, we could have missed articles that report an educational chatbot that could not be found in the selected search databases. To deal with this risk, we searched manually to identify significant work beyond the articles we found in the search databases. Nevertheless, the manual search did not result in any articles that are not already found in the searched databases. Most articles (13; 36.11%) used an experiment to establish the validity of the used approach, while 10 articles (27.77%) used an evaluation study to validate the usefulness and usability of their approach. The remaining articles used a questionnaire (10; 27.7%) and a focus group (3; 8.22%) as their evaluation methods. In comparison, chatbots used to teach languages received less attention from the community (6 articles; 16.66%;).

This knowledge is crucial for educators and policymakers to make informed decisions about the continued integration of chatbots into educational systems. Secondly, understanding how different student characteristics interact with chatbot technology can help tailor educational interventions to individual needs, potentially optimizing the learning experience. Thirdly, exploring the specific pedagogical strategies employed by chatbots to enhance learning components can inform the development of more effective educational tools and methods. However, the study also highlights the challenges that need to be addressed, such as the requirement for more sophisticated AI algorithms capable of adjusting to the learner’s proficiency level and the improvement of speech technologies.

Explore chatbot design for streamlined and efficient experiences within messaging apps while overcoming design challenges. For example, an e-commerce company could deploy a chatbot to provide browsing customers with more detailed information about the products they’re viewing. The HR department of an enterprise organization might ask a developer to find a chatbot that can give employees integrated access to all of their self-service benefits. Software engineers might want to integrate an AI chatbot directly into their complex product. Security and data leakage are a risk if sensitive third-party or internal company information is entered into a generative AI chatbot—becoming part of the chatbot’s data model which might be shared with others who ask relevant questions.

Subsequently, it was imported into the Rayyan tool Footnote 6, which allowed for reviewing, including, excluding, and filtering the articles collaboratively by the authors. Concerning their interaction style, the conversation with chatbots can be chatbot or user-driven (Følstad et al., 2018). Chatbot-driven conversations are scripted and best represented as linear flows with a limited number of branches that rely upon acceptable user answers (Budiu, 2018). When the user provides answers compatible with the flow, the interaction feels smooth.

It is important for the student to know their instructors or the realities of how easy or difficult a course is. You can set up sessions with current student ambassadors to answer any queries like this. Before the student decides to apply for a course, parents and the student would like to know more about the campus facilities as well as the kind of exposure their child can get. For example, queries related to financial aid, course details, and instructor details often have straightforward answers, or the student can be redirected towards the right page for information. In today’s digitally driven world, technological advancements continue to reshape various industries, and higher education is no exception. The comprehensive list of included studies, along with relevant data extracted from these studies, is available from the corresponding author upon request.

In 2011 Apple introduced Siri as a voice-activated personal assistant for its iPhone (Aron, 2011). Although not strictly a chatbot, Siri showcased the potential of conversational AI by understanding and responding to voice commands, performing tasks, and providing information. In the same year, IBM’s Watson gained fame by defeating human champions in the quiz show Jeopardy (Lally & Fodor, 2011). It demonstrated the power of natural language processing and machine learning algorithms in understanding complex questions and providing accurate answers.

Do chatbots have special qualities that are suited for out-in-the-world learning?

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. In 2023, AI chatbots are transforming the education industry with their versatile applications. Among the numerous use cases of chatbots, there are several industry-specific applications of AI chatbots in education.

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. For instance, you can ask AtlasRTX’s higher ed digital assistants questions such as whether you need to submit SAT scores to apply, or what your minimum GPA needs to be. However, ask it what the meaning of life is and the answer you receive will likely be less satisfactory.

This line of research investigates how the interactive nature of some AICs can reduce students’ anxiety and cognitive load (Hsu et al., 2021) and promote an engaging learning environment (Bao, 2019). Furthermore, some authors have examined the ability of chatbots to promote self-directed learning, given their wide availability and capacity for personalized responses (Annamalai et al., 2023). Firstly, it aims to investigate the current knowledge and opinions of language teacher candidates regarding App-Integrated Chatbots (AICs). Secondly, it seeks to measure their level of satisfaction with four specific AICs after a 1-month intervention.

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). ELIZA could mimic human-like responses by reflecting user inputs as questions. Another early example of a chatbot was PARRY, implemented in 1972 by psychiatrist Kenneth Colby at Stanford University (Colby, 1981).

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. Chatbots can help educational institutions in data collection and analysis in various ways. Firstly, they can collect and analyze data to offer rich insights into student behavior and performance to help them create more effective learning programs.

Additionally, chatbots streamline 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 https://chat.openai.com/ enhance communication, offer 24/7 support, and cater to the unique needs of each student. The landscape of mobile-application language learning (MALL) has been significantly reshaped in recent years with the incorporation of AICs (Pham et al., 2018).

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. 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. 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.

In general, the studies conducting evaluation studies involved asking participants to take a test after being involved in an activity with the chatbot. The results of the evaluation studies (Table 12) point to various findings such as increased motivation, learning, task completeness, and high subjective satisfaction and engagement. In general, the followed approach with these chatbots is asking the students questions to teach students certain content. 63.88% (23) of the selected articles are conference papers, while 36.11% (13) were published in journals. Interestingly, 38.46% (5) of the journal articles were published recently in 2020. Intriguingly, one article was published in Computers in Human Behavior journal.

Learn about how the COVID-19 pandemic rocketed the adoption of virtual agent technology (VAT) into hyperdrive. Take this 5-minute assessment to find out where you can optimize your customer service interactions with AI to increase customer satisfaction, reduce costs and drive revenue. IBM watsonx Assistant provides customers with fast, consistent and accurate answers across any application, device or channel.

For example, a chatbot can be added to Microsoft Teams to create and customize a productive hub where content, tools, and members come together to chat, meet and collaborate. Concerning the educational setting, Spanish participants interacted more frequently with all four AICs compared to Czech students. The SD values show a similar level of variation in the weekly interaction hours across all four AICs for both Spanish and Czech participants, suggesting a comparable spread of interaction frequencies within each group.

Modern chatbots are trained to conduct very complex tasks, yet they can be easily built without coding. Most bots provide specific answers depending on the words and phrases people use, so the building process usually involves asking questions and generating possible outcomes. When we talk about educational chatbots, this is probably the biggest concern of teachers and trade union organizations. The truth is that they will take over the repetitive tasks and make a teacher’s work more meaningful. 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. One of them presented in (D’mello & Graesser, 2013) asks the students a question, then waits for the student to write an answer.

The model also highlights the potential of AICs in language learning, particularly in terms of providing immediate feedback, and fostering a supportive learning environment. The Chatbot-Human Interaction Satisfaction Model (CHISM) is a tool previously designed and used to measure participants’ satisfaction with intelligent conversational agents in language learning (Belda-Medina et al., 2022). This model was specifically adapted for this study to be implemented with AICs. The pre-post surveys were completed in the classroom in an electronic format during class time to ensure a focused environment for the participants. Quantitative data obtained were analysed using the IBM® SPSS® Statistics software 27. The main objective was to determine the average responses by calculating the means, evaluate the variability in the data by measuring the standard deviation, and assess the distribution’s flatness through kurtosis.

This can include information on policies and procedures, campus resources, and frequently asked questions. Chatbots can facilitate student engagement by offering personalized recommendations for clubs, organizations, and events based on students’ interests and goals. They can also provide information on extracurricular activities, sports teams, and volunteer opportunities. AI chatbots are becoming increasingly popular in educational institutions as they offer several benefits that can significantly improve student and faculty support. In this article, we will discuss a higher education chatbot, how AI chatbots improve student and faculty support, some use cases of higher education chatbots, and the best chatbots for higher education.