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

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). 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. The remaining journal articles were published in several venues such as IEEE Transactions on Affective Computing, Journal of Educational Psychology, International Journal of Human-Computer Studies, ACM Transactions on Interactive Intelligent System. Most of these journals are ranked Q1 or Q2 according to Scimago Journal and Country Rank Footnote 7.

We also discussed and clarified all doubts and gray areas after analyzing each selected article. Various design principles, including pedagogical ones, have been used in the selected studies (Table 8, Fig. 8). 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. 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.

Tailoring Educational Content Based on Analytics

Firstly, further research on the impacts of integrating chatbots can shed light on their long-term sustainability and how their advantages persist over time. 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.

Indeed, articles published in 2023 accounted for 70% (28/40) of the included articles, which might be due to either increased scholarly interest or intensified effort. This study tries to delve into the technological education aspect of health care, which is a rapidly expanding area. Consequently, it will provide a comprehensive reflection of the dynamic and developing educational sector. Conversational AI chatbots can remember conversations with users and incorporate this context into their interactions. When combined with automation capabilities including robotic process automation (RPA), users can accomplish complex tasks through the chatbot experience. And if a user is unhappy and needs to speak to a real person, the transfer can happen seamlessly.

Also, a lack of clarity and satisfaction among the students will waste all your time and efforts. Say No to customer waiting times, achieve 10X faster resolutions, and ensure maximum satisfaction for your valuable customers with REVE Chat. Pounce answers questions about admissions, financial aid, and registration, reducing the number of students who drop out due to confusion or lack of information. Since different researchers with diverse research experience participated in this study, article classification may have been somewhat inaccurate. As such, we mitigated this risk by cross-checking the work done by each reviewer to ensure that no relevant article was erroneously excluded.

With active listening skills, Juji chatbots can help educational organizations engage with their audience (e.g., existing or prospect students) 24×7, answering questions and providing just-in-time assistance. Furthermore, in regard to problems faced, it was observed that in the Chat GPT EC group, the perception transformed from collaboration issues towards communicative issues, whereas it was the opposite for the CT group. According to Kumar et al. (2021), collaborative learning has a symbiotic relationship with communication skills in project-based learning.

Voice of the Customer Methodologies to Generate Customer Feedback

In terms of the evaluation methods used to establish the validity of the articles, two related studies (Pérez et al., 2020; Smutny & Schreiberova, 2020) discussed the evaluation methods in some detail. However, this study contributes more comprehensive evaluation details such as the number of participants, statistical values, findings, etc. 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. 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. Look for features such as natural language processing, integration capabilities with school databases, scalability, and the ability to handle a wide range of queries.

This choice can be explained by the flexibility the web platform offers as it potentially supports multiple devices, including laptops, mobile phones, etc. The remaining articles (13 articles; 36.11%) present chatbot-driven chatbots that used an intent-based approach. The idea is the chatbot matches what the user says with a premade response. In general, the followed approach with these chatbots is asking the students questions to teach students certain content.

The input you provide largely determines the chatbots’ predictive responses. The more context, details, and nuances you give the chatbot the more it has to work with to generate responses. 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? The ability to transfer skills and knowledge that you learned to a new situation involves abstract thinking, problem-solving, and self-awareness. Deliberate practice, such as role-playing, can help you develop these transfer skills.

Depending on the activity and the goals, I often design the bot to ask students for a code name instead of their real name (the chatbot refers to the person by that name at different points in the conversation). I’m also very clear, through what the bot says to the user and what I say when I first introduce the bot, about how the information that is shared will be used. Oftentimes reflections that students share with the bot are shared with the class without identifiable information, as a starting point for social learning.

HR automation can improve the employee experience and save time for your entire staff. They help businesses eliminate unqualified leads and connect sales reps with qualified ones. This helps sales specialists spend less time acquiring leads and more on building relationships with prospects. Another global giant, Starbucks, uses an AI agent to help customers compose their favorite coffee drink.

For instance, both groups portrayed high self-realization of their value as a team member at the end of the course, and it was deduced that their motivational belief was influenced by higher self-efficacy and intrinsic value. Next, in both groups, creativity was overshadowed by post-intervention teamwork significance. Therefore, we conclude that ECs significantly impact learning performance and teamwork, but affective-motivational improvement may be overshadowed by the homogenous learning process for both groups. Interestingly, the percentage of students that found “interaction with lecturer” and “online feedback and guidance” for the EC was higher than the control group, and this may be reflected as a tendency to perceive the chatbot as an embodiment of the lecturer. Furthermore, as for constructive feedback, the outcomes for both groups were very similar as the critiques were mainly from the teammates and the instructor, and the ECs were not designed to critique the project task. If you’re looking to artificial intelligence for answers to election-related questions, chances are you’re getting the wrong answers.

According to Garcia Brustenga et al. (2018), EC can be designed without educational intentionality where it is used purely for administrative purposes to guide and support learning. The ECs were also developed based on micro-learning strategies to ensure that the students do not spend long hours with the EC, which may cause cognitive fatigue (Yin et al., 2021). Furthermore, the goal of each EC was to facilitate group educational chatbots work collaboration around a project-based activity where the students are required to design and develop an e-learning tool, write a report, and present their outcomes. Next, based on the new design principles synthesized by the researcher, RiPE was contextualized as described in Table 5. In our review, the predominant study design was reviews, constituting 20% (8/40) of the total articles [36,46,49,50,56,59,60].

They use natural language processing (NLP) and machine learning algorithms (MLAs) to understand and respond to a wide range of queries. These enhance student satisfaction and reduce the workload on administrative staff. There is no doubt that higher education chatbots offer multifaceted benefits in education.

They hurt advertisers paying for those clicks and create quite a headache for marketers who get unreliable data. Bad bots can also break into user accounts, steal data, create fake accounts and news, and perform many other fraudulent activities. Tay was supposed to chat with millennials and prove a computer program can get smarter with “casual and playful conversations.”

The chatbot can invite a customer to chat and collect their contact details. It can share coupon codes, provide personalized product recommendations, and promote your job offers. This means they only answer questions they were prepared to answer by using predefined answers. So, the more an AI chatbot communicates with users, the more patterns, words, and contexts it learns. We created this course to give you a beginning-to-end understanding of chatbots and how they work. During the lessons, you’ll gain practical skills with which you can plan and design successful chatbots using a no-code platform.

Whether it’s admission-related inquiries or general questions, educational chatbots offer a seamless and time-saving alternative, empowering students with instant and accurate assistance at their fingertips. According to Schmulian and Coetzee (2019), there is still scarcity in mobile-based chatbot application in the educational domain, and while ECs in MIM has been gaining momentum, it has not instigated studies to address its implementation. Furthermore, there are also limited studies in strategies that can be used to improvise ECs role as an engaging pedagogical communication agent (Chaves & Gerosa, 2021). Besides, it was stipulated that students’ expectations and the current reality of simplistic bots may not be aligned as Miller (2016) claims that ANI’s limitation has delimited chatbots towards a simplistic menu prompt interaction.

Authors and Affiliations

Keep in mind that the tone or style of coaching provided by chatbots may not suit everyone. For example, Toyota Poland uses a chatbot to initiate the sales process with a prospective customer. The chatbot asks the user a set of questions, gets the user’s details, and passes them on to a selected car dealer, who based on collected information, provides the potential customer with a sales offer and a financial calculation.

Because universities aren’t providing much help, professors are flocking to informal online discussion groups, professional development webinars and conferences for information. Discover different ways to create a chatbot and find out which one is best for you. I’m Kaia with LiveChat, and together with our chatbot experts, we’ll walk you through your journey to master chatbot building. A 2023 Forrester Consulting Total Economic Impact™ study, commissioned by IBM, modeled a composite organization from real client data that showed 370% ROI over three years. Between 2010 and 2020, on average, 1 article was published every 3‐4 years, culminating in a total of 3 articles, contributing to 8% of the 40 publications.

• Powered by super AI, a unique combination of generative AI and cognitive AI, Juji’s education solution enables the best-in-class chatbots to aid both students and instructors, aiming at delivering superior user experience and learning outcomes.
• At some point, we decided we were gonna build a chatbot to help our support team deal with all those inquiries, and so we did.
• YouChat also provides short bits of information and important facts to answer user questions quickly.
• It utilizes GPT-4 as its foundation but incorporates additional proprietary technology to enhance the capabilities of users accustomed to ChatGPT.
• Yellow.ai is an excellent conversational AI platform vendor that can help you automate your business processes and deliver a world-class customer experience.

Powerful AI chatbot marketing software helps you improve customer experiences and boost lead generation with fast, personalized customer support. The search findings were imported into Covidence (Veritas Health Innovation) while adhering to established protocols. Initially, titles and abstracts were screened, followed by a thorough review of full-text articles.

Personalized learning and academic support

After defining the criteria, our search query was performed in the selected databases to begin the inclusion and exclusion process. Initially, the total of studies resulting from the databases was 1208 studies. The metadata of the studies containing; title, abstract, type of article (conference, journal, short paper), language, and keywords were extracted in a file format (e.g., bib file format). Subsequently, it was imported into the Rayyan tool Footnote 6, which allowed for reviewing, including, excluding, and filtering the articles collaboratively by the authors.

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. While chatbots serve as valuable educational tools, they cannot replace teachers entirely. Instead, they complement educators by automating administrative tasks, providing instant support, and offering personalized learning experiences. Teachers’ expertise and human touch are indispensable for fostering critical thinking, emotional intelligence, and meaningful connections with students. Chatbots for education work collaboratively with teachers, optimizing the online learning process and creating an enriched educational ecosystem. Nevertheless, Wang et al. (2021) claims while the application of chatbots in education are novel, it is also impacted by scarcity.

However, you need to design a valid bot flow and input related questions accordingly. 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. Before they even use ChatGPT, I help students discern what is worth knowing, figuring out how to look it up, and what information or research is worth “outsourcing” to A.I. I also teach students how to think critically about the data collected from the chatbot — what might be missing, what can be improved and how they can expand the “conversation” to get richer feedback.

By creating a sense of connection and personalized interaction, these AI chatbots forge stronger bonds between students and their studies. Learners feel more immersed and invested in their educational journey, driven by the desire to explore new topics and uncover intriguing insights. According to Adamopoulou and Moussiades (2020), it is impossible to categorize chatbots due to their diversity; nevertheless, specific attributes can be predetermined to guide design and development goals. For example, in this study, the rule-based approach using the if-else technique (Khan et al., 2019) was applied to design the EC.

Explore chatbot design for streamlined and efficient experiences within messaging apps while overcoming design challenges. Selecting the right chatbot platform can have a significant payoff for both businesses and users. Users benefit from immediate, always-on support while businesses can better meet expectations without costly staff overhauls. AI chatbots are commonly used in social media messaging apps, standalone messaging platforms, proprietary websites and apps, and even on phone calls (where they are also known as integrated voice response, or IVR). Chatbots can make it easy for users to find information by instantaneously responding to questions and requests—through text input, audio input, or both—without the need for human intervention or manual research. Many brands are successfully using AI chatbots for education in course examinations and assessments.

Limitations of Educational Chatbots and Why It’s Vital to Address Them

The research, conducted over two academic years (2020–2022) with a mixed-methods approach and convenience sampling, initially involved 163 students from the University of X (Spain) and 86 from the University of X (Czech Republic). However, the final participant count was 155 Spanish students and 82 Czech students, as some declined to participate or did not submit the required tasks. Participation was voluntary, and students who actively engaged with the chatbots and completed all tasks, including submitting transcripts and multiple-date screenshots, were rewarded with extra credits in their monthly quizzes. This approach ensured higher participation and meaningful interaction with the chatbots, contributing to the study’s insights into the effectiveness of AICs in language education. I do not see chatbots as a replacement for the teacher, but as one more tool in their toolbox, or a new medium that can be used to design learning experiences in a way that extends the capacity and unique abilities of the teacher.

Following closely was the United States, contributing 15% (6/40) of the articles [39,40,46,52,55,59]. South Korea secured the third position, representing 10% (4/40) of the articles [41,47,48,63]. Canada [26,28,30], Mainland China [33,50,64], and Singapore [57,58,60] each contributed 8% (3/40) of the articles.

Since pupils seek dynamic learning opportunities, such tools facilitate student engagement by imitating social media and instant messaging channels. This study applies an interventional study using a quasi-experimental design approach. Creswell (2012) explained that education-based research in most cases requires intact groups, and thus creating artificial groups may disrupt classroom learning. Therefore, one group pretest–posttest design was applied for both groups in measuring learning outcomes, except for learning performance and perception of learning which only used the post-test design. The EC is usually deployed for the treatment class one day before the class except for EC6 and EC10, which were deployed during the class.

This gives transparent and structured assessment outcomes to educatee, faculty, and stakeholders. The e-learning showed the need for exceptional support, especially in the wake of COVID-19. 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. The authors declare that this research paper did not receive any funding from external organizations.

Nevertheless, given the possibilities of MIM in conceptualizing an ideal learning environment, we often overlook if instructors are capable of engaging in high-demand learning activities, especially around the clock (Kumar & Silva, 2020). Chatbots can potentially be a solution to such a barrier (Schmulian & Coetzee, 2019), especially by automatically supporting learning communication and interactions (Eeuwen, 2017; Garcia Brustenga et al., 2018) for even a large number of students. AI language models such as chatbots have caused a revolution in nursing education through the provision of personalized and interactive learning activities. Chatbots are implemented in nursing education for personalized instruction, patients-care simulation, and critical thinking enhancement. Chatbots in health care are used for teleconsultation to improve communication skills, support clinical judgment, and enable remote patient monitoring.

These indispensable assistants generate specific scorecards and provide insights into learning gaps. Timely and structured delivery of such results aids students in understanding their progress, showing the areas for improvement. Here chatbots play an important role, as they can track progress, ensuring continuous interaction through personalized content and suggestions.

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 https://chat.openai.com/ 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.

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.

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%). You can foun additiona information about ai customer service and artificial intelligence and NLP. The findings point to improved learning, high usefulness, and subjective satisfaction. 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.

CASE STUDY

Chatbot interfaces with generative AI can recognize, summarize, translate, predict and create content in response to a user’s query without the need for human interaction. After all, we all know that these educational chatbots can be the best teaching assistants and give some relief to educators. Bots in education can help students with regular mock tests, rank tests, etc. They can also track project assignments and teachers with individually tailored messages and much more.

Gemini is the new name for “Google Bard.” It shares many similarities with ChatGPT and might be one of the most direct competitors, so that’s worth considering. Gemini responds with code, images, and text based on your conversation. The free version should be for anyone who is starting and is interested in the AI industry and what the technology can do. Many people use it as their primary AI tool, and it’s tough to replace. Many other AI chatbots are built on the technologies that OpenAI has developed, which means they’re often behind the curve with new features and innovation.

Since then, AI technology has significantly advanced and chatbots are now able to provide more comprehensive language learning support, such as conversational exchange, interactive activities, and multimedia content (Jung, 2019; Li et al., 2022). 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. The traditional education system faces several issues, including overcrowded classrooms, a lack of personalized attention for students, varying learning paces and styles, and the struggle to keep up with the fast-paced evolution of technology and information.

Learning performance is defined as the students’ combined scores accumulated from the project-based learning activities in this study. Henceforth, we speculated that EC might influence the need for cognition as it aids in simplifying learning tasks (Ciechanowski et al., 2019), especially for teamwork. Three categories of research gaps were identified from empirical findings (i) learning outcomes, (ii) design issues, and (iii) assessment and testing issues. EC studies have primarily focused on language learning, programming, and health courses, implying that EC application and the investigation of learning outcomes have not been investigated in various educational domains and levels of education.

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 teachers to devote more time and attention to designing exciting lessons and providing learners with the personalized attention they deserve. Chatbots in education serve as valuable administrative companions for both prospective and existing students. Instead of enduring the hassle of visiting the office and waiting in long queues for answers, students can simply text the chatbots to quickly resolve their queries. This user-friendly option provides convenient and efficient access to information, enhancing the overall student experience and streamlining administrative processes.

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. It’s important to note that some papers raise concerns about excessive reliance on AI-generated information, potentially leading to a negative impact on student’s critical thinking and problem-solving skills (Kasneci et al., 2023). For instance, if students consistently receive solutions or information effortlessly through AI assistance, they might not engage deeply in understanding the topic.

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. Use structured conversation flows with clear options and avoid jargon that might confuse the user.

There are two ways a chatbot can understand what humans say, and they can be divided into two groups —  AI chatbots and rule-based chatbots. Since you’re already here, I’m guessing you’re a business owner who’s considering adding chatbots to your customer service armory. Maybe you’re thinking about starting a new career as a chatbot designer, and you need to level up your skills. Or, you just heard about chatbots and you want to find out if they’re worth exploring. Generali Poland built a virtual assistant that answers more than 120 customer support scenarios and FAQs without requiring any redirection to human agents. Brands use conversational agents to diversify their customer-engagement strategy.

In the car, Keast queried his kids for their thoughts on the software until they begged him to stop. Soon after ChatGPT was released in November, Darren Keast noticed students in his college English composition class turning in essays that read as if they’d been written by machine. Many contained fabricated quotes and cited sources that didn’t exist — telltale signs they were created by the artificial intelligence chatbot. He’s dreading a repeat of that confusion this fall, so he scrambled over summer break to adapt. That’s right, but a human can’t effectively chat with multiple users at the same time — a chatbot can, and it can do it around the clock without getting out of breath. On top of that, AI assistants are a great repository of knowledge about customers.

• Since the emergence of chatbots like ChatGPT, China has made building its own advanced AI a priority.
• Likewise, it was deemed necessary due to the nature of the project, which involves design.
• Such a strategy was used to ensure that the instructor could guide the students the next day if there were any issues.

Chatbots will be virtual assistants that offer instant help and answer questions whenever students get stuck understanding a concept. Subsequently, the chatbot named after the course code (QMT212) was designed as a teaching assistant for an instructional design course. It was targeted to be used as a task-oriented (Yin et al., 2021), content curating, and long-term EC (10 weeks) (Følstad et al., 2019). Students worked in a group of five during the ten weeks, and the ECs’ interactions were diversified to aid teamwork activities used to register group members, information sharing, progress monitoring, and peer-to-peer feedback.

The key task of chatbot technology is to provide conversational responses to customer queries without human intervention. The advantage of virtual assistants is that they can chat with multiple users simultaneously and provide information within seconds. They can improve customer engagement, identify business leads, and reduce wait times. Today, chatbots can consistently manage customer interactions 24×7 while continuously improving the quality of the responses and keeping costs down.

As a digital assistant, the EC was designed to aid in managing the team-based project where it was intended to communicate with students to inquire about challenges and provide support and guidance in completing their tasks. According to Cunningham-Nelson et al. (2019), such a role improves academic performance as students prioritize such needs. Therefore, supporting the outcome of this study that observed that the EC groups learning performance and teamwork outcome had a more significant effect size than the CT group. Accordingly, chatbots popularized by social media and MIM applications have been widely accepted (Rahman et al., 2018; Smutny & Schreiberova, 2020) and referred to as mobile-based chatbots.

These chatbots ensure that educational content and resources are accessible to all students, regardless of their abilities or limitations. However, the use of AICs as virtual tutors also presents certain challenges. Some studies have emphasized that interactions with AICs can seem detached and lack the human element (Rapp et al., 2021). Additionally, while AICs can handle a wide range of queries, they may struggle with complex language nuances, which could potentially lead to misunderstandings or incorrect language usage. It has also been observed that some students’ interest dwindled after the initial period of engagement due to repetitive conversation patterns and redundancies, making the interaction less natural compared to student–teacher exchanges (Fryer et al., 2019).