Chatbots in Educational Recommender Systems: A Systematic Literature Review

This summary refers to a full research article. The article presents a Systematic Literature Review (SLR) that aims to characterize the use of conversational agents (CHATBOTS) in the current scenario of Educational Recommendation Systems (ERS).The objective of this work is to improve the quality of teaching by using chatbots and ERS as valuable tools for teaching, in order to personalize the student learning experience and provide relevant recommendations based on their behavior and learning history, making it more engaging, personalized, and efficient. Following the SLR protocol proposed by Kitchenham, the string and connector chain (“recommendation” OR “recommender”) AND (“chatbot” OR “chatbots” OR “chaterbots”) was planned and used in the search fields of 4 highly relevant academic data repositories in the computing area: Institute of Electrical and Electronic Engineers (IEEE), Scopus, Association for Computing Machinery (ACM), and Science Direct, covering the period from 2018 to 2023, selecting 1,401 published articles, of which, after applying inclusion criteria, 158 were analyzed in the final phase of the review. As main results, we can highlight: Personalization of learning: with the help of chatbots, ERS can analyze student data, such as academic history, test results, and learning preferences, to provide personalized recommendations for educational content, maximizing student learning; Accessibility: Chatbots help make education more accessible to students, as they are available without interruption, which means that students can get help whenever they need it, regardless of the time or location; Engagement: Chatbots help with educational content by providing personalized recommendations for content that is relevant and interesting, keeping students engaged and motivated. Additionally, chatbots can use gamification techniques, such as rewards and competitions, to encourage students to engage more with educational content; Data analysis: Chatbots help collect and analyze data on student performance, tracking student progress and learning activities and signaling according to predefined parameters; Integration with existing technologies, such as learning management systems and online teaching platforms, can help provide a more integrated and unified learning experience for students. In conclusion, the use of chatbots in ERS has the potential to transform education, providing a more personalized, accessible, and efficient learning experience for students, being a complementary tool to help improve the learning experience of students.