The Chatbot Effect in Supporting Blended Learning on Students' Academic Achievement

This study is motivated by the use of technology in education that is increasingly developing, and with chatbot applications, is one of the technologies that can be utilized to improve classroom learning quality. The research method used is quantitative. The type of research is quasi-experimental with a pretest-posttest control group design. The total population and sample consist of 63 students divided into two classes, 5A and 5B. Data collection techniques using test and non-test. The data collection instruments are question sheets, observation sheets, and documentation guidelines. The analysis technique used is descriptive analysis and hypothesis testing. Based on the data analysis obtained, 1) The Control class pretest learning outcomes are 47.74. while the posttest is 71.61. 2) The experimental class pretest learning outcomes are 53.44, and the posttest is 86.88. 3) The blended learning method assisted by the NAFA chatbot application has a significant effect. 4) The blended learning method assisted by the NAFA chatbot application has an effect size test of 4.2335. So, it can be concluded that the blended learning method assisted by the NAFA chatbot application greatly influences learning outcomes. These findings imply that chatbot-assisted blended learning holds strong potential for fostering interactive and student-centered classrooms in elementary education. Future studies are recommended to expand the scope across subjects, student populations, and school settings, and to explore their long-term impact on learners’ motivation, engagement, and critical thinking.