Using Educational Chatbots with Metacognitive Feedback to Improve Science Learning

Educational chatbots (ECs) can offer instructional feedback to enhance learning. However, the effect of metacognitive feedback on science education has not been fully explored. This study focuses on the effect of the EC with metacognitive feedback on students’ knowledge retention, transfer, and intrinsic motivation in the field of biology science. A between-group experimental design with 62 college students was conducted. Students in the experiment group received metacognitive feedback, whereas students in the control group received no feedback. The results of the ANCOVA test showed that students in the experiment group demonstrated better knowledge retention and transfer than those in the control group (F = 13.11, p = 0.001; F = 14.39, p < 0.001). Further, students in the experiment group reported more learning interest and higher perceived competence and value than those in the control group (F = 3.72, p = 0.001; F = 1.91, p = 0.009; F = 2.70, p = 0.004). In addition, correlation analysis revealed that perceived competence in the metacognitive feedback group was positively related to knowledge transfer (r = 0.39, p = 0.032). However, there was no significant difference in perceived pressure between both groups (p = 0.203). This study highlights the potential of the EC with metacognitive feedback for science learning.