<![CDATA[Conceptual understanding of science in the topic of motion remains a challenge for junior high school students due to its intangible and the need for appropriate visualization. The study aims to develop a deep learning-based digital comic media on the topic of motion and to analyze its effectiveness in improving the conceptual understanding of science among seventh-grade junior high school students. The study employed the research and development (R&D) method using the ADDIE model, which includes five stages: analysis, design, development, implementation, and evaluation. The research subjects were seventh-grade students of SMP Negeri 1 Peureulak, selected using a simple random sampling technique. The research instruments consisted of a media validation sheet and a conceptual understanding test. The results of the material expert validation showed an Aiken's V index of 0.818, categorized as high, while the media expert validation yielded 0.803, also categorized as high, indicating that the media is feasible to use. The implementation results showed that students' conceptual understanding increased from an average of 35.28 in the pretest to 78.56 in the posttest, with a significance value of 0.00 (p < 0.05) and an N-Gain of 0.7, categorized as high. The results of the paired sample t-test proved that there was a significant difference before and after the use of the media. It was concluded that the deep learning-based digital comic media is proven to be valid, feasible, and effective in improving students' conceptual understanding of science on the topic of motion. The implications of this study recommend the use of similar media for other abstract science topics, as well as further development using stronger experimental designs]]>
Copyrights © 2026
