Pengembangan Platform Pembelajaran Daring “KakTutor” Berbasis Kecerdasan Buatan dalam Menganalisis Emosi Siswa

Tanjaya, Edmund Tyan
Sarkozy, Ferdiansyah
Haryanto, Immanuel Christian
Lienandi, Joseph Mitchel
Cen, Vin
Ningsih, Rahmi Yulia
Pratiwi, Chairani Putri

Jurnal Ilmiah Universitas Batanghari Jambi
Vol 26, No 1 (2026): Februari

This study aims to develop an AI-based online learning system capable of detecting and analyzing students’ facial expressions in real time to help instructors better understand their emotions and levels of understanding. The research method employed is Research and Development (R&D) using a Prototype model, consisting of the stages of planning, prototype creation, user evaluation, refinement, and system finalization. The system was developed using the Face API and Google Gemini API with the Facial Action Coding System (FACS) approach to detect facial expressions. Expert testing results show a high level of system accuracy and effectiveness, with an average score of 4.44 (classified as very good). The system is considered effective in assisting instructors in recognizing students’ emotions and adapting teaching strategies accordingly. Therefore, the application of artificial intelligence in online learning has the potential to create a more interactive, empathetic, and effective learning environment.