Comparison of Naive Bayes and KNN for Honey-Mumford Learning Style Classification in Interpersonal Skill: Komparasi Naive Bayes dan KNN untuk Klasifikasi Gaya Belajar Honey-Mumford pada Interpersonal Skill

Hari Moerti (Institut Teknologi dan Bisnis Yadika Pasuruan)
Hamzah Setiawan (Informatika, Universitas Muhammadiyah Sidoarjo)

JOINCS (Journal of Informatics, Network, and Computer Science)
Vol. 8 No. 2 (2025): November

Developing soft skills competence, particularly interpersonal abilities, often presents a challenge for Informatics students accustomed to technical and structured thinking patterns. The mismatch between teaching methods and student learning preferences can hinder the absorption of non-technical material. This study aims to classify student learning style profiles in the Interpersonal Skill course using a Machine Learning approach based on the Honey-Mumford model (Activist, Reflector, Theorist, Pragmatist). The research methodology employs Educational Data Mining techniques by comparing the performance of Naive Bayes and K-Nearest Neighbor (KNN) algorithms in predicting learning styles based on academic history data and behavioral questionnaires. Experimental results indicate that the Naive Bayes algorithm outperforms KNN in recognizing student characteristic patterns, achieving an accuracy rate of 93.33%. These findings suggest that engineering students possess heterogeneous learning styles; therefore, adaptive and varied teaching strategies are essential to optimize the comprehension of soft skills materia.