The increasing prevalence of mental health disorders, particularly depression, highlights the need for data-driven approaches to support effective analysis and classification of depression levels. Depression assessment data often contain diverse characteristics and require proper preprocessing to ensure reliable analytical results. Therefore, data mining techniques play an important role in extracting meaningful patterns from mental health data. This study aims to explore patterns of depression levels using the K-Nearest Neighbor (KNN) algorithm on preprocessed datasets. The research methodology includes data cleaning, normalization, and attribute selection as preprocessing stages prior to the classification process. The KNN algorithm is then applied to classify depression levels, and model performance evaluation is conducted to assess classification effectiveness. The results indicate that the KNN algorithm is capable of classifying depression levels effectively after appropriate data preprocessing is applied. The analysis successfully identifies patterns within the depression dataset, providing clearer insights into the characteristics of mental health data. It can be concluded that the application of the KNN algorithm on preprocessed data is effective in supporting depression level analysis using data mining techniques. This research is expected to serve as a reference for the development of data-driven mental health analysis systems in the future. Keywords : Depression; Data Mining; KNN; Classification; Preprocessing; Mental Health
Copyrights © 2025