Reading interest is a key indicator in assessing the success of library services. However, manually understanding visitors' preferences poses a challenge for library managers. This study aims to classify the reading interests of regional library visitors by employing the Naïve Bayes algorithm, a widely-used classification method in data mining. The research data includes visit records and book borrowing data from a regional library. Through a quantitative approach, this study analyzes reading interest patterns and evaluates the performance of the Naïve Bayes algorithm in classifying these interests. The analysis results show that the algorithm achieves an accuracy of 65%, with a precision of 62%, recall of 63%, and F1-score of 63%. These findings are expected to assist libraries in formulating better-targeted collection management and service policies, contributing to the overall improvement of reading interest in the community. This study contributes to the field by providing a practical, data-driven solution for libraries to enhance service quality through a better understanding of visitor preferences. Furthermore, it demonstrates the applicability of the Naïve Bayes algorithm in a non-commercial context, encouraging future research on data-driven approaches in library management to support literacy and educational development