Journal of Information & Systems Management Jinbo Li 15 4 2025 https://doi.org/10.6025/jism/2025/15/4/161-168 https://www.dline.info/jism/fulltext/v15n4/jismv15n4_2.pdf The paper explores the application of data mining techniques specifically the LDA (Latent Dirichlet Allocation) topic model and the Apriori association rule algorithm to enhance personalized tourism route recommendations. As tourism shifts from standardized group itineraries toward individualized experiences, the study addresses inefficiencies in current travel planning methods, which often over look user preferences. By analyzing user generated content such as reviews, browsing histories, and click behaviors, the LDA model uncovers latent thematic interests and sentiment trends within tourism related text data. Meanwhile, the Apriori algorithm identifies frequent associations among tourist attractions and services, enabling the construction of optimized, preference aligned itineraries. The proposed recommendation system features a three tier architecture (application, logic, and data processing layers) that integrates real time user data to refine suggestions dynamically. The research demonstrates that combining LDA for topic and sentiment analysis with Apriori for association mining improves the accuracy, relevance, and personalization of travel recommendations. This approach not only enhances user satisfaction but also boosts competitiveness for tourism enterprises by aligning offerings with actual traveler needs. The study concludes that these datadriven methods effectively address information overload and preference ambiguity in modern tourism, marking a significant step toward intelligent, personalized travel planning in the big data era.