The Impact of Similarity Fusion based Travel Interest Point Recommendation Algorithm in Youth Users’ Study Tours

Abstract

Study tours for adolescent users are somewhat contemporary and traditional methods, such as questionnaires cannot meet their psychological expectations. To bring a better experience to teenagers’ study tour, a Latent Dirichlet Allocation (LDA) theme model was used to mine teenage users and their interest points, and then the similarity between LDA and the check-in matrix was calculated and fused. Based on this, an RT-CNN model was built for deep feature extraction of review information, and point-of-interest recommendation was performed by fusing similarity, check-in behavior, and geographic location. The RT-CNN model had an accuracy of 92.7%, a recall of 87.1%, a Mean Absolute Error (MAE) value of 4.2%, a Root Mean Square Error (RMSE) of 4.8%, and F1 values of 89.2% and 88.7% in the two datasets. The new model in this experiment has high accuracy in making interest point recommendations and has a good overall performance.