Book Rating Prediction Model Based on LightGBM and Text Convolutional Neural Network

Personalized recommendation is one of the key components of efficient library services today. Most existing collaborative filtering algorithms predict ratings based on user similarity and item similarity, without considering the influence of features such as book authors and user age on ratings. This limitation leads to insufficient accuracy in rating predictions. To address this issue, this paper proposes a rating prediction algorithm based on LightGBM and text convolutional neural networks. Firstly, the gradient boosting tree algorithm LightGBM is employed to calculate the impact of all features on ratings. High-impact features are selected and input into the neural network. For features containing semantic information, such as book titles, text convolutional neural networks are used for processing. Subsequently, feature vectors for users and books are trained, enabling the prediction of book ratings.