A Method of Attribute Prediction for Movie Review Website Users Based on Deep Neural Network

Abstract

The invention discloses a method for predicting attributes of movie review website users based on a deep neural network, and belongs to the fields of data mining, machine learning, and the like. The present invention decomposes the matrix of the sparse user rating data in the movie review website, decomposes the user rating matrix into a user-feature matrix and a movie-feature matrix, uses these two matrices to partially fill the user vector, and the filled user rating data is used as User's feature vector. The user's feature vector data is input into the fully connected deep neural network, combined with multi-task learning technology, the network model is trained, and the label scores of each task are obtained; decision analysis is performed according to the label scores of each task, and the final classification result is obtained. The invention uses the deep neural network technology to automatically predict the attributes of movie review website users, solves the problem of data sparsity, and has higher classification accuracy and efficiency.

Description

technical field [0001] An attribute prediction method for movie review website users based on a deep neural network, which is used to predict various attributes-people's preference for movies based on movie reviews, and belongs to the technical fields of data mining, deep learning, and matrix decomposition. Background technique [0002] Deep learning originates from artificial neural networks. With the help of modern neurological ideas, it can simulate the structure and mechanism of neurons in biological brains and build artificial neural network models. Deep learning is to establish multiple hidden layers between the input layer and the output layer of the network to form a complex neural network, optimize and adjust the parameters between the networks through unlabeled or labeled learning of sample data, and solve the problem of classification after regression. question. [0003] The essence of deep learning is to build a multi-layer neural network model to learn useful f...

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to provide a method for predicting attributes of movie review website users based on a deep neural network; to solve the prediction effect caused by the limitations of the number of labels or categories of tasks and data sparsity in the prior art bad question

Images