Microblog user age prediction method based on LSTM and LeNet fusion

Abstract

The invention relates to a microblog user age prediction method based on LSTM and LeNet fusion, and belongs to the technical field of information prediction. The method comprises the following steps of crawling data, crawling the information of a microblog user, and storing the information in a local computer; carrying out word segmentation processing on the microblog text, after the text contentword segmentation and stop word filtering, vectorizing the word segmentation results; building an LSTM, adopting a long short-term memory model (LSTM) to model the vector, and predicting the age of the user; preprocessing the images, unifying the images into the same size; establishing the LeNet, establishing a LeNet model, enhancing the picture data of the data set, converting the picture data into the tensor, and testing to select a model with the highest hit rate; and integrating the results, integrating the trained text processing module model and the picture processing module model. Compared with the prior art, the problem that a previous model is difficult to follow the trend is solved, the recognition accuracy is improved, and the method has a wide application prospect in the fieldsof user operation, precise advertisement marketing, user analysis, data analysis, recommendation systems and the like in the future.

Description

technical field [0001] The invention relates to a microblog user age prediction method based on the integration of LSTM and LeNet, which belongs to the field of information prediction technology and is applicable to user operation, precise advertising marketing, user tendency analysis, network content monitoring and the like. Background technique [0002] User age prediction is a sub-problem of constructing user portraits. User portraits are actually labeling the personal information of Weibo users. Building personas has two benefits. First, it can store microblog user information in a structured way, which is convenient for computers to identify and calculate them. Second, labels are accurate and non-ambiguous, which can help human processing and understanding. User portraits have varying degrees of application in user operations, precision advertising marketing, user analysis, data analysis, and recommendation systems. [0003] Weibo has become one of the most popular s...

AI Technical Summary

Problems solved by technology

The characteristics of this method are, first, use a multi-modal model including two modalities of text and pictures to process text and pictures separately, put more user information into the prediction process, and solve the problem that the information of a single user is relatively small. underutilized or underutilized

Images