Social media user demographic attribute prediction method based on multi-model stack fusion

Abstract

The invention relates to a social media user demographic attribute prediction method based on multi-model stack fusion, and three demographic attributes including gender, age and region of a user arepredicted. The prediction of the three demographic attributes comprises the steps of (S1) user feature extraction, (S2) model training, and (S3) multi-model fusion to obtain a prediction result. The feature extraction in the present invention is not only for the text content of user Weibo, but also relates to statistical features, time information features and social relationship features, and theaccuracy of prediction is ensured. The mode of multi-model stack fusion is used to fuse logistic regression, random forest, and XGBoost models, a generalization error can be effectively reduced, andthe prediction accuracy is greatly improved.

Description

technical field [0001] The present invention relates to the technical field of model prediction, in particular to a method for predicting social media user demographic attributes based on multi-model stack fusion. Background technique [0002] With the continuous advancement of my country's informatization process and the continuous development of network technology, the Internet and communication terminals are speeding up their integration into modern life. The speed of development, and gradually become an independent, new way of information exchange and dissemination, and constantly changing people's lives. The rapid development of social media, while providing social convenience for people, has also had a huge impact and influence on advertising media. How does the advertising media use the characteristics of social media users to mine hidden user characteristics such as gender, age, region, etc. by mining the user’s behavior preferences on social media, and deliver more ...

AI Technical Summary

Problems solved by technology

[0004] 1. Since there are a large number of user-generated content such as advertisements, sharing, news, etc. in the content published on social media, there will be large errors in only text mining

[0005] 2. High-dimensional data problems

The traditional text classification method generally extracts the TFIDF features of the text, and the dimension can be as high as hundreds of thousands of dimensions. For the traditional SVM classification model, it will cause extremely long training time and cannot effectively converge.

[0006] 3. There is an imbalance in the data, most of the Weibo users are male

Images