Method for quantitatively predicting microblog forwarding breadth and depth

Abstract

The invention belongs to the technical field of information and data processing, and discloses a method for quantitatively predicting microblog forwarding breadth and depth, which comprises the following steps: dividing extracted features into user features, microblog features and social features, and storing the user features, the microblog features and the social features into a file; reading all processed data, taking 70% of the data as a training data set, and taking 30% of the data as a test data set; extracting features useful for the training model in the training data set; establishing a model by using an improved random forest algorithm, and predicting the forwarding breadth and depth of each microblog; and testing the accuracy of the algorithm by using test set data, and calculating an average absolute percentage error and prediction precision. According to the invention, the propagation breadth and depth of user forwarding behaviors are predicted by using a machine learning algorithm; and the improved random forest algorithm is high in prediction precision, small in fluctuation, and insensitive to various characteristic changes, which indicates that the prediction result has a high reference value.

Description

technical field [0001] The invention belongs to the technical field of information and data processing, and in particular relates to a method for quantitatively predicting the forwarding breadth and depth of microblogs. Background technique [0002] At present: some scholars at home and abroad have studied the forwarding behavior of Weibo users, trying to analyze various factors that affect the forwarding behavior. The forwarding behavior of users is the result of the combined action of many factors, and the influencing factors are summarized as information content factors and group influencing factors. The former mainly includes the characteristics of the information content itself and the degree of agreement between the information content and the user's interests; the latter mainly includes the influence of the information publisher on the user and the influence of other information forwarders on the user. According to the different influencing factors of prediction, use...

AI Technical Summary

Problems solved by technology

[0005] (1) The research on Weibo users’ reposting behavior mainly focuses on whether Weibo will be reposted, but there are few studies on quantitative prediction of Weibo dissemination scale and depth

[0006] (2) In the research on the prediction of the number of retweets on Weibo, the number of retweets on a specific topic is generally predicted, and th...

Images