Microblog popularity prediction method based on active learning

Abstract

The invention provides a microblog popularity prediction method based on active learning. The method comprises the following steps: crawling a related microblog data set by utilizing a Sina microblogAPI; utilizing a k-Means algorithm initializes the unmarked data set into a training set L; performing feature extraction on the training data to obtain a feature vector; training an improved model based on active learning of a support vector machine according to the extracted feature vectors, and selecting samples with uncertainty, diversity and representativeness from an unmarked sample set according to the trained multi-classification model; calling the screened samples as information vectors, and marking the information vectors to experts; and adding the marked training data into the initial training set L, and circulating the process until the performance of the model reaches a stable state to obtain the microblog popularity prediction model. According to the method, the redundancy problem is reduced, the abnormal value problem is reduced, the number of marks of training samples is reduced, and meanwhile a good prediction effect is obtained under the condition that training data is few.

Description

technical field [0001] The invention relates to a prediction method, in particular to a microblog popularity prediction method based on active learning, which belongs to the field of machine learning. Background technique [0002] Microblog is a typical representative of social network, and it is a way for people to obtain, share and exchange information. The emergence of microblog is quietly changing the lives of modern people. Weibo attracts the attention and use of a large number of users and mass media platforms. Weibo users share information with their fans by forwarding other people's Weibo, and the fans of this user can continue to share information by continuing to forward Weibo. It also enables messages to be disseminated in large quantities and quickly through the Weibo platform to achieve information sharing. Through the Weibo platform, people can socialize with people who are far away from their own circle of life and are interested in them, and can express thei...

AI Technical Summary

Problems solved by technology

However, traditional machine learning methods also have great limitations. It requires a large amount of manually labeled data sets for model training, which requires a lot of cost, time and human resources to obtain labeled data sets.

Images