A specified information push method based on sentiment classification of webpage text data

Abstract

The invention discloses a webpage text data sentiment classification designated information push method which includes acquiring sentimental emotional words of the current webpage text data, extracting the emotional words as characteristic data, and generating characteristic vectors according to the extracted emotional words; inputting the characteristic vectors into a pre-built classification model and computing to obtain sentiment type of the current webpage text data; pushing the designated information matched with the sentiment type to the current webpage according to the sentiment type of the webpage text data. According to the webpage text data sentiment classification designated information push method, the sentimental emotional words of the webpage text data are extracted for generating the corresponding characteristic vectors, the webpage text data, which are of increased click rate of the corresponding designated information, are taken as training data for training to obtain the classification model, thus, users' requirements are met while the click rate of the recommended designated information is increased.

Description

technical field [0001] The present invention relates to the field of computer application technology, in particular to a designated information push method based on sentiment classification of webpage text data. Background technique [0002] In recent years, the Internet has become the preferred platform for people to express their opinions, search for information, and conduct information interaction. The analysis results are used to recommend relevant information, so that the recommended content can adapt to the needs of users. At present, most of the methods for recommending webpage information use the browsing records in historical data to recommend information. Although this is more in line with the prediction of big data analysis, it cannot target the actual impact of webpage text data on users or the interest they arouse. Therefore, it is impossible to truly grasp the actual needs of users, especially the impact of web page text data on user emotions. Therefore, sent...

AI Technical Summary

Problems solved by technology

These emotional classifications belong to the user's classification of text, and have little to do with the current user's emotional state. As a result, in most cases, they cannot arouse the emotional resonance of the viewer, that is, it is difficult to influence the user to watch the recommended information.

On the other hand, most of the existing classification algorithms use the method of supervised learning, which requires a large amount of training corpus, and these training corpus and test data are manually labeled offline.

This will not only cause a lot of waste of human and financial resources, but also cannot adapt to the ever-changing needs of Internet data

In addition, the existing classification algorithms not only have high complexity, but also have a large amount of calculation, which is not suitable for online real-time recognition

Moreover, it is impossible to accurately grasp the impact of webpage text data on users by classifying webpage text data based solely on the conventional emotional categories judged by humans.

[0004] Therefore, in the process of realizing the present invention, the inventor found that the prior art has at least the following defects: the specified information recommended by the web page cannot fully meet the needs of users, resulting in a low click-through rate of the recommended specified information; most of the recommended information is based on user Browsing records or simple analysis of web page text information, and the correlation with the user's click on the specified information is not high

Images