Classification method and system of emotions of news readers

Abstract

The invention discloses a classification method and system of emotions of news readers. The classification method comprises the following steps: acquiring a news text and a comment text as well as word characteristic information from target linguistic data; fusing the word characteristic information and converting the word characteristic information into available linguistic data with a corresponding format of a maximum entropy model; dividing the available linguistic data into training linguistic data and testing linguistic data according to a pre-set rule, and dividing the training linguistic data into marked samples and unmarked samples; training the marked samples to obtain a maximum entropy model; classifying emotion classes of the unmarked samples by using the maximum entropy model to obtain posterior probability of each emotion class corresponding to the unmarked sample; carrying out emotion class marking on the unmarked samples with the preset quantity and maximum uncertainty of the posterior probability to form new marked samples, and updating the current marked samples and unmarked samples; and circulating the last step until all the unmarked samples are marked. The classification method and system can be used for efficiently classifying the emotions of the news readers when the scale of marking the linguistic data is relatively small.

Description

Technical field [0001] The present invention relates to the field of information classification, in particular to a method and system for classifying news reader emotions. Background technique [0002] The rapid development of Web technology has promoted the continuous transformation of the Internet to an "interactive Internet", and has gradually become an important carrier of various information in society. With the rise of various social platforms, more and more user-generated content on the Internet has produced a large amount of text information, such as news, microblogs, and blogs. Faced with such large and emotionally expressed text information, it is entirely possible to consider serving people by exploring their potential value. In order to process and analyze these information resources, sentiment analysis has become a basic hot research task in the field of computational linguistics. Here, emotions specifically refer to subjective psychological feelings and objective ...

AI Technical Summary

Problems solved by technology

[0004] Most of the previous research work is based on fully supervised learning methods. The premise of fully supervised learning methods is that there is a sufficiently large-scale labeled corpus. However, obtaining large-scale corpus is a time-consuming and labor-intensive task. In small-scale It is difficult to improve news reader sentiment classification performance when labeling samples

Images