Classification method and system of emotions of news readers
A news and emotion technology, applied in the field of information classification, can solve the problems of time-consuming and labor-intensive, and it is difficult to improve the performance of news readers' emotion classification
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] This embodiment provides a classification method of news reader sentiment, figure 1 The flowchart of this embodiment is shown, including:
[0037] Step S101: Obtain news text and comment text from the target corpus, obtain the word feature information of the news text and the comment text, and merge the word feature information of the news text and the comment text;
[0038] Get the news text and the comment text, and the news text and the comment text correspond one by one. When obtaining the word feature information of news text and comment text, since there is no obvious word segmentation information between words in the sentence, the text needs to be segmented, and the ICTCLAS word segmentation tool can be used to segment it. When fusing the word feature information of the news text and the comment text, in order to distinguish the news text feature and the comment text feature in the fusion feature, a preset symbol can be used to add one of the types of features, such a...
Embodiment 2
[0063] This embodiment provides a classification system of news reader sentiment, image 3 Shows a schematic structural diagram of this embodiment, including:
[0064] Word feature information fusion module 101, corpus format conversion module 102, corpus classification module 103, sample update module 104, and annotation verification module 105;
[0065] The word feature information fusion module 101 is used to obtain news text and comment text from a target corpus, and obtain the word feature information of the news text and the comment text, and combine the information of the news text and the comment text Word feature information is fused;
[0066] The corpus format conversion module 102 is used to convert the fused word feature information into usable corpus in a format corresponding to the maximum entropy model;
[0067] The corpus classification module 103 is configured to divide the available corpus into training corpus and test corpus according to preset rules, and divide the...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com