An Emotionally Unstable User Detection Method for Regular Video Comments
A technology for stabilizing users and detection methods, applied in the field of review text classification, can solve the problems of unresolved reviewers, changes, etc., and achieve the effect of solving the psychological problems of teenagers, good social benefits and economic value
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0105] (1) Data collection. A web crawler is used to obtain 349,612 regular comments of time-synchronized comments on the bilibili website. The data of the comment dataset comes from videos of 13 chapters of a series of works, which are stored from EP1-EP13 in the order of video release, and the interval between video updates and releases is 7 days , the total number of days that comment data persists is 545. Since there is currently no public and reliable bilibili website time-synchronized comment and regular comment sentiment classification dataset, in order to train and verify the sentiment analysis method, 9000 regular comments were randomly crawled as a sentiment classification dataset and marked.
[0106] (2) When users post regular comments, they can use the preset emoticons on the website, and add emoticons to the comment text to form a richer expression. Collect and organize the emoticon packages of the website, build the corresponding emoticon and text comparison ta...
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