False comment identification method based on rolling type cooperative training
A technology of collaborative training and recognition methods, applied in the field of false review recognition, can solve problems such as time-consuming and laborious, low recognition accuracy, and lack of manual annotation in standard data sets
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
experiment example
[0129] (1) Data source:
[0130] The present invention obtains the original experimental data set from the yelp review website. The original experimental data set includes multiple fields such as user ID, total number of comments, comment content, comment level, comment time, etc., and a total of 5854 comment texts. And with the help of the false comment filtering system of the yelp review website, the false comments are marked, and the experimental data set is shown in Table 1.
[0131] Table 2 Experimental data set
[0132] type of data Comments User number real comment 5076 4231 fake review 778 743 total number of comments 5854 4974
[0133] (2) Experimental platform
[0134] The algorithm used in this application adopts Win64-bit server operating environment; processor Intel(R) Core(TM) i5-5200UCPU @2.20GHz 2.20GHz; running memory 8G; Python3.7.0 version; gensim3.8.0 version; scikit-learn0.20.1 version; text paragraph vector traini...
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