Malicious comment information identification method and device

Abstract

The present invention proposes a method and device for identifying malicious comment information, wherein the method includes: acquiring user comment information to be released inputted by the user into an application component, and extracting keywords from the user comment information to be published; The sensitive word data model determines that the keyword is a sensitive word; according to the sensitive word, it is determined that the user comment information to be published is the malicious comment information. Therefore, malicious comment information can be automatically identified according to sensitive words, the identification accuracy is high, and there is no need to invest a lot of manpower and time, and the processing efficiency of identifying malicious comment information is greatly improved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method and device for identifying malicious comment information. Background technique [0002] With the development of Internet technology, various Internet platforms emerge in an endless stream. Users can express their opinions and provide their own experience for reference by others through the Internet platform. For example, users can share their knowledge and experience through Tieba, Zhihu, etc. ; Publish your own shopping and product experience after purchasing items through a shopping website; publish corporate review information on the corporate credit query platform that provides corporate information query. However, there are many users who, out of unfair competition with competitors, make baseless attacks and malicious slanders, thereby causing unfair treatment to the reviewers and misleading other users' decision-making judgments. [0003] At present, after us...

AI Technical Summary

Problems solved by technology

However, there are many users who baselessly criticize and maliciously slander out of unfair competition with competitors, thereby causing unfair treatment to the reviewers and misleading other users' decision-making judgments

[0003] At present, after users comment on the commented person and post the comment information, if the commented person thinks it is a malicious comment and reports it, manual review and argumentation is required. Enterprises need to invest a lot of manpower and time in identifying malicious comments, and the processing efficiency is low.

Images