Comment information quality evaluation method, system, comment information processing method and system

Abstract

The invention discloses a comment information quality evaluation method and system. The method includes the following steps that: an entire comment text is obtained; equal-information amount short sentence segmentation is performed on the entire comment text, so that short sentence units can be obtained; the information entropy-based information values of the short sentence units are determined; the weights of the information values of the short sentence units are adjusted on the basis of industry information; and the quality of the entire comment text is determined according to the information values of the short sentence units. The invention also discloses a comment information processing method and system. With the methods and systems of the invention adopted, the objective and accuratequality evaluation of comment information can be realized, and thus, more effective reference information can be provided for user transactions.

Description

Technical field [0001] The present invention relates to the technical field of information processing, in particular to a method and system for evaluating review information quality, and also to a method and system for processing review information. Background technique [0002] O2O (Online To Offline, online-offline / online-to-offline) refers to the combination of offline business opportunities with the Internet, making the Internet a platform for offline transactions. Different from the traditional consumer direct consumption model at merchants, in the O2O platform business model, the entire consumption process is composed of online and offline two parts. Online platforms provide consumers with consumer guides, preferential information, convenient services (reservations, online payments, maps, etc.) and sharing platforms, while offline merchants focus on providing services. [0003] In the O2O model, consumers will feedback their consumption experience to the online platform, tha...

AI Technical Summary

Problems solved by technology

[0004] But in reality, on the one hand, due to the different amount of information and content covered by user reviews, the quality of review information will also vary, and some reviews are not only worthless, but also affect the experience of subsequent consumers; On the other hand, due to the large amount of review information and the limitations of the review display interface, it is more difficult for users to find useful information in the massive reviews

Although many platforms display review information with recent reviews or useful votes, neither of these two methods can guarantee the stability of the quality of new review information displayed to users

Images