Comment assessment method, device, equipment and storage medium

Abstract

The embodiment of the invention provides a comment assessment method, device, equipment and computer readable storage medium. The comment assessment method comprises the steps that first vectorizationrepresentation of a set of text items in comments referring to a target object is acquired. The method further comprises the steps that semantic features of at least two continuous text items in theset of text items are extracted based on the first vectorization representation, importance degree of the at least two continuous text items in a context of the comments is determined, and based on the importance degree and the semantic features, the degree of the comments facilitating user assessments for the target object is determined. By adopting the method, the automatic, efficient and correct assessments for comment value are achieved.

Description

technical field [0001] Embodiments of the present disclosure generally relate to the field of interaction, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for evaluating reviews. Background technique [0002] With the development of network technology, more and more Internet platforms support the generation of user-generated content (UGC). Therefore, users can publicly comment on specific objects in many Internet platforms. Such comments not only enrich the relevant information of the commented object (such as products, services, content such as news, video, short text, etc.), but also help other users understand the quality and characteristics of the commented object. [0003] Since comments are usually generated by users themselves, not all comments can provide other users with useful or valuable information about the commented object, and some comments may even have nothing to do with the commented object. If there are too ma...

AI Technical Summary

Problems solved by technology

If there are too many comments on the commented object, useful comments and useless comments are mixed together, it is difficult for other users to quickly obtain useful information from numerous comments, and useless information is not conducive to the correct evaluation of the commented object by the provider or other third parties (e.g. whether it is worth recommending, etc.)

Images