Commodity performance evaluation method through network evaluation test guiding

Abstract

The present invention provides a commodity performance evaluation method through network evaluation test guiding. The method comprises: a, obtaining all the evaluation tests of the commodity from the network aiming at the commodity requiring performance evaluation; b, performing preprocessing of the obtained commodity evaluation test, comprising works such as removing stop words, performing participle, marking phrase and the like; c, obtaining the evaluation object of the commodity according to the processed evaluation test, namely the commodity features which clients may pay attention to, and calculating the weight of the evaluation object; d, performing preprocessing of each comment of the commodity, constructing the evaluation object vector, and performing normalization processing; e, extracting the emotion words related to the evaluation object, and giving emotion polarity, and extracting the privative words and the adverb of degree related to the emotion word and giving a weight; and f, according to the obtained data, calculating the emotion polarity of each comment so as to obtain the emotion polarity of all the evaluation texts.

Description

technical field [0001] The invention relates to a commodity performance evaluation method, which is a commodity performance evaluation method guided by network evaluation texts. Background technique [0002] With the rapid development of e-commerce, online shopping has become a common phenomenon. However, due to the lack of direct contact with commodities in online shopping, checking other people's comments on commodities has become an important way for consumers to obtain commodity information. [0003] However, the current product evaluation system is not satisfactory. Most of the products adopt the method of good, medium and bad reviews. Although some products have parameters such as materials and other performance parameters, there are often performance characteristics that customers are concerned about. It is not included in the evaluation. At this time, it is necessary to check the comments of other customers one by one to dig out the information you need, which is ext...

AI Technical Summary

Problems solved by technology

[0003] However, the current product evaluation system is not satisfactory. Most of the products adopt the method of good, medium and bad reviews. Although some products have parameters such as materials and other performance parameters, there are often performance characteristics that customers are concerned about. It is not included in the evaluation. At this time, you need to check other customers' comments one by one to dig out the information you need, which is extremely time-consuming

Images