Big data-based online sales commodity emotional tendency analysis method

Abstract

The invention discloses a big data-based online sales commodity emotional tendency analysis method. In the method, an emotion score of a certain kind of commodities is calculated by the following steps of B1) acquiring online sales commodity links belonging to the same kind of commodities on a network platform and data information including brand data and comment data corresponding to the online sales commodity links; B2) through an emotion tendency analysis method based on a comment analysis dictionary, carrying out emotion analysis on each collected comment of each online sales commodity link, and carrying out calculation to obtain an emotion score of each comment under each online sales commodity link; B3) calculating a commodity emotion score of each online sales commodity link based on the emotion score of each comment under each online sales commodity link; and B4) calculating the emotion score of each brand under the same kind of commodities in combination with the obtained commodity emotion score and brand data of each online sales commodity link. Qualitative comments of the user are converted into emotion scores representing the quality of the commodities, and the emotionscores can be used as references for customer selection, and are more distinguishable.

Description

technical field [0001] The invention relates to an analysis method for online sales commodities, in particular to an analysis method for emotional tendency of online sales commodities. Background technique [0002] With the continuous development of social life, the online sales model is also constantly evolving and evolving. Online shopping has gradually penetrated into thousands of households. More and more people accept and choose to purchase needed commodities and materials through various online sales platforms. [0003] A major service feature of online sales products is that users can comment on the purchased products through user evaluations / reviews, including product quality, logistics services, user experience and other information can give comments and scores for each transaction, etc. , so as to provide a reference for other customers when purchasing, and also provide a certain degree of binding force on the products and services provided by the seller. [0004]...

AI Technical Summary

Problems solved by technology

[0004] However, for the dazzling array of brands, the dazzling array of online sales links, and the thousands of comments data under each sales link, customers often cannot directly and intuitively extract the required accurate information from the massive comments, and form a relative objective judgment

At the same time, in the review data of online marketing products, most of the negative reviews account for a small proportion, and the proportion of positive or default positive reviews is relatively high. Buried in a large number of favorable comments, on the other hand, the favorable rate given by different sales links according to the proportion of positive and negative reviews is also very different. It is difficult for customers to get close to or the same favorable rate (or favorable rate) such as 98%. In the distinction of 1 to 2 points such as 99%, the difference of products or services can be perceived. For some rating system review systems, it is also difficult for customers to distinguish between similar or identical ratings such as 4.8, 4.9, etc. Perceived differences in products or services

Different online marketing platforms use different scoring methods, and the scores obtained are difficult to directly compare with each other

For example, it is difficult for users to judge which is better, 95% or 4.9

Images