Machine learning-based method for analyzing customer satisfaction degree of e-commerce products

Abstract

The invention discloses a machine learning-based method for analyzing the customer satisfaction degree of e-commerce products. The method comprises the steps of: obtaining e-commerce product review text and carrying out data preprocessing such as word segmentation, part-of-speech annotation and the like; selecting Chinese chunk mark symbols to manually annotate word segmenting results; training amodel on the basis of a Lib-SVM (Library for Support Vector Machine) tool, obtaining nominal Chinese chunks to serve as candidate product features and calculating TF-IDF (term frequency-inverse document frequency) value filtering features; constructing an emotional dictionary and calculating the emotional score of each feature of a product; training a word vector language model and obtaining vector representations of the product features; and carrying out customer satisfaction degree clustering on the product features on the basis of word vector similarity degree and calculating a total score.The method disclosed by the invention can be applied to product review text-based product recommending systems and has the beneficial effects that through the customer satisfaction degree analysis, five aspects of the product features are clustered and the product feature dimension and sparsity are reduced, so that the designed recommending systems have the performance of being faster and more accurate.

Description

technical field [0001] The invention relates to the fields of natural language processing and data mining, in particular to a commodity evaluation method based on comment text. Background technique [0002] With the rapid development and popularization of Internet technology, network information has exploded. In the era of information "explosion", the traditional store sales model can no longer meet the needs of consumers, and e-commerce has emerged as the times require. The emergence of e-commerce, on the one hand, expands the scope of consumer goods to buy; on the other hand, consumers can express their views and opinions on e-commerce products. Customer satisfaction, also called customer satisfaction index, is the abbreviation of the customer satisfaction survey system in the service industry. It is an index obtained by customers after comparing the perceived effect of a product with its expected value. Reflection of customer satisfaction. By mining the review informat...

AI Technical Summary

Problems solved by technology

At present, there are few effective methods for evaluating e-commerce products based on customer satisfaction

Images