Machine learning-based commodity comment data sentiment analysis method

Abstract

The invention discloses a machine learning-based commodity comment data sentiment analysis method. The method comprises the steps of collecting and extracting commodity comment data; preprocessing thedata, wherein the preprocessing comprises text duplicate removal, mechanical compression word removal and short sentence deletion; based on a Jieba word segmentation method, performing text word segmentation on the preprocessed data; building a sentiment analysis model: generating word vectors based on NNLM (Neural Network Language Model) training, and establishing a semantic network; and based on an LDA topic model, performing semantic mining, and generating a topic in an unsupervised manner. The unsupervised sentiment analysis method is realized; and a result shows that the sentiment analysis mode can effectively analyze comment sentiments of users.

Description

technical field [0001] The invention relates to the technical field of emotion analysis of review data, in particular to a method for emotion analysis of commodity review data based on machine learning. Background technique [0002] Along with the development of e-commerce, a large amount of user data is growing day and night. Although the storage and maintenance of these data have brought a lot of enterprise costs and technical difficulties, the hidden commercial value is immeasurable. Among the e-commerce data, the data that can most intuitively reflect the user's views on the product and the e-commerce platform is the product review data. These data can not only reflect the user's opinion on the product, but also extract the user's emotional information , to provide commercial reference value for more users and e-commerce platforms, to provide a way to recommend products, improve products and compare similar products with each other. [0003] The method and process of se...

AI Technical Summary

Problems solved by technology

[0009] Nowadays, the sentiment analysis of short Chinese texts is mostly based on Chinese word segmentation, but there are some rhetorical techniques such as rhetorical questions or double negatives in the use of Chinese, such as: "It's not impossible", "Why are so many people I think it’s good”, or the first half expresses negation, and the second half expresses some complex semantic sentences: “The quality is not good and the appearance is not good-looking, but overall it is still very affordable

Images