Part-of-speech-tagging-based dictionary construction method applied in shopping comment emotion analysis

Abstract

The invention discloses a part-of-speech-tagging-based dictionary construction method applied in shopping comment emotion analysis. The method comprises the steps of conducting pre-treatment on text data of a shopping comment, in other words, conducting segmentation and word segmentation on a comment text, filtering out words which are not used any more, and partitioning shopping domains; constructing a basic emotion dictionary and a network buzzword emotion dictionary; taking a shopping comment corpus as a data set, conducting part-of-speech tagging on the data set, extracting words with the part-of-speech as habitually used words, adverbs and adjectives as candidate words, selecting new emotion words as domain emotion words by calculating the PTF-IDF values of the candidate words, and adding the domain emotion words to a domain emotion dictionary. The domain emotion dictionary is combined with the basic emotion dictionary and the network buzzword emotion dictionary, emotional characteristic screening and extraction are conducted on the shopping comment, and the emotion classification of the shopping comment is studied. It is shown through experiments that the method is high in accuracy rate, free of limitation of shopping domains and more suitable for practical application.

Description

technical field [0001] The invention relates to the field of natural language processing or conversion in data processing methods suitable for specific functions, and in particular to a dictionary construction method based on part-of-speech tagging in emotional analysis of shopping reviews. Background technique [0002] With the vigorous development of the Internet, the rise of e-commerce has attracted more and more users to start shopping online, experiencing the "stay at home" and "cheap and beautiful" brought by online shopping. At the same time, users also express their subjective views and opinions on commodities by commenting on purchased commodities in online shopping malls. However, since online shopping has no geographical restrictions, while bringing convenience to users, it also prevents users from directly touching and understanding the quality of the products, which may cause differences between the descriptions of the products in online shopping malls and the a...

AI Technical Summary

Problems solved by technology

The algorithm used in this method is complex and requires a large amount of appropriate and labeled corpus when training the sentiment feature classifier

[0006] The main disadvantages of the invention patent with the publication number CN104731923A and the name "Construction Method of Internet Commodity Review Mining Ontology Thesaurus" are: 1. It does not use a general stop vocabulary, but calculates the feature frequency and document frequency in the experimental data. , take words with high values ​​as stop words, which are prone to deviations in the process, and words with emotional tendencies are lost, which affects the experiment; second, in the process of constructing the thesaurus, it does not consider other part-of-speech words except nouns Impact on Product Review Analysis

[0007] The main disadvantages of the invention patent with the publication number CN103207855A and titled "Fine-Grained Sentiment Analysis System and Method for Product Review Information" are as follows: 1. The sentiment analysis system needs to be trained with a large number of marked texts, and it needs to be updated regularly. Increased a lot of manpower and time consumption; second, did not consider the impact of stop words and Internet buzzwords on sentiment analysis; third, relied too much on collocation and combination dictionaries in the database, which made the calculation process complicated, and did not consider words of different parts of speech Sentimental Tendency in Review Text

[0008] In summary, the existing sentiment classification research for shopping reviews is not accurate enough to meet the needs of practical applications.

Images