Semi-supervised automatic aspect extraction method and system based on domain information

Abstract

The invention discloses a semi-supervised automatic aspect extraction method based on domain information. The semi-supervised automatic aspect extraction method comprises the steps of network information crawling, information pre-processing, keyword extraction, comment document recombination and fine-grit mark LDA learning. The invention further discloses a semi-supervised automatic aspect extraction system based on the domain information. The semi-supervised automatic aspect extraction system based on the domain information comprises a network information crawling module, an information pre-processing module, a keyword extraction module, a comment document recombination module and a fine-grit mark LDA learning module. By the adoption of the semi-supervised automatic aspect extraction method and system based on the domain information, all extracted aspects of a commodity are more clear and more definite, and the differences between the aspects are more clear; a generated aspect structure (order and content) generated through the semi-supervised automatic aspect extraction method and system can be kept consistent with a commodity aspect structure which is predefined in a seed word set, so that the semi-supervised automatic aspect extraction method and system have the advantages that semantic clustering can be conducted on different expressions used by a consumer for description of the same commodity aspect, and human interference can be reduced in the process of opinion mining of the commodity.

Description

technical field [0001] The present invention relates to a commodity opinion mining technology, in particular to a semi-supervised aspect automatic extraction method and system based on domain information. Background technique [0002] With the increasing popularity of e-commerce, more and more consumers choose to buy goods and services online, especially in recent years, with the vigorous development of different models (B2B, B2C, C3C, etc.), various types of electronic products in different fields Business websites continue to emerge, competition continues to intensify, and user demands continue to improve. Manufacturers and sellers always try to obtain the public or consumers' evaluations of their products and services in a timely manner in order to improve product quality and sales; and potential consumers also want to know the current consumption before enjoying a service or buying a product. In order to choose the product that really suits you. Automated opinion minin...

AI Technical Summary

Problems solved by technology

Third, the opinion mining system can also process documents in multiple languages, which is difficult for ordinary people to meet the requirements of mastering multiple languages ​​in traditional methods

The main deficiency of the former is that it cannot classify semantically related terms describing the same aspect of the product, which makes this type of method unable to help users quickly and intuitively understand the characteristics of various aspects of the product in a structured way; for the latter, Most methods use an unsupervised learning method, which leads to the following shortcomings and deficiencies:

[0004] 1. The granularity and classification standards of model generation may be contrary to people's cognitive habits, making the results difficult to understand

[0005] 2. The aspect sequence generated by the unsupervised model cannot maintain a stable structure each time, making it difficult to apply in automated analysis algorithms

[0006] 3. Since most of the reviews contain the same or similar product aspects, it will make it difficult for the topic model method based on the word co-occurrence principle to clearly distinguish each related but different aspect

Images