Fine-grained sentiment analysis system and method specific to product comment information

Abstract

The invention discloses a fine-grained sentiment analysis system and method specific to product comment information. The system comprises a user interface, a product comment information training sample data base, a loading module of relevant dictionaries such as sentiment dictionaries, a text preprocessing module, a characteristic extraction module, a sentiment analysis model training module, a sentiment tendency judging module and a feedback module. A user can store and manage various tagged product comment information training samples and perform processes of sentence segmentation, word segmentation, part-of-speech tagging, syntactic analysis and the like by means of the system. The user can also add user-defined sentiment dictionaries to perform characteristic extraction and vectorization on well processed text information, train sentiment analysis models and use the sentiment analysis models to perform sentiment tendency judgment on vectorized text information. The system feeds sentiment analysis results back to the user to support the user to correct and store the analysis results.

Description

technical field [0001] The invention relates to the field of sentiment analysis of Chinese text, in particular to an entity-level fine-grained sentiment analysis system and method for product review information. Background technique [0002] Product review information generally refers to comments or opinions expressed by users or consumers on a certain product or a certain attribute of the product. These comment information often have a strong subjective emotional color, which reflects the user's subjective feelings about the product or a certain attribute. [0003] On the one hand, with the vigorous development of Web2.0, Internet users have changed from passively receiving Internet information to actively creating Internet information; on the other hand, the rapid development of e-commerce has changed people's shopping habits, starting from offline to online, The popularity of online shopping has brought about the rapid expansion of such product review information. These ...

AI Technical Summary

Problems solved by technology

[0008] The existing sentiment analysis technology mainly has the following deficiencies: A) The granularity of sentiment analysis is relatively large, and it only makes analysis and judgment on the emotional tendency of the entire sentence or the entire article. The more fine-grained information causes the loss of a large amount of valuable information in the text, and the information contained in the text cannot be fully utilized; B) the existing few entity-level sentiment analysis technologies separate the identification of entities and the judgment of emotional orientation It is carried out as two independent steps, ignoring the connection between entity recognition and emotional tendency judgment, so that the final joint accuracy is not high; C) It is necessary to manually label the text in the training data set, which will consume a lot of time and manpower resources, and due to the different cognition of the markers, it is inevitable that there will be contradictory marking results during the marking process, which will affect the training effect; It is directly output to the user without subsequent processing, and lacks the process of re-learning the wrong judgment results; E) lack of research focusing on the sentiment analysis of product review information, and this kind of information is very rich and easy on the Internet. At the same time, it also contains huge commercial value and business opportunities. Reasonable and full use of this information can create huge value and benefits for businesses and society

Images