Text orientation analysis method and product review orientation discriminator on basis of same

Abstract

The invention discloses a text orientation analysis method which comprises the following steps of: preprocessing a review text; identifying a dependency relation structure of the Chinese syntax; calculating content polarity values of sentiment words; completing two-tuples extraction of evaluated objects and evaluation words and determining a slave relation between the evaluated objects; weighting and summing orientation values of the sentiment words to obtain an orientation value of a sentence so as to implement discrimination on orientation of a sentence level; discriminating appraising orientation of sentiment in the review by positive and negative polarity values of the sentence level; and according to the size of a polarity absolute value, discriminating intensity of appraising sentiment in the review. A product review orientation discriminator comprises an acquisition module, a preprocessing module, a syntactic analysis module, a sentiment calculating engine, a two-tuples mining engine, a content controller and a sentiment discriminator. According to the invention, a combined sentiment dictionary is combined and a domain ontology is added into text orientation analysis; accuracy of polarity calculation of the sentiment words and (the evaluated objects and the evaluation words) two-tuples extraction is improved; and orientation analysis on product reviews in a forum is implemented.

Description

technical field [0001] The invention relates to the technical field of text tendency analysis, in particular to a text tendency analysis method and a forum-oriented commodity review tendency discriminator based on the method. Background technique [0002] With the rapid development of the Internet, especially the gradual deepening of the Web2. An invisible virtual society is formed in the space, and all kinds of information are disseminated. People are now relying more and more on the Internet for information. For example, users can express their personal opinions on a certain car model on the Netease Auto Forum, such as car cost performance, fuel consumption, etc. At the same time, companies can also improve their products through feedback from users in various forums, and timely adjust the improvement plan for the next generation of products And marketing strategies to improve the competitiveness of enterprises in the market. Therefore, product reviews on the forum are ...

AI Technical Summary

Problems solved by technology

However, in the face of such a huge Internet environment, it is impossible to rely on manual screening and induction of relevant comment information, so a system with automatic retrieval, screening, and summary of relevant information has an urgent market demand

[0003] Through the analysis of a large amount of literature at home and abroad, it can be found that the current tendency analysis technology for product reviews in specific online forums still has the following problems: (1) At present, the Internet is used as a bridge, using information retrieval, natural language processing and other technologies to develop a There are relatively few examples of mature and open propensity analysis systems for a certain field; (2) There are not many sentiment dictionaries for Chinese at present, especially domain sentiment dictionaries. Now the more popular one is HowNet (HowNet). In the process, the impact of evaluation objects on emotional polarity was not considered, and the characteristics of network language flexibility were ignored, resulting in the absence of a dedicated emotional dictionary for the Internet and specific fields; (3) The evaluation object extraction method based on semantic rules is still Only frequent evaluation objects can be found, the accuracy rate of non-frequent evaluation object extraction is low, and the scalability is poor

Images