Text fine granularity sentiment analysis method and text fine granularity sentiment analysis device

Abstract

The invention discloses a text fine granularity sentiment analysis method. The text fine granularity sentiment analysis method includes the steps: performing sentiment word orientation intensity quantitative calculation; performing combined recognition of evaluation object attributes and sentiment expression elements thereof; and performing fine granularity attribute classification and sentiment calculation. The invention further discloses a text fine granularity sentiment analysis device which comprises a comment data acquiring and preprocessing module, a data processing module, a data analysis module and an information display module. The text fine granularity sentiment analysis method adopting the three steps has the advantages that accuracy rate is increased by nearly 30% by the aid of the sentiment word orientation intensity quantitative calculation step; the step of combined recognition of the evaluation object attributes and the sentiment expression elements thereof aims at the specific sentiment analysis application fields, and combined recognition accuracy rate is above 80%; and integral performance of sentiment calculation can be increased above 2.5% by the step of fine granularity attribute classification and sentiment calculation.

Description

Technical field [0001] The present invention is a computer application technology field. It is specifically a fine -grained emotional analysis method and device of subjective text. It can be applied to the commodity reviews of business websites, online public opinion analysis of enterprises or government departments. Background technique [0002] With the rapid development of the Internet, especially the gradual popularization of Web2.0 technology, the majority of online users have become the main manufacturer of network content from the past simple information acquisitioners.According to data from the "30th China Internet Development Status Status Statistics Report" (CNNIC, 2012) released by the China Internet Information Center, as of June 2012, the total number of Internet users in my country has reached 538 million, and the size of netizens has increased compared to the end of 2011. 24.5 million people, the Internet penetration rate is 39.9%.Such a huge and fast -growing netw...

AI Technical Summary

Problems solved by technology

[0008] When these two types of methods conduct text sentiment analysis, whether it is a sentence or a chapter, they all strongly rely on the sentiment dictionary. Therefore, the quality of the sentiment dictionary directly affects the correctness of the sentiment analysis. At present, more sentiment dictionaries are manually analyzed. The workload is huge, and with the development of the Internet, new emotional words emerge in endlessly, so it is far from enough to build a one-time emotional dictionary. At the same time, the current emotional dictionary often lacks the quantification of polarity strength, which is difficult. Meeting the Needs of Affective Computing

On the other hand, in the specific sentiment analysis process, the existing methods generally only consider the characteristics of words. After sentence segmentation and part-of-speech tagging, they use the characteristics of part-of-speech to identify attributes and emotional words, but lack the overall semantic understanding of sentences. , which leads to low recognition efficiency

Images