Fixed topic-based text sentiment orientation classification method

Abstract

The invention discloses a fixed topic-based text sentiment orientation classification method and belongs to the field of text sentiment orientation classification. The method comprises the steps of first finding out a topic of a sentence, calculating sentiment orientations before and after the topic by two steps according to the position of the topic in the sentence separately, and finally calculating a sentiment orientation of the topic. Sentiment symbols in the sentence are found out by utilizing characteristic sentiment symbols and a common sentiment dictionary; negative words and degree adverbs are searched for between topic words and the sentiment symbols, and the influence of the negative words and the degree adverbs on the sentiment symbols is calculated; and a connection relationship is searched for between the sentiment symbols, and the sentiment orientation of the topic is calculated. According to the method, a user can be assisted to obtain orientation degrees of other users to important attributes of a product, a service, an event or a character, and subdivide sentiment orientations of related users to the aspects of characteristics of the product, the event or the character.

Description

technical field [0001] The invention relates to a text sentiment tendency classification method based on a fixed theme, which belongs to the field of text sentiment tendency classification. Background technique [0002] In the era of Internet information explosion, how to get the public's views or opinions on a certain event or product, that is, how to find useful reference data from these commentary information, has been an important content of relevant researchers at home and abroad in the past ten years. [0003] At present, machine learning based on sentiment lexicon and large-scale corpus are mainly used for the classification of sentiment tendency. Whether it is dictionary-based or machine learning, the key lies in the quality of the sentiment lexicon. Using a sentiment dictionary to classify different topics, the quality of the sentiment dictionary must not meet the professional requirements and will greatly reduce the speed of sentiment classification. Due to the di...

AI Technical Summary

Problems solved by technology

Using a sentiment dictionary to classify different topics, the quality of the sentiment dictionary must not meet the professional requirements and will greatly reduce the speed of sentiment classification

Images