Emotion analysis method of automobile review based on automobile ontology and part-of-speech rules

Abstract

The invention provides an emotion analysis method of automobile review based on automobile ontology and part-of-speech rules, which comprises the following steps: a dictionary of automobile ontology,an emotion dictionary and an emotion adjustment dictionary are constructed; Get user comments on the car; The emotion words, negative words and degree adverbs in the comments are identified accordingto the emotion dictionary and the emotion adjustment dictionary, and the automobile feature words in the comments are identified according to the ontology dictionary of automobile field and mapped tothe corresponding automobile performance dimension. Extracting part-of-speech rules from user comments, constructing an effective set of part-of-speech rules for affective analysis; The correspondingemotion comment sentences are extracted from the comment sentences by the part-of-speech rule set. According to the emotion dictionary, degree dictionary and adjustment dictionary, the comprehensive emotion values corresponding to the vehicle performance dimension in the car review are calculated respectively, and the fine-grained and digital emotion values of the users are obtained.

Description

technical field [0001] The invention relates to an analysis method, in particular to a car comment sentiment analysis method based on car ontology and part-of-speech rules. Background technique [0002] At present, most domestic automobile manufacturers mainly rely on traditional channels such as 4S stores, questionnaire surveys, user visits, telephone interviews, and dealers to obtain the car purchase experience and feedback of a small number of users, which has low timeliness, high cost, long cycle, and few samples. limited. The professional automobile websites represented by Autohome, Sina Auto, and Netease Auto are flourishing, providing a platform for many netizens to share and exchange car purchase experience and product feedback. The massive amount of online car review information generated by these platforms makes it possible for car manufacturers to obtain timely and large-scale user feedback information. But at the same time, the overall informatization level of ...

AI Technical Summary

Problems solved by technology

The existing sentiment analysis method based on sentiment lexicon ignores the contextual semantic connection of words, isolates words from sentences, and affects the effect of sentiment classification of review texts; while the sentiment analysis method based on machine learning is used to deal with the whole article or Works well for sentences, but less so for sentiment analysis on finer-grained text

Images