Text data viewpoint summary mining method merging topic attributes and emotion information

Abstract

The invention provides a text data viewpoint summary mining method merging topic attributes and emotion information. The method comprises the steps of preprocessing a text corpus set of a topic; inputting a topic corpus set and a background corpus set; extracting the topic attributes of the topic corpus set; adding emotional polarities to the obtained topic attributes, and vectorizing sentences; taking the obtained topic attributes as evaluation objects, obtaining emotional attribute features contained in the sentences, and conducting feature vectorization on one sentence by means of a topic attribute and emotion analysis method; utilizing an obtained topic attribute set and a text sentence feature vector set S to construct a three-layer graph structure, and clustering all the text sentences; selecting sentences from class clusters to form a viewpoint summary, and selecting the sentences with high scores to form a viewpoint summary. According to the text data viewpoint summary mining method, the extracted topic attributes are more accurate by adopting a topic attribute extraction method, and meanwhile the text data viewpoint summary mining method can be applied not only to the field of Chinese microblogs but also to the field of website news and product reviews.

Description

technical field [0001] The present invention relates to the fields of text summarization and sentiment analysis, and more specifically, relates to a method for generating short opinion summaries with rich user emotional information for massive topic text data of Chinese microblog corpus, and the opinion summaries can accurately cover the text discussed and can be applied to practical application scenarios such as news summaries and commodity review analysis. Background technique [0002] Currently, there are many techniques and methods available for research in the field of opinion summarization. Traditional view summarization models include graph models and ranking models. The representative methods of graph models include Textrank, PageRank, LexRank and other methods. They use sentences as nodes, and a certain relationship between sentences as the weight of edges, and iteratively update and calculate the scores of sentences through the random walk model, so as to realize ...

AI Technical Summary

Problems solved by technology

The disadvantage is that most of the existing graph models consider using text sentences and topic features to construct graph structures, and describe the emotional information of opinion summaries through the emotional information of the entire text sentence, without integrating the emotional information of topic attributes in the graph structure, there is no Considering that the topic features of different emotions are two subjects with different meanings, resulting in sentences containing different emotional topic attributes being associated

Images