Study on the Influence of Wuthering Heights Characters Based on Web Analysis and Text Mining

Abstract

The rapid development of network technology and the popularity of the Internet have made people rely more and more on the exchange and sharing of network information, and the demand for obtaining information about people from the Internet has gradually increased, but the massive amount of network data has made the information about people fragmented and disorganized, and the existing work on portraits has mainly focused on the extraction of people’s attributes. In this paper, we examine the artistic construction and characterization of Wuthering Heights on the basis of a tasting of the book, with the aim of presenting the “alienated personalities” hidden in the depths of the characters’ consciousness and showing the author’s unique creative art through an analysis of thematic ideas, the use of temporal elements, and the tracing of the creation of the characters’ original forms. In the aspect of character social relationship extraction, first, the method of expanding the seed dictionary by means of synonym word forest is used to build a character relationship lexicon, which avoids the inefficiency caused by manual lexicon collection; second, a character relationship extraction algorithm based on the combination of rule matching and syntactic tree is proposed, which effectively overcomes the disadvantage of low recall rate caused by rule matching, and the average F-value of this algorithm reaches 82.61% in the experiment The algorithm achieves an average F-value of 82.61% in the experiment, which is a significant advantage over other methods.