ABSTRACT
Gu Long’s novels are divided into three periods. Here, 16 novels have been selected as Gu Long’s representative works. To compare the style of the three periods, we have selected the following 14 features: average paragraph lengths, word lengths, sentence lengths, dispersion of word lengths, dispersion of sentence lengths, part of speech (POS), POS of content words, POS of function words, punctuation, high-frequency words, n-gram of POS, n-gram of words, n-gram of punctuation and multiple features. We have as well utilized a hierarchical clustering method to cluster the novels, based on all the features. The results show that there exist differences among the first, the middle and the last period and Gu Long’s novel style has undergone a deep change over the years.
Disclosure statement
No potential conflict of interest was reported by the authors.