A Study Of The Author Of Dream Of Red Mansions Based On Machine Learning

There is no doubt about the status of "Dream of Red Mansions" in the histo-ry of Chinese literature.Who is the author,of course,has also become one of the core research issues in literary circles.Although most people agree that the first 80 chapters of "Dream of Red Mansions" were written by Cao Xueqin and the last 40 chapters were written by Gao E,the voices of doubts still continue to appear.This paper takes the writer’s problem of "Dream of Red Mansions" as the research back-ground,the machine learning theory as the research tool and adopts supervised learning algorithm(SVM,Logistic regression)and unsupervised learning algorithm(K-means)in machine learning to analyze the writing style of the first 80 chapters and last 40 chapters to determine whether it is actually written by two authors.The first chapter briefly introduces the research background of "Dream of Red Mansions" and the background knowledge of SVM,Logistic regression and K-means algorithms as well as their respective advantages and disadvantages.The second chapter introduces the background of the Logistic regression and the estimation of the related parameters of the model and gives the generalization of the model.Then it introduces the basic principle of the K-means algorithm,mainly introduces the distance measure and finally gives a specific algorithm.Finally it introduces SVM algorithm with dividing it into three parts for a detailed introduction.The main con-tent of the third chapter is to extract the features we need from the text of "Dream of Red Mansions",to train the classification model and predict the classification results of 120 chapters of "Dream of Red Mansions".The paper gives detailed processes and results;Finally,it gives some specific analysis and comparison for the classifi-cation results and algorithms of the "Dream of Red Mansions".