Modern Chinese literary work author identification system and method

Abstract

The invention discloses a modern Chinese literary work author identification system and method. The system comprises an author known and author unknown sample data processing module, a sample writingfeature extraction and vectorization module, a multi-layer neural network model training module and an anonymous literary work author discrimination module. The sample data processing module is used for making training sample data and discrimination sample data required by the author identification system; the writing feature extraction and vectorization module is used for extracting language features reflecting writing habits of an author so as to make a training sample vector and a discrimination sample vector; and the multi-layer neural network model training module is used for training a multi-layer neural network model by utilizing the training sample vector data and establishing a discrimination model. The discrimination module is used for discriminating an 'anonymous literary work'author by utilizing the discrimination model according to the writing habit language feature vector. According to the system and method, the identification precision of the'anonymous literary works' author within a specified range is very high and even can be close to 100%.

Description

technical field [0001] The present invention relates to a system and method for identifying authors of modern Chinese writing works within a given range. Background technique [0002] The problem of the authorship of Chinese articles has existed since ancient times. The four major classics of ancient Chinese literature all have authorship problems, among which the problem of "Dream of Red Mansions" is the most well-known. Who is the author of "Dream of Red Mansions"? Is the first 80 chapters and the last 40 chapters the same author? These issues are not only academic issues that have been debated for a long time in the academic circle, but also have received widespread attention from the society. For a long time, the academic circles have used various methods to study the authorship of "A Dream of Red Mansions". Among these methods, the textual research method advocated by Hu Shi and the statistical method advocated by Gao Benhan are the most representative. [0003] In re...

AI Technical Summary

Problems solved by technology

These are all academic explorations, and there are no reports on the mature identification technology of authors of modern Chinese writing works

Images