AUTHOR=Shen Jun , Jiang Leping 

TITLE=Correlation Analysis Between Japanese Literature and Psychotherapy Based on Diagnostic Equation Algorithm

JOURNAL=Frontiers in Psychology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2022.906952

DOI=10.3389/fpsyg.2022.906952

ISSN=1664-1078

ABSTRACT=Literary therapy theory provides a new field for contemporary literature research, and is of great significance for maintaining the physical and mental health of modern people. "Healing" is a major feature of Japanese literature. No matter what kind of themes, plots and characters, the purpose of such works is to serve the healing of the works. The quantitative evaluation of therapeutic effect in Japanese healing literature is a hot research topic at present.  Based on the fact that Japanese literature can assign different weights to words of different importance, Text convolutional neural network (TEXT-CNN) is selected in this paper. By using multiple convolutional kernels of different sizes to extract psychological therapy features of different granularity and the relationship between literary works and psychological therapy effects, In this paper, bidirectional threshold recurrent neural network (BiGRU) is used to process the dependence information between properties with large distance, and further optimized on the basis of CNN-BilSTM model, a parallel hybrid network integrated with attention mechanism is constructed to analyze the correlation between literature and psychotherapy. Through experimental verification, the model in this paper further improves the accuracy of correlation classification and has strong adaptability.