Title: A study on the evaluation of humanistic literacy cultivation model of University English teaching based on MTCNN

Authors: Wenfang Li

Addresses: Department of Foreign Language Teaching, Dianchi College of Yunnan University, Kunming, 650228, China

Abstract: To give consideration to the speed and accuracy of evaluation and reduce the experimental cost and the error caused by human operation in evaluating humanistic literacy cultivation for University English teaching, an evaluation model based on MTCNN is proposed. On the basis of CNN, AMTL is used as the main tool to adjust the adaptability of different types of subtask loss in the training process, and auxiliary tasks are introduced to iterate the evaluation model to judge the loss function and the weight change of subtasks. Determine the weight value a0 = 0.297 of the method proposed in the study. This result is more accurate than the optimal weight 0.3 obtained by the traditional MTCNN. The accuracy, sensitivity and specificity values of the proposed method are 69.83, 64.94 and 72.79, respectively, which are higher than those of other methods and have good accuracy, sensitivity and specificity. It indicates that the method can mine the information of evaluation indexes and help cultivate all-round development college students.

Keywords: multitasking; convolutional neural networks; humanistic literacy; nurturing models; evaluation models.

DOI: 10.1504/IJKBD.2023.133326

International Journal of Knowledge-Based Development, 2023 Vol.13 No.2/3/4, pp.148 - 163

Received: 19 Aug 2022
Accepted: 30 Aug 2022
Published online: 12 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article