Influencing Factors of Negative Motivation in College Students’ English Learning Relying on the Artificial Neural Network Algorithm

• Published in: Computational intelligence and neuroscience Vol. 2022; pp. 1 - 9
• Main Author: Liu, Ping
• Format: Journal Article
• Language: English
• Published: New York Hindawi 17.10.2022; John Wiley & Sons, Inc
• Subjects: Algorithms; Analysis; Artificial neural networks; College students; Colleges & universities; Education; Eigenvalues; Error analysis; Investigations; Learning; Machine learning; Motivation; Neural networks; Principal components analysis; Students; Study abroad; Teachers; Teaching; University students; United Kingdom
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2022/2323870

College English has received increasing focus as an important part of the education system. However, the continuous development of English instruction has not simultaneously promoted students’ positive learning motivation for English courses. The generation and growth of negative motivation have become a common problem among college students. Students’ enthusiasm for learning English courses is gradually fading and teachers’ teaching value has also become difficult to guarantee, which seriously affects the normal and orderly progress of education and teaching activities. Therefore, it is very important for the healthy development of English teaching to understand and study the affecting elements of negative motivation in English learning of university students and to provide scientific and effective suggestions for teachers and learners to establish a good teaching and learning attitude. Relying on the interpretation of a negative motivation theory, this paper studies various influencing factors by means of the artificial neural network algorithm. The principal component analysis method is introduced to improve the traditional BP algorithm in terms of the frequency of iterations and the length of computation time, which realizes the accurate and efficient analysis of college students’ English learning data. The results of the analysis revealed that the comprehensive error of this algorithm in the analysis of influencing factors was in the range of 0.004 to 0.012. Through the calculation of the eigenvalues and cumulative contribution rate of negative motivation influencing factors, it is found that factors such as the curriculum setting, teaching method, and teacher-student relationship have the greatest influence on students’ negative motivation in English learning. The eigenvalues were 1.027, 1.319, and 1.422, respectively. The cumulative contribution rate reached 64.57%, 26.11%, and 23.62%, respectively. From this aspect, it is necessary to improve these aspects in order to eliminate the negative motivation of learning.