Title: Development strategy of online English teaching based on attention mechanism and recurrent neural network recommendation method

Authors: Linli Du; Yan Xu

Addresses: Hubei University of Science and Technology, Xianning 437000, China ' Xianning Vocational Technical College, Xianning 437000, China

Abstract: In the era of artificial intelligence, a profound examination of the significance and purpose of contemporary English education in tertiary institutions assumes paramount importance. This paper endeavours to explore sustainable development strategies for English education. Firstly, a recurrent neural network model is employed to meticulously analyse the learning characteristics of teachers and students engaged in English studies. These characteristics are predominantly extracted from library search engines, encompassing articles, journals, works, and keywords. Secondly, the attention mechanism is skilfully integrated to capture users' focus on information. Thirdly, the gated recurrent unit is utilised to acquire session information and provide users with pertinent content recommendations, thereby enhancing the recommendation's capacity for generalisation. The experimental results demonstrate that the proposed model attains the highest mean average precision when compared with traditional personalised search methods. Additionally, the effectiveness of the attention mechanism and the click feature within this model is also corroborated. On one hand, this model inspires college students to take the initiative in their learning and empowers them to independently assimilate the valuable knowledge resources of online English teaching. On the other hand, this model facilitates teachers in cultivating a more innovative generation of students within the realm of artificial intelligence.

Keywords: recurrent neural network; recommendation system; online English teaching development strategy.

DOI: 10.1504/IJDMB.2024.137748

International Journal of Data Mining and Bioinformatics, 2024 Vol.28 No.2, pp.140 - 155

Received: 20 Apr 2023
Accepted: 07 Sep 2023
Published online: 04 Apr 2024 *

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