Kehan Du

"English Language and Literature" courses are essential components of university education. They provide a significant avenue for understanding the politics, economics, and customs of English-speaking countries. These courses facilitate a mastery of English grammar, which in turn enhances students' comprehension of spoken and written English content. However, traditional modes of instruction in English Language and Literature often lack engagement and interactivity, thereby limiting the effectiveness of learning in this field. In order to boost learners' interest and efficiency in studying English, it is imperative to shift away from conventional teaching approaches. With the rapid advancement of artificial intelligence in various domains, its integration with English Language and Literature education can yield intelligent learning experiences. This study employs a combination of Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU) to reform the teaching model in English Language and Literature. The results indicate that CNN and GRU methodologies offer substantial support in realizing intelligent approaches to teaching this field. These methods exhibit a high degree of similarity and accuracy in predicting linguistic features in English Language and Literature. They excel in terms of predictive and scatter error distribution, showcasing superior performance.