The English composition is an important indicator of English learners’ overall language skills and is asked in large-scale English examinations, both in China’s college entrance examinations and graduate examinations and in the TOEFL, GRE, and IELTS examinations in Europe and the United States. Some automatic scoring systems for English writing have been created in the United States and internationally, however the systems still have issues with generalization, accuracy, and error correction. In this paper, we present a method to improve the accuracy of existing automatic composition scoring systems through deep learning techniques in a wireless network environment. Experiments reveal that the method can accurately assess the quality of English learners’ writings, paving the way for the creation of an automated composition scoring system for large-scale machine testing and web-based self-learning platforms.

To explore the correlation between academic performance and learning motivation in English course under a corpus-data-driven blended teaching model, this study set research objects as 62 year-2020-enrolled undergraduate students majoring in English from a university in Jinan City, Shandong Province, eastern China. According to their previous frequencies of using information technology to learn English, these 62 students were divided into two groups: practice group with high frequency and control group with low frequency, with 31 students in each group. The two groups of students were taught 3 English lessons per week for a total of 15 weeks by the exact same teachers using a corpus-data-driven blended teaching model. The students’ English academic performances were assessed by well-organized final tests, and their English learning motivations were measured by a motivation scale and questionnaires. The results show that the correlation coefficients between the average score of motivation questionnaires, intrinsic motivation factors, extrinsic motivation factors, and the average score of academic performances in practice group were 0.894, 0.682, and 0.724, respectively, while those in control group were 0.749, 0.836, and 0.904. In all the above correlation analyses, the significance level is 0.01, and all coefficient values are higher than critical value. Hence, there is a positive correlation between learning motivation and academic performance of the two groups of subjects. It is found that the corpus-data-driven blended teaching model has a significant impact on college students’ English academic performance and learning motivation, and it has a positive effect on the improvement of their English academic performance and the cultivation of learning motivation. In general, the key to this teaching model lies in reasoning and acquisition by analyzing the language provided by the corpus, and the whole process of data-driven learning is student-centered. Students are exposed to a large number of authentic language knowledge and cultural information, which promotes the sensitivity to relevant points. The results of this paper provide a reference for further research on the analysis of the correlation between academic performance and learning motivation in English course under the corpus-data-driven blended teaching model.

We show how to optimize English diagnostic Q matrix based on cognitive diagnostic model fitting method. Firstly, attribute annotation verifies the reliability of existing Q matrix and fitting analysis, as researchers found that they still have the original Q matrix optimization space; secondly, this paper proposes a classification algorithm based on organization evolution and the information entropy of English in the diagnosis of intelligent evaluation algorithm, the running mechanism of the existing evolutionary algorithm, and the evolution of its direct effects on operation data rather than the rule. After the end of evolution, rules can be extracted from each organization to avoid meaningless rules in the process of evolution. According to the characteristics of the classification problem, we put forward three kinds of evolutionary operators and a selection mechanism, which is presented based on the information office of the evolution of the way of attribute importance. Based on this definition, the organizational fitness function, and finally the algorithm used in six test data sets and compared with the existing two classification methods, the experimental results show that the method obtained the higher forecast accuracy, and smaller rule sets are produced. Finally, a matching combination and quantitative fitting screening based on G-DINA measurement model were decomposed and analyzed, and a better fitting model was optimized based on the original Q matrix model. The results show that, first, the optimized new model is better than the original model in relative data fitting value and interpretation and diagnosis of fractional variation; second, the new model has a higher correlation with the results of self-evaluation, indicating that the probability of the new model is closer to the results of self-evaluation.