Strategies for Improving College English Reading Comprehension Based on Text Mining Technology

Reading is an important part of college English learning, which plays an important role in improving students’ language comprehension, critical thinking, writing ability and cross-cultural cognitive ability. The article takes the benefits and obstacles of cultivating college English comprehension as an entry point, and establishes a model for teaching college English reading with the support of a smart classroom. In order to enrich college English reading teaching resources, a reading preference model is established based on students’ reading behavior, and reading preference resources are classified by the TF-IDF algorithm. Then the recommendation algorithm applied to English reading resources is designed by combining the similarity of students’ knowledge structure when they are reading English resources. Students in the first year of a university in the College of Foreign Languages of a university were selected as the research object and a teaching comparison experiment was designed as a way to verify the effectiveness of the university English reading teaching model. With a certain number of students, the accuracy of this paper’s recommendations for English reading teaching resources is approximately 3% to 40% higher than that of User-CF and Item-CF algorithms. The difference between the reading comprehension scores of students in class A and class B before and after the experiment is 7.42 points, and there is a significant difference (P<0.01), and the average value of students’ English reading comprehension level is 3.697 points. With the support of informatization technology combined with text mining technology, it is possible to realize the accurate recommendation of English reading teaching resources, and the university English reading teaching mode supported by smart classroom has a good prospect.