We study the difficulty modeling for Chinese reading materials using artificial intelligence. First, the training data set of Chinese reading materials is constructed. Secondly, a large number of ...students' questions and answers after reading the reading material samples are recorded, and the average score of students is calculated as the difficulty label of each reading material sample. Then, the characteristics of each reading material sample are extracted according to the student's psychological cognitive characteristics. Finally, an iterative LightGBM method is constructed as the difficulty-scoring model of reading materials. A 10-fold cross-validation test result shows that the accuracy rate of this model is 81.5%, the recall rate is 85.3%, and F1 score is 83.4%. The accuracy of the model is acceptable.
The study was aimed to examine how EFL learners of English reacted to graded readers in terms of reading strategy use, comprehension, speed, and attitude as well as motivation when control for ...ability level was determined. Eighty Thai high school students placed into their own reading level of graded readers by the scores gained from the graded reading-vocabulary size test (Wan-a-rom, 2010) participated in a six-week-extensive reading project. Through observations, semi-structured interviews, book journals, and post-reading questionnaires, it was found that both male and female participants increased the use of strategies. When moving through other graded readers at the same level the numbers of strategies utilized by males and females were different at the 0.05 level of significance and the time spent on reading decreased on average. Evidently, comprehension, attitude and motivation were cultivated. Interesting information about students' interaction with graded readers was found and discussed for pedagogical practice.
To automate the graded reading task, we urgently need to extract and calculate the important index of the complexity of the relationship between the characters affecting the plot complexity of ...narrative literature. In order to realize this purpose, this paper describes a computational method for automatic analysis of the virtual social network from children's literature works. We selected the required bibliography for primary school students recommended by the Ministry of Education, then automatically extract the characters of the novel by CRF, and constructs the character network based on the co-occurrence relationship. The statistical analysis method of complex network provides a quantitative basis for distinguishing the complexity of characters' relationships in different texts. The results show that the structural characteristics of character interaction networks are similar to those of small world networks, and the selected network measurement indexes are significantly related to the complexity of text characters. Finally, we achieved effectively evaluating and predicting the complexity of the social networks from more extensive literature works some classical regression model based on machine learning.
PDF