| Summary: | 碩士 === 國立彰化師範大學 === 資訊管理學系所 === 97 === With the rapid development of networking technology, the whole world is becoming a global village where English plays an important role as a communicating language for people around the world. Enhancing our English proficiency not only will improve our communication skill for global competition, but also will allow us to absorb knowledge efficiently and effectively. However, there are few English readability assessing tools to help learners select proper articles to read. Therefore, this thesis presents a method to analyze the readability of English articles with Bayesian Network which takes GEPT’s vocabulary difficulty levels and the average number of words per sentence as its evaluation parameters. The test material of this study comes from 110 GEPT’s Elementary, Intermediate and High-Intermediate level’s reading comprehension articles. These articles are used to build the Bayesian Network structure and compare the effectiveness of it with Flesch Reading Ease and KNN algorithm. Results indicate that the proposed method is more effective than the other two in predicting the readability of English articles.
|
|---|
