Syllabus Mining for Faculty Development in Science and Engineering Courses

Creating an informative syllabus that can be searched and fully utilized by students is essential for effective education at universities. In this study, we empirically investigate the searchability of a collection of syllabi. In our study, 6,493 online syllabi of a national university in Japan are examined. First, we compare a baseline method and our ameliorated method of query expansion using the book information in syllabi. The results of our experiment demonstrated that book information in syllabi is effective in improving the searchability. Next, we compare methods for word suggestions using deep learning approaches and large text corpora. In the experiment, we used a bibliographic database of university libraries in Japan, which contains 3,990,646 bibliographic entries, and a version of Japanese Wikipedia, which contains 2,351,545 articles. The results indicate that a wide range of vocabulary is advantageous for improving the searchability of syllabi. Finally, we propose some guiding principles for writing a better syllabus based on our findings.