Abstract

Classification new book is needed in facilitating students and lecturers to find books. The law used is Dewey Decimal Classification (DDC) classification. The application of the DDC classification requires a high level of accuracy and concentration in grouping books into appropriate classes. Errors that occur in the form of discrepancies in the provision of class books. Performance can be improved by the existence of an information system that can help classify classes in books according to DDC law. The process of giving classes to books by looking for the highest similarity between titles and synopsis of books with each DDC dictionary class. Adjusting to the process of giving classes to books at the University of Jember Library, the title, synopsis and DDC dictionary are processed using the text mining method. Text mining produces data in the form of basic words from the title, synopsis and DDC dictionary. The number of occurrences of each word is useful for measuring how important a word is in a document. The method that is suitable for calculating the importance of a word in a document is the method of weighting Term Frequency-Inverse Document Frequency (TF-IDF). The results of the TF-IDF weighting are used to find the highest similarity between the title and the synopsis with the class in the DDC dictionary. The appropriate method in calculating the similarity of two documents is Cosine Similarity. The biggest similarity value between the title and synopsis with the DDC dictionary using Cosine Similarity method is made a priority in determining the class of books. The results of the application of the method in the system there are 20 data books resulting in book classes in DDC 000 class there are 3 books, DDC 100 class is 1 book, DDC class 200 there is 1 book, DDC 300 class there are 6 books, DDC 400 class there are 4 books, DDC 500 class is 1 book, DDC 600 class there are 2 books and DDC 700 class there are 2 books. Testing book classification information system produces accuracy percentage of 35 %.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call