Computation of Scientific References Using Vector Space Model over Cosine Similarity and Hamming Distance (Case Study: Department of Informatics UNS)

Abstract

Bibliography on final project contains references that are used by writer. References cited in the form of books, journals, magazines, newspapers or internet. Scientific works in the form of journals and proceedings used as references also are listed in the bibliography. Calculation of scientific works that have been noted in the bibliography can be used to calculate the frequency of the use of scientific works used by undergraduate students of Informatics UNS in the form of Vector Space Model using Cosine Similarity and Hamming Distance.

Calculation of the frequency of use of the work of the scientific method using Vector Space Model to find the value of the weight of the title scientific papers where the results will be used to identify the title similarity search papers by using the method of Cosine Similarity. Hamming Distance method used to calculate the distance of the similarity of author names and year. The data used for this research is 100 final project documents. There are 47% of eligible documents Harvard and APA.

The result of the calculation has been done i.e. There are 27 same scientifi works, and produces 12 scientific papers that have a frequency of occurrence of twice or more. There are 5 scientific papers originating from within the country, and 7 scientific papers which came from international.