Efficient Similarity Measurement by the Combination of Distance Algorithms to Identify the Duplication Relativity

Abstract

This paper studied the efficient similarity measurement in order to improve the duplication detection techniques in a programming class. This work used the combination of the three proficient algorithms that include Smith-Waterman, longest common subsequence, and Damalau-Levenshtein distance to measure the distance between each pair of the code files. In order to identify the proximity of the person who duplicates each other, this work applied the frequency of occurrence technique to score the accumulated similarity of duplication, the number of times or the regularity of the duplication happens, and the relationship between incidence and time period. Moreover, this work proposed the technique to identify a group of people positioned closely together. The result shows that the proposed of the combination of algorithms could measure the similarity of files efficiently. This work could identify the relativity of a person who frequently duplicates together, and the people positioned closely together. Finally, this work suggested the number of time that student duplicated the code files.