<![CDATA[Every final year student who has completed his lecture must definitely make a thesis in order to get his degree. Before making a thesis, students must propose a thesis title to the study program admission section first. The title will be checked for feasibility by the study program. One of the requirements of the thesis title is said to be feasible, the title has never been used by other students. But every semester there are so many students who submit thesis titles, so the study program is overwhelmed if they have to match one by one the incoming thesis titles with the previous thesis title because it requires a lot of energy and time. Therefore, a system needs to be developed to detect the similarity of the thesis title so that the process of assessing the feasibility of the title can be done faster and easier. Rabin Karp is an algorithm that can detect similarities in documents, using the hash method in searching for a word. This theory is rarely used to find a single word, but it is quite important and very effective when used for multiple searches. For this reason, in this study Rabin Karp's ability to detect the similarity of the thesis title will be proven by giving the title similarity value. Thesis title is preprocessing, so that the data becomes "clean", so it is feasible to do the hashing process. After hashing, then apply the Rabin Karp algorithm to each word and measure its similarity using dice's Coefficient, resulting in a similarity value from the title of the thesis. The better the stemming process in the preprocessing process, the higher the similarity value. Keywords: Thesis Title, Similarity, Rabin Karp]]>
Copyrights © 2018
