Abstract

The collection of the certificates was one of the requirements for graduating from Tarumanagara University that the certificate became an important point of attention to improving the competency of Tarumanagara University students. Certificates can be collected from seminars, workshops, courses, and so forth. The Certificate Information Extraction design were created using Uipath Studio application that uses vb.Net programming language and Levenshtein Distance Algorithm. The design aims to assist the study program in validation on student certificates file by obtaining better accuracy using the Levenshtein Distance Algorithm.. The design uses input data as student certificates that’s next to be processed by text preprocessing consisting of text deductions (parsing), case folding, lexical analysis (tokenizing), and text removal (stopword removal). After processing, the Levenshtein Distance Algorithm will be used to calculate the minimum distance between one text and the other with a two-dimensional matrix operation, thus determining the validity of student certificates. The results of this design represent that using the Levenshtein Distance Algorithm, obtaining the best word accuracy result of 83.52% and RPA running time of 94.7 ms.

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