Notice: Undefined index: item_type_code in /var/www/html/pustaka/repository/lib/detail.inc.php on line 462
Santa Sabina Tarigan Pengarang Alfonsus Situmorang S.Si., M.Kom Dosen Pembimbing 1

ABSTRACT Research or thesis is a requirement for student graduation. Every year research increases and allows students to take the same or nearly the same topic. Filing of letters at the Karo Regency Regional People's Legislative Assembly office is needed to save time searching and identifying letters for grouping them, therefore an application is needed to simplify the process of filing letters at the Karo Regency Regional People's Legislative Assembly office. TF-IDF is a method for determining the frequency of using a word in a sentence or document by doing text preprocessing first. The preprocessing stage is divided into several parts, namely tokenization, filtering, stemming, and word weighting. By determining the frequency of word use in a sentence, a pattern of similarity will be found between one sentence and another with further steps, namely Cosine Similarity and Cosine Distance. After similarities are found, they will be grouped into several clusters. Through this research a web- based application was developed to classify incoming and outgoing mail data at the Karo Regency Regional People's Legislative Assembly office. The results of grouping and archiving this letter will show how the pattern of a letter is similar to another. In this study the trials were carried out by producing three clustering. From the results of the analysis, letters have been grouped into three clusters consisting of Leadership Invitations, Service Invitations, and Community Invitations. Keywords: Archiving, Mail Clustering, DPRD, Text Mining, TF-IDF