Main Article Content

Abstract

Text mining is the process of discovering new, previously unknown information from several text documents. Text mining can be applied to the fields of information extraction, topic tracking, document summarization, document categorization or grouping, concept linking or question answering systems. One thing that is often done in implementing text mining is information extraction. Information extraction aims to extract information from unstructured documents into structured data, with the aim of making it easier to analyze the data. In this study, feature extraction will be used to extract features from the Community Service document, using the Frequent Itemset Mining (FIM) algorithm. The features taken are PKM Title, Abstract, Year of Service, Location, and research topic. After obtaining the features, the service topics will be grouped using the Naive Bayes algorithm. The results of this study were tested using a confusion matrix, with an accuracy of 70%. Factors that affect the accuracy results include the amount of training data, the distribution of training data, and the optimization of the algorithm used

Keywords

Text Mining Ektraksi Fitur Algoritma Naive Bayes

Article Details

How to Cite
Nurmalasari, D., & Ribut Yuliantoro, H. . (2022). Implementasi Ekstraksi Fitur untuk Pengelompokan Dokumen Proposal Menggunakan Algoritma Naïve Bayes. Jurnal Komputer Terapan, 8(1), 194–203. https://doi.org/10.35143/jkt.v8i1.5351

References

Read More

Similar Articles

<< < 1 2 3 4 5 > >> 

You may also start an advanced similarity search for this article.