TF-IDF Algorithm For Weighting In Determining The Similarity Of Text In Documents

Bustami Bustami (Universitas Malikussaleh)

Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Vol. 1 (2018): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)

The grouping of research documents is needed to facilitate information retrieval. Sometimes we have to read one by one the contents of a document to be able to group it or know the existing information. This research attempts to help in finding information that exists in documents quickly. The information searching in documents by calculating the Term Frequency (TF) and Inverse Document Frequency (IDF) values on each token (word) in each document. The TF-IDF algorithm is an algorithm to calculate the weight of each word that is most commonly used in information retrieval. This algorithm is also known to be efficient, easy and accurate to get results. The accuracy of this algorithm in finding the information in a document reaches above 83,3%.