Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Infotek : Jurnal Informatika dan Teknologi
Buana Perdana, Rendi
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sistem Rekomendasi Peminjaman Buku Menggunakan Metode Vector Space Model Berbasis Pembobotan TF-IDF dan FastText (Studi Kasus Perpustakaan SMP Negeri 1 Kartasura) Buana Perdana, Rendi; Hartanti, Dwi; Hasanah, Herliyani
Infotek: Jurnal Informatika dan Teknologi Vol. 8 No. 2 (2025): Infotek : Jurnal Informatika dan Teknologi
Publisher : Fakultas Teknik Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/jit.v8i2.30540

Abstract

Libraries play an important role in supporting the learning process at school. However, in its utilization, students often find it difficult to find books that suit their needs and interests due to the non-optimal management of the book collection. This problem also occurs at SMP Negeri 1 Kartasura, where there is no system that can generate book recommendations automatically and relevantly. The purpose of this research is to build a Content-Based Filtering-based book recommendation system with the Vector Space Model method which is further developed by combining TF-IDF weights and word vector representation from FastText, resulting in the TF-IDF Weighted with FastText technique. TF-IDF is used to determine the importance of a word in a book description, while FastText is used to capture the semantic meaning of the word in more depth. The system is implemented using book collection data in SMP Negeri 1 Kartasura Library, with input in the form of keywords from users. The document vector representation resulting from the combination of TF-IDF and FastText is then calculated using cosine similarity to determine the most relevant book. Evaluation was then conducted using the Precision@10 metric against ten different keywords, and the system produced an average Precision@10 of 0.93, indicating that 93% of the recommendations provided by this system are relevant to the user's keywords.
Co-Authors Dwi Hartanti Hasanah, Herliyani