MACHINE LEARNING JOURNAL ARTICLE RECOMMENDATION SYSTEM - USING CONTENT BASED FILTERING

Aug 2, 2026

Upload by Violet

Study proposes a machine learning journal article recommendation system using the Content Based Filtering approach to address the difficulty of locating relevant publications in Indonesia. The research follows CRISP-DM and implements TF-IDF feature representation with Cosine Similarity for document matching. A dataset of 100 machine learning journal articles is evaluated using a precision matrix, achieving 76% precision, indicating good performance. Limited dataset size reduces recommendation coverage for some queries.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

I. INTRODUCTION

Background of AI and machine learning publications

Recommendation system need in Indonesia

MACHINE LEARNING JOURNAL ARTICLE RECOMMENDATION SYSTEM USING CONTENT BASED FILTERING Afika Rianti1), Nuur Wachid Abdul Majid2), and Ahmad Fauzi3) 1, 2, 3)Kampus UPI di Purwakarta, Universitas Pendidikan Indonesia Jl. Veteran No.8, Nagri Kaler, Kec. Purwakarta, Kabupaten Purwakarta, Jawa Barat, Indonesia e-mail: [afika@upi.edu](afika@upi.edu1)[1](afika@upi.edu1)), [nuurwachid@upi.edu](nuurwachid@upi.edu2)[2](nuurwachid@upi.edu2)), [ahmad.fauzi@upi.edu](ahmad.fauzi@upi.edu3)[3](ahmad.fauzi@upi.edu3)) ABSTRACT Indonesia is a country that hasn’t studied much about artificial intelligence. This has resulted in a small number of publications related to thatfield including areas within such as machine learning. For that reason, it caused difficulties in finding relevant journal articles. The purpose of this study is to know the performance of the Content Based Filtering method in providing machine learning journal article recommendations. The research procedure used is CRISP-DM with algorithms used are TF-IDF and Cosine Similarity. The dataset used consists of 100 machine learning journal articles. Based on the research that has been done, it’s concluded that the performance of the Content Based Filtering method in providing machine learning journal article recommendations as measured using the precision evaluation matrix showed a score of 76%, which means the result is quite good. However, the model couldn’t be used properly for some data due to the small number of datasets which affects the limited recommendations. Keywords: Content Based Filtering, CRISP-DM, machine learning journal article, precision, recommendation system SISTEM REKOMENDASI ARTIKEL JURNAL MACHINE LEARNING MENGGUNAKAN CONTENT BASED FILTERING Afika Rianti1), Nuur Wachid Abdul Majid2), and Ahmad Fauzi3) 1, 2, 3)Kampus UPI di Purwakarta, Universitas Pendidikan Indonesia Jl. Veteran No.8, Nagri Kaler, Kec. Purwakarta, Kabupaten Purwakarta, Jawa Barat, Indonesia e-mail: [afika@upi.edu](afika@upi.edu1)[1](afika@upi.edu1)), [nuurwachid@upi.edu](nuurwachid@upi.edu2)[2](nuurwachid@upi.edu2)), [ahmad.fauzi@upi.edu](ahmad.fauzi@upi.edu3)[3](ahmad.fauzi@upi.edu3)) ABSTRAK Indonesia merupakan negara yang belum banyak mempelajari tentang kecerdasan buatan. Hal ini menyebabkan sedikitnyajumlah publikasi terkait dengan bidang tersebut termasuk bidang-bidang di dalamnya seperti machine learning. Oleh karenaitu, hal ini menyebabkan kesulitan dalam menemukan artikel jurnal yang relevan. Tujuan dari penelitian ini adalah untuk mengetahui performa metode Content Based Filtering dalam memberikan rekomendasi artikel jurnal machine learning. Prosedur penelitian yang digunakan adalah CRISP-DM dengan algoritma yang digunakan adalah TF-IDF dan Cosine Similarity. Dataset yang digunakan terdiri dari 100 artikel jurnal machine learning. Berdasarkan penelitian yang telahdilakukan, dapat disimpulkan bahwa performa metode Content Based Filtering dalam memberikan rekomendasi artikel jurnal machine learning yang diukur menggunakan matriks evaluasipresisi menunjukkan nilai sebesar 76% yang berarti hasilnya cukup baik. Namun, model tersebut tidak dapat digunakan dengan baik untuk beberapa data karenajumlah dataset yang sedikit sehingga mempengaruhi rekomendasi yang terbatas. Kata Kunci: Content Based Filtering, CRISP-DM, artikel jurnal machine learning, presisi, sistem rekomendasi I. INTRODUCTION Artificial intelligence (AI) is one of the work fields that is needed in the industry. AI itself is the development and integration of the fields of electronics, computer science, and mathematics that are capable of doing work like humans [1] . This field continues to grow from time to time. Quoted from the Journal Risk and Financial Management, stated that the rapid development of AI has started to occur from 2012 until now [2] . Then from the data in the 2020 World Economic Forum (WEF) Future of Jobs Survey, it said that jobs related to AI are in second place

FAQs

What problem does the study address?

The study addresses the difficulty of finding relevant machine learning journal articles because related AI research and publications in Indonesia remain limited.

Which method and algorithms are used for the recommendation system?

Content Based Filtering is used, with TF-IDF for text representation and Cosine Similarity to measure similarity between articles.

How is performance evaluated and what result is achieved?

Performance is measured using a precision evaluation matrix, producing a score of 76%, which the study describes as quite good.

Aug 2, 2026

Upload by Violet