Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Malcom: Indonesian Journal of Machine Learning and Computer Science JRIIN :Jurnal Riset Informatika dan Inovasi
Rosyada, Mila
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Perbandingan Model Regresi Linier dan Random Forest Regressor dalam Estimasi Harga Jual Rumah Berdasarkan Data Properti di Yogyakarta Indriani Zabrina Putri; Rosyada, Mila; Salma Elsa Widyadhana; Saskia Aila Virda; Muhammad Arifin
Jurnal Riset Informatika dan Inovasi Vol 2 No 12 (2025): JRIIN: Jurnal Riset Informatika dan Inovasi
Publisher : shofanah Media Berkah

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Determining the selling price of a house is a crucial aspect in property transactions, especially in regions with dynamic market conditions such as Yogyakarta. This study compares two predictive modeling approaches Linear Regression and Random Forest Regressor in estimating house prices based on property data obtained from the rumah123.com website. The dataset used consists of 1,036 entries, covering variables such as price, land area, building area, number of bedrooms, number of bathrooms, availability of a carport, and location. After undergoing data preprocessing, both models were trained and tested using the same dataset to assess their predictive performance. Evaluation results indicate that the Random Forest model outperforms Linear Regression in terms of accuracy, particularly in handling data variation and non-linear relationships between variables. Although Linear Regression produced a coefficient of determination (R²) of 0.846 indicating that the model could explain 84.6% of the variability in house prices Random Forest demonstrated more precise predictions on the test data. These findings emphasize that selecting the appropriate model depends heavily on the complexity of the data and the required level of accuracy. This study provides a valuable contribution to the development of data-driven decision support systems for property price estimation and serves as a foundation for further research using more advanced machine learning approaches.
Analisis Sentimen dan Pemodelan Topik Komentar YouTube tentang Aplikasi AI Menggunakan Naïve Bayes dan Support Vector Machine: Sentiment and Topic Modeling of YouTube Comments on AI Applications Using Naïve Bayes and Support Vector Machine Rosyada, Mila; Setiawan, R. Rhoedy; Romadhon, Zainur
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 4 (2026): MALCOM October 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i4.3044

Abstract

Komentar pengguna YouTube mengenai aplikasi kecerdasan buatan (Artificial Intelligence/AI), seperti ChatGPT, Google Gemini, dan Perplexity AI, terus meningkat sehingga menghasilkan opini yang sulit dianalisis secara manual. Penelitian ini menggabungkan analisis sentimen dan pemodelan topik untuk memperoleh gambaran tentang persepsi pengguna terhadap beberapa aplikasi AI. Penelitian ini bertujuan untuk menganalisis sentimen dan mengidentifikasi topik utama dari 5.588 komentar YouTube terkait aplikasi AI. Data diproses menggunakan tahapan preprocessing sederhana yang meliputi cleaning, case folding, normalisasi, tokenisasi, stopword removal, dan stemming. Pelabelan sentimen dilakukan menggunakan pendekatan berbasis leksikon, sedangkan fitur diekstraksi menggunakan Term Frequency–Inverse Document Frequency (TF-IDF). Klasifikasi sentimen dilakukan menggunakan Naïve Bayes dan Support Vector Machine (SVM), sementara pemodelan topik dilakukan menggunakan Latent Dirichlet Allocation (LDA). Hasil pelabelan menunjukkan 4.801 komentar (85,92%) positif dan 787 komentar (14,08%) negatif. Evaluasi menunjukkan Naïve Bayes memperoleh akurasi 94,72%, sedangkan SVM mencapai 98,39%, sehingga SVM memberikan performa terbaik. Selain itu, LDA berhasil mengidentifikasi tiga topik dominan, yaitu pengalaman pengguna, kualitas layanan, dan diskusi umum tentang AI. Hasil penelitian menunjukkan bahwa kombinasi analisis sentimen dan pemodelan topik mampu memberikan gambaran yang lebih komprehensif mengenai persepsi pengguna terhadap aplikasi AI berdasarkan komentar di YouTube.
Co-Authors Indriani Zabrina Putri MUHAMMAD ARIFIN R Rhoedy Setiawan Romadhon, Zainur Salma Elsa Widyadhana Saskia Aila Virda