Article Per Year (5 Year)
p-Index From 2021 - 2026
0.882
P-Index
This Author published in this journals
All Journal Jurnal Simetris Speed - Indonesian Journal on Computer Science Seruni - Seminar Riset Unggulan Nasional Inoformatika dan Komputer Speed - Sentra Penelitian Engineering dan Edukasi JITK (Jurnal Ilmu Pengetahuan dan Komputer) Indonesian Journal of Applied Informatics Jurnal Teknik Informatika (JUTIF) Indonesian Journal of Networking and Security - IJNS SPEED - Sentra Penelitian Engineering dan Edukasi Komunita: Jurnal Pengabdian dan Pemberdayaan Masyarakat
Berliana Kusuma Riasti
Universitas Sebelas Maret
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Library & Information Science Public Health Social Sciences

Published : 55 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 55 Documents
Search

 2   3   4   5   6 
MENTORA: Inovasi Digital untuk Pemberdayaan Masyarakat Berbasis Data Fiddin Yusfida; Hartatik, Hartatik; Firdaus, Nurul; Kusuma Riasti, Berliana; Supriyadi, Andy
KOMUNITA: Jurnal Pengabdian dan Pemberdayaan Masyarakat Vol 4 No 3 (2025): Agustus
Publisher : PELITA NUSA TENGGARA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60004/komunita.v4i3.225

Abstract

Kegiatan Pelatihan dan Serah Terima Aplikasi MENTORA dilaksanakan oleh Grup Riset Applied Data Science and AI (DSAI) Universitas Sebelas Maret (UNS) Surakarta melalui skema Pengabdian Kepada Masyarakat Hibah Grup Riset (PKM HGR-UNS) pada 10 Juli 2025 di D3 Teknik Informatika, Sekolah Vokasi UNS. Kegiatan ini bertujuan meningkatkan efektivitas pengelolaan data pendampingan komunitas dengan memanfaatkan teknologi informasi. MENTORA adalah aplikasi digital inovatif yang dirancang untuk mendukung pemberdayaan masyarakat berbasis wilayah dengan fitur unggulan seperti Admin Center, Fasilitator Hub, Group Management, Community Management, Activity Management, Activity Insights Dashboard, dan Data Exporter. Pelatihan diikuti oleh admin dan fasilitator yang akan mengoperasikan aplikasi di lapangan untuk memastikan implementasi optimal. Acara ini juga menjadi momentum inisiasi kerja sama tridharma perguruan tinggi antara UNS dan Majelis Pemberdayaan Masyarakat PP Muhammadiyah. Diharapkan dengan hadirnya MENTORA, pengelolaan data pendampingan masyarakat menjadi lebih terstruktur, transparan, dan mendukung transformasi digital di komunitas.
A Hybrid Approach for Recommender Systems Based on Alternating Least Squares and CatBoost Yusfida A'la, Fiddin; Hartatik, Hartatik; Riasti, Berliana Kusuma
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 4 (2025): JUTIF Volume 6, Number 4, Agustus 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.4.5002

Abstract

This study aims to improve the accuracy of movie rating predictions by applying and combining collaborative filtering and machine learning techniques in a hybrid recommender system. The research utilizes the MovieLens dataset to implement two distinct approaches: the Alternating Least Squares (ALS) matrix factorization model and the CatBoost gradient boosting model. The ALS model is trained to capture latent user–item interactions, while CatBoost leverages nonlinear relationships using user and item features. A simple hybrid strategy averages the predictions from both models to evaluate potential performance gains. Experimental results show that the hybrid approach achieves lower error metrics compared to either model individually, with Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values of 0.828 and 0.666, respectively. This demonstrates that combining latent factor models with tree-based learning can effectively reduce prediction errors by exploiting complementary strengths. The novelty of this research lies in its efficient yet effective hybridization strategy that improves recommendation quality without complex ensembling techniques. The findings suggest that even lightweight model fusion can significantly enhance predictive accuracy in recommender systems and may be adapted for other domains where combining linear and nonlinear modeling is beneficial. This research contributes to the field of Informatics and Computer Science by demonstrating that a lightweight hybridization of latent factor models and tree-based learning can significantly improve recommender system accuracy while offering practical implications for real-world digital applications.
COMPARATIVE STUDY OF TRANSFORMER-BASED MODELS FOR AUTOMATED RESUME CLASSIFICATION Firdaus, Nurul; Kusuma Riasti, Berliana; Asri Safi'ie, Muhammad
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.7453

Abstract

This study presents a comparative evaluation of transformer-based models and traditional machine learning approaches for automated resume classification—a key task in optimizing recruitment workflows. While traditional approaches like Support Vector Machines (SVM) with TF-IDF demonstrated the highest performance (93.26% accuracy and 95% F1-score), transformer models such as DistilBERT and RoBERTa showed competitive results with 93.27% and 91.34% accuracy, respectively, and fine-tuned BERT achieved 84.35% accuracy and an F1-score of 81.54%, indicating strong semantic understanding. In contrast, Word2Vec + LSTM performed poorly across all metrics, highlighting limitations in sequential modelling for resume data. The models were evaluated on a curated resume dataset available in both text and PDF formats using accuracy, precision, recall, and F1-score, with preprocessing steps including tokenization, stop-word removal, and lemmatization. To address class imbalance, we applied stratified sampling, macro-averaged evaluation metrics, early stopping, and simple data augmentation for underrepresented categories. Model training was conducted in a PyTorch environment using Hugging Face’s Transformers library. These findings highlight the continued relevance of traditional models in specific NLP tasks and underscore the importance of model selection based on task complexity and data characteristics
COMPARATIVE STUDY OF TRANSFORMER-BASED MODELS FOR AUTOMATED RESUME CLASSIFICATION Nurul Firdaus; Berliana Kusuma Riasti; Muhammad Asri Safi'ie
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.7453

Abstract

This study presents a comparative evaluation of transformer-based models and traditional machine learning approaches for automated resume classification—a key task in optimizing recruitment workflows. While traditional approaches like Support Vector Machines (SVM) with TF-IDF demonstrated the highest performance (93.26% accuracy and 95% F1-score), transformer models such as DistilBERT and RoBERTa showed competitive results with 93.27% and 91.34% accuracy, respectively, and fine-tuned BERT achieved 84.35% accuracy and an F1-score of 81.54%, indicating strong semantic understanding. In contrast, Word2Vec + LSTM performed poorly across all metrics, highlighting limitations in sequential modelling for resume data. The models were evaluated on a curated resume dataset available in both text and PDF formats using accuracy, precision, recall, and F1-score, with preprocessing steps including tokenization, stop-word removal, and lemmatization. To address class imbalance, we applied stratified sampling, macro-averaged evaluation metrics, early stopping, and simple data augmentation for underrepresented categories. Model training was conducted in a PyTorch environment using Hugging Face’s Transformers library. These findings highlight the continued relevance of traditional models in specific NLP tasks and underscore the importance of model selection based on task complexity and data characteristics
Rancang Bangun Sistem Antrian Terkustomisasi Berbasis Android Yoeseph, Nanang Maulana; Riasti, Berliana Kusuma; Hartatik, Hartatik; Pratisto, Eko Harry; A'la, Fiddin Yusfida
IJAI (Indonesian Journal of Applied Informatics) Vol 6, No 1 (2021)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v6i1.56778

Abstract

Abstrak : Sebagian besar pelayanan publik di era ini masih menggunakan sistem konvensional. Yang mana, klien layanan mendapatkan tiket antrean, menunggu, dan dilayani di tempat yang sama. Penelitian ini bertujuan untuk memudahkan dan memungkinkan orang untuk mengantre dari jarak jauh. Dengan demikian waktu yang awalnya digunakan untuk dihabiskan menunggu, bisa digunakan untuk dihabiskan melakukan sesuatu yang lain lebih berguna.Berdasarkan kondisi yang dikatakan di atas, aplikasi yang menghubungkan agen layanan dengan klien layanan perlu dibuat. Aplikasi ini memanfaatkan internet dan smartphone yang dapat diakses melalui aplikasi Android atau browser web. Pengembangan aplikasi ini menggunakan kerangka kerja Ionic React. Aplikasi ini dirancang dan dibangun menggunakan metode Waterfall yang terdiri dari pengamatan dan pengumpulan data, analisis, desain sistem, bangunan dan pengujian, kesimpulan dan saran.Dari desain dan bangunan yang telah dilakukan, dibuat aplikasi yang memiliki ftur dasar untuk antrean online. Aplikasi ini dapat dijalankan di browser web dan perangkat Android dengan sistem operasi minimum Android 4.4 KitKat.Abstract : Most public services in this era still use conventional systems. Which is, service clients get queue tickets, wait, and be served in the same place. This research aims to ease and enable people to queue remotely. Thus the time that is originally used to be spent waiting, could be used to be spent doing something else more useful. Based on the conditions said above, an application that connects service agencies with service clients needs to be made. This application utilizes the internet and smartphone which can be accessed through Android application or web browser. The development of this application uses the Ionic React framework. This app is designed and built using the Waterfall method consisting of observation and data collection, analysis, system design, building and testing, conclusion and suggestion.
Co-Authors - Fakultas Teknologi Informatika Universitas Surakarta, Rokhimah Ratnawati ., Nur Badri ., Sri Haryanti A'la, Fiddin Yusfida Aditya Prihantara Aditya Prihantara - Fakultas Teknologi Informatika Universitas Surakarta Akhmad Rindo Akhmad Sholikhin Alex Fahrudin Alfian Eko Hery Setyawan Andy Supriyadi Anjar Priyadna Annisa Annisa Asri Safi'ie, Muhammad ‘Adhim, Ismu Bambang Eka Purnama Bambang Eka Purnama Bambang Eka Purnama Budhi Santoso Dafit Nur Hidayanto Dimas Sasongko Dimas Sasongko Dina Khusnia Dwi Ngatmono Dwi Ngatmono, Dwi Eko Harry Pratisto Eko Wahyudianto Eksan Setyawan Endah Setyorahayu Fachry Abda El Rahman Fiddin Yusfida Firdaus, Nurul Gita Anesya Pebrianika Hartatik Hidayah, Insani Nur Hisyam Wahid Luthfi Hisyam Wahid Luthfi . Ida Asta Rina Ida Astarina - Fakultas Teknologi Informatika UNIVERSITAS SURAKARTA Ismu ‘Adhim Kaharudin Setiyawan Luky Adrianto Muhammad Asri Safi'ie Muhammad Khoirul Nanang Maulana Yoeseph Nur Badri Nursahid . Nurul Firdaus Ongki Risti Pramitha Dita Syilvia Prihandoko Eko Putro Prihandoko Eko Putro - Fakultas Teknologi Informatika Universitas Surakarta Pringgo Winoto Purnama, Bambang Eka Puryanto . Ramadian Agus Triyono Riky Hardianti Rindo, Akhmad Rini Purwanti Rokhimah Ratnawati Rokhimah Ratnawati - Fakultas Teknologi Informatika Universitas Surakarta Rudi Hartono Sahirul Alim Tri Bawono Salsabila, Unik Hanifah Samuri . Sinta Susilowati Sri Haryanti Sri1 Haryanti Sukadi . Tri Agus Setiawan Tri Irianto TJ Yanuarti, Rosita Yoni Widhiarso Yusfida A'la, Fiddin