Claim Missing Document
Check
Articles

The effect of Chi-Square Feature Selection on Question Classification using Multinomial Naïve Bayes Yusliani, Novi; Aruda, Syechky Al Qodrin; Marieska, Mastura Diana; Saputra, Danny Mathew; Abdiansah, Abdiansah
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 4 (2022): Article Research: Volume 6 Number 4, October 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i4.11788

Abstract

Question classification is one of the essential tasks for question answering system. This task will determine the expected answer type (EAT) of the question given to the system. Multinomial Naïve Bayes algorithm is one of the learning algorithms that can be used to classify questions. At the classification stage, this algorithm used a set of features in the knowledge model. The number of features used can result in curse of dimensionality if the feature is in high dimension. Feature selection can be used to reduce the feature dimension and could increase the system performance. Chi-Square algorithm can be used to select features that describe each category. In this research, the Multinomial Naïve Bayes is used to classify the question sentences and the Chi-Square algorithm is used for the feature selection. The dataset used is a set of Indonesian question sentences, consisting of 519 labeled factoids, 491 labeled non-factoids, and 185 labeled other. The test results showed an increase in accuracy of 0.1 when used feature selection. System accuracy when used feature selection is 0.87 with the number of features used are 248. Without feature selection, the accuracy is 0.77 with the number of features used are 1374.
Ekstraksi Kata Kunci pada Bahasa Indonesia Menggunakan Metode Yake Yusliani, Novi; Plakasa, Gerald; Abdiansah, Abdiansah; Marieska, Mastura Diana; Saputra, Danny Matthew
Jurnal Linguistik Komputasional Vol 6 No 1 (2023): Vol. 6, NO. 1
Publisher : Indonesia Association of Computational Linguistics (INACL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jlk.v6i1.117

Abstract

Peneliti, Mahasiswa, dan Juga Dosen biasanya melakukan penelitian untuk menghasilkan publikasi hasil penelitiannya. Saat ini pertumbuhan publikasi ilmiah terus meningkat. ketika publikasi akan di berikan ke reviewer maka publikasi yang kirimkan harus sesuai dengan bidang yang diampu oleh reviewer tersebut. Salah satu cara untuk mengetahui inti dari sebuah publikasi ilmiah yaitu dengan melakukan ekstraksi kata kuncinya. Metode yang digunakan untuk ekstraksi kata kunci salah satunya yaitu YAKE (Yet Another Keyword Extraction). Penelitian ini menggunakan dataset 100 publikasi ilmiah dari website jtiik, jatisi, dan jepin dengan topik Ilmu Komputer. Berdasarkan penelitian yang telah dilakukan, konfigurasi pada parameter Levenshtein Distance memiliki pengaruh terhadap hasil kata kuncinya. Evaluasi dari penelitian ini menghasilkan nilai f-measure sebesar 54,1% dan nilai akurasi sebesar 97,05% dengan parameter Levenshtein Distance < 2.
Pencarian Tugas Akhir dengan Ontologi dan Boyer-Moore (Studi Kasus: Jurusan Teknik Informatika UNSRI) Rodiah, Desty; Yunita, Yunita; Yusliani, Novi
Generic Vol 15 No 1 (2023): Vol 15, No 1 (2023)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/generic.v15i1.140

Abstract

Website sipeta.ilkom.unsri.ac.id adalah website yang menampung data tugas akhir mahasiswa Jurusan Teknik Informatika UNSRI. Namun website tersebut menggunakan penyimpanan dengan basis data biasa. Pada penelitian ini membuat pencarian data tugas akhir mahasiswa dengan memanfaatkan web semantik ontologi agar data yang dimiliki tidak hanya memiliki nilai, tetapi juga memiliki pengetahuan tentang relasi antar informasi yang saling berkaitan. Komponen yang digunakan dalam teknologi semantik adalah RDF yang dipergunakan sebagai representasi pengetahuan yang digunakan, kemudian SPARQL yang digunakan sebagai query untuk mengambil informasi yang terdapat dalam Ontologi RDF. Selain itu juga digunakan Algoritma Boyer Moore untuk mendapatkan nilai similarity antara data yang didapatkan dari hasil pencarian dengan keyword yang dimasukkan. Jenis pencarian yang dirancang ada 3 pencarian yaitu keyword search, simple search dan advanced search. Dan ketiga pencarian tersebut juga akan di kombinasikan dengan algoritma Boyer Moore. Hasil pencarian dengan ontologi dengan pencarian dengan ontologi dan Algoritma Boyer Moore dihasilkan bahwa pencarian dengan Boyer Moore membutuhkan waktu lebih lama secara rata-rata sekitar >=0,0001 perdetik dalam 5 kali percobaan dibandingkan pencarian dengan ontologi saja. Untuk Algoritma Boyer Moore dilakukan pengujian dengan ROC didapatkan hasil akurasi sebesar 99,84% untuk 16 kali percobaan.
Keyphrase Extraction Using TextRank for Indonesian Text Muhammad, Fadel; Yusliani, Novi; Rachmatullah, Muhammad Naufal
Sriwijaya Journal of Informatics and Applications Vol 5, No 1 (2024)
Publisher : Fakultas Ilmu Komputer Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/sjia.v5i1.62

Abstract

Keywords are commonly used as a form of summary from scientific publications. But in determining keywords, it requires expertise in the related field and a long amount of time because you have to read and understand the entire contents of scientific publications. Keyphrase Extraction can be a solution to get relevant keywords in a short time based on titles and abstracts from scientific publications. TextRank method is used to extract keywords. This research will perform keyword extraction using the TextRank method for Indonesian text. The evaluation results of this study showed an accuracy value of 95.53% and an f1-score of 59.32% with a threshold configuration of 80% and using all keyword candidates.
Education for Sustainable Development Based of Technological Pedagogical and Content Knowledge using Mixed-Methods Approach in Physics Teaching Ariska, Melly; Anwar, Yenny; Widodo, Ari; Sari, Diah Kartika; Yusliani, Novi; Rahmannisa, Amanda; Az Zahra, Lutfiah; Milka, Ikbal Adrian; Al Fatih, Zaky
Jurnal Penelitian & Pengembangan Pendidikan Fisika Vol. 10 No. 2 (2024): JPPPF (Jurnal Penelitian dan Pengembangan Pendidikan Fisika), Volume 10 Issue
Publisher : Program Studi Pendidikan Fisika Universitas Negeri Jakarta, LPPM Universitas Negeri Jakarta, HFI Jakarta, HFI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/1.10217

Abstract

Sustainable development aims to raise the standard of living for present and future generations. The Sustainable Development Goals (SDGs) are a set of 17 objectives related to sustainable development. Education for Sustainable Development, or ESD, is one initiative to achieve the SDGs. Presenting the findings of literature research on the features and use of ESD in science education is the goal of this paper. The primary source material for this literature study came from seven publications published in different journals. This study utilized a mixed-methods approach with a concurrent triangulation design involving questionnaires, interviews, and FGDs with 78 physics teachers. The TPACK scores showed a mean of 3.10, with the highest score in Attitude (3.27) and the lowest in Inquiry (3.04). The analysis's findings indicate that 1) Eight critical competencies are thought to be crucial for promoting sustainable development. 2) Learning tools, learning media, and learning models are ways ESD can be included in science education. These findings demonstrate that integrating ESD capabilities into science instruction can promote sustainable development and help attain the SDGs. The results highlight the need for targeted training in inquiry-based approaches and technology integration to enhance ESD implementation in physics education.
Hyperparameter optimization of convolutional neural network using particle swarm optimization for emotion recognition Rini, Dian Palupi; Sari, Tri Kurnia; Sari, Winda Kurnia; Yusliani, Novi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 1: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i1.pp547-560

Abstract

Emotion identification has been widely researched based on facial expressions, voice, and body movements. Several studies on emotion recognition have also been performed using electroencephalography (EEG) signals and the results also show that the technique has a high level of accuracy. EEG signals that detected by standart method using exclusive representations of time and frequency domains presented unefficient results. Some researchers using the convolutional neural network (CNN) method performed EEG signal for emotional recognition and obtained the best results in almost all benchmarks. Although CNN has shown fairly high accuracy, there is still a lot of room for improvement. CNN is sensitive to its hyperparameter value because it has considerable effect on the behavior and efficiency of the CNN architecture. So that the use of optimization algorithms is expected to provide an alternative selection of appropriate hyper parameter values on CNN. Particle swarm optimization (PSO) algorithm is a metaheuristic-based optimization algorithm with many advantages. This PSO algorithm was chosen to optimize the hyperparameter values on CNN. Based on the evaluation results in each model, hybrid CNN-PSO showed better results and achieved the best value in 80:20 split data which is 99.30% accuracy.
PENINGKATAN MOTIVASI BELAJAR SISWA SMA MELALUI PENDEKATAN PEMROGRAMAN KOMPUTER Abdiansah, Abdiansah; Utami, Alvi Syahrini; Yusliani, Novi; Miraswan, Kanda Januar; Wedhasmara, Ari
Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Vol. 1 No. 4 (2023): Agustus
Publisher : CV. Alina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59407/jpki2.v1i4.56

Abstract

PISA adalah penilaian tingkat internasional yang diselenggarakan setiap tiga sekali untuk menguji kemampuan akademis siswa yang berusia 15 tahun. Tujuan PISA adalah untuk menguji dan membandingkan prestasi anak-anak sekolah di seluruh dunia. Nilai PISA Indonesia di tahun 2018 masih rendah untuk ketiga bidang yang dinilai, yaitu: Matematika, Sains, dan Membaca. Untuk mengatasi hal tersebut dibutuhkan metode pembelajaran yang mampu memotivasi belajar siswa, terutama di bidang STEM (Science, Technology, Engineering, Math). Salah satu metode kegiatan yang dapat meningkatkan motivasi siswa adalah dengan memberikan pengenalan konsep dan praktik pemrograman komputer untuk diterapkan di bidang matematika, fisika, dan kimia. Hasil evaluasi menunjukkan bahwa terjadi peningkatan kemampuan belajar siswa sebesar 15.00% (N-Gain) meskipun secara keseluruhan hasilnya masih belum signifikan. Meskipun demikian hasil evaluasi kegiatan pelatihan cukup memuaskan dengan nilai sebesar 84.91% (Skala Likert). Hasil tersebut membuktikan bahwa pendekatan pemrograman komputer untuk meningkatkan motivasi belajar siswa di bidang STEM cukup menjanjikan. Kata Kunci: PISA, STEM, Pemrograman Komputer
Recommender System for Tourist Destinations in Indonesia Using Matrix Factorization Method Saputra, Danny Matthew; Angelia, Nadya; Yusliani, Novi
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 5 No 3 (2024)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.5.3.254

Abstract

Indonesia has various tourist destinations. The large number of tourist destinations makes people confused about choosing a suitable tourist destination. The recommendation system is an appropriate way to help Indonesians choose tourist destinations that suit their preferences. One recommendation system method is matrix factorization. This research uses a matrix factorization algorithm, Alternating Least Square (ALS). The dataset used is Indonesia Tourism Destination from Kaggle. Based on research that has been carried out, this algorithm is successful in predicting tourist attractions that suit users. The evaluation results are an MAE value of 1.27203388032266, while the RMSE value is 1.475271987.
Aplikasi QR-code untuk sistem daftar hadir: Solusi digitalisasi administrasi di SMA dan SMK Rodiah, Desty; Yusliani, Novi; Abdiansah; Utami, Alvi Syahrini; Miraswan, Kanda Januar; Marieska, Mastura Diana; Yunita; Rini, Dian Palupi
Jurnal Inovasi Hasil Pengabdian Masyarakat (JIPEMAS) Vol 8 No 2 (2025)
Publisher : University of Islam Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33474/jipemas.v8i2.22696

Abstract

Kebijakan Merdeka Belajar dari Kemendikbud RI mendorong guru untuk menerapkan pendekatan pengajaran yang fleksibel dan adaptif melalui integrasi teknologi dalam kegiatan pembelajaran. Dalam konteks ini, program pengabdian kepada masyarakat memberikan pelatihan untuk mengembangkan sebuah aplikasi daftar hadir berbasis QR-Code menggunakan Python untuk guru SMA dan SMK. Aplikasi ini dirancang untuk mencatat kehadiran siswa secara cepat, tepat, dan efisien, serta mendukung kemudahan administrasi dan memberikan pengalaman langsung dalam penggunaan teknologi pemrograman. Kegiatan pengabdian ini menerapkan metode Participatory Action Research (PAR), yang meliputi lima tahap: To Know (menggali kebutuhan mitra melalui survei), To Understand (mengevaluasi pelatihan sebelumnya), To Plan (menyusun materi dan instrumen evaluasi), To Act (melaksanakan pelatihan melalui presentasi dan praktikum), dan To Change (melakukan evaluasi). Evaluasi dilakukan dengan pendekatan N-Gain dan skala Likert. Hasil N-Gain sebesar 20,90% menunjukkan efektivitas pelatihan yang kurang meskipun terdapat peningkatan nilai rata-rata sebesar 7,37 poin. Hal ini dipengaruhi oleh latar belakang peserta yang sudah berpengalaman, sehingga materi dan soal perlu dikembangkan lebih lanjut. Di sisi lain, hasil Likert menunjukkan persepsi peserta yang sangat positif. Kendala koneksi internet sempat memengaruhi praktikum, namun narasumber dan mahasiswa aktif membantu peserta yang mengalami hambatan tersebut.
Comparing Word Representation BERT and RoBERTa in Keyphrase Extraction using TgGAT Novi Yusliani; Aini Nabilah; Muhammad Raihan Habibullah; Annisa Darmawahyuni; Ghita Athalina
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 2 (2025): April 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i2.6279

Abstract

In this digital era, accessing vast amounts of information from websites and academic papers has become easier. However, efficiently locating relevant content remains challenging due to the overwhelming volume of data. Keyphrase Extraction Systems automate the process of generating phrases that accurately represent a document’s main topics. These systems are crucial for supporting various natural language processing tasks, such as text summarization, information retrieval, and representation. The traditional method of manually selecting key phrases is still common but often proves inefficient and inconsistent in summarizing the main ideas of a document. This study introduces an approach that integrates pre-trained language models, BERT and RoBERTa, with Topic-Guided Graph Attention Networks (TgGAT) to enhance keyphrase extraction. TgGAT strengthens the extraction process by combining topic modelling with graph-based structures, providing a more structured and context-aware representation of a document’s key topics. By leveraging the strengths of both graph-based and transformer-based models, this research proposes a framework that improves keyphrase extraction performance. This is the first to apply graph-based and PLM methods for keyphrase extraction in the Indonesian language. The results revealed that BERT outperformed RoBERTa, with precision, recall, and F1-scores of 0.058, 0.070, and 0.062, respectively, compared to RoBERTa’s 0.026, 0.030, and 0.027. The result shows that BERT with TgGAT obtained more representative keyphrases than RoBERTa with TgGAT. These findings underline the benefits of integrating graph-based approaches with pre-trained models for capturing both semantic relationships and topic relevance.
Co-Authors Abdiansah Abdiansah, Abdiansah Abdiansyah Ahmad Fali Oklilas Aini Nabilah Al Fatih, Zaky Alvi Syahrini Alvi Syahrini Utami Angelia, Nadya Anna Dwi Marjusalinah Annisa Darmawahyuni Ari Firdaus Ari Firdaus Ari Wedhasmara Ari Widodo Ariska, Meli Armansyah, Risky Armenia Yuhafiz Aruda, Syechky Al Qodrin Aspirani Utari Astero Nandito Ayu Purwarianti Az Zahra, Lutfiah Betharia Sri Fitrianti Danny Matthew Saputra Darmawahyuni, Annisa Darmawahyuni, Annisa Deris Stiawan Desty Rodiah Desty Roodiah Dhiya Fairuz Diah Kartika Sari Dian Palupi Rini Dian Palupi Rini Dian Palupi Rini Fadel Muhammad, Fadel Firdaus Firdaus Fitria Khoirunnisa Ghita Athalina Gilbert Christopher Jambak, Muhammad Ihsan Kanda Januar Miraswan Kartika, Diah Lidya Irfiyani Silaban M Fachrurrozi M. Fachrurrozi . Mastura Diana Marieska Melly Ariska Milka, Ikbal Adrian Muhammad Fachrurrozi Muhammad Fachurrozi Muhammad Naufal Rachmatullah Muhammad Omar Braddley Muhammad Raihan Habibullah Muhammad Rizqi Assabil Muharromi Maya Agustin Nur Hamidah Nurul Izzah Oktadini, Nabila Rizky Osvari Arsalan Plakasa, Gerald Rahma Haniffia Rahmannisa, Amanda Rahmat Fadli Isnanto Raisha Fatiya Reyhan Navind Shaquille Ridho Putra Sufa Rifka Widyastuti Rizki Kurniati Rizki Ramadandi Rusdi Efendi Saputra, Danny Mathew Saputra, Danny Matthew Sari, Tri Kurnia septi ana Siti Nurmaini Syechky Al Qodrin syechky al qodrin aruda Tiara Dewangga Tristi Dwi Rizki Wenty Octaviani Winda Kurnia Sari Yenny Anwar Yesi Novaria Kunang YUNITA Yunita Yunita Yunita Yunita Yunita Yunita