Article Per Year (5 Year)
p-Index From 2021 - 2026
1.197
P-Index
This Author published in this journals
All Journal SIGMA: Jurnal Pendidikan Matematika JAMBURA JOURNAL OF PROBABILITY AND STATISTICS Griya Journal of Mathematics Education and Application Research Review: Jurnal Ilmiah Multidisiplin Jurnal Riset Mahasiswa Matematika Sciencestatistics: Journal of Statistics, Probability, and Its Application Journal of Mathematics, Computation and Statistics (JMATHCOS)
Siti Nurmardia Abdussamad
Universitas Negeri Gorontalo
Humanities Computer Science & IT Decision Sciences, Operations Research & Management Education Environmental Science Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Comparison of Multiple Kernel Learning and Single Kernel Support Vector Machine for Public Opinion Classification Shafiah Poliyama; Novianita Achmad; Siti Nurmardia Abdussamad
Journal of Mathematics, Computations and Statistics Vol. 9 No. 1 (2026): Volume 09 Issue 01 (March 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/qea76e33

Abstract

Abstract. Social media has become a digital public space where public opinion is expressed on various government policies. Social media platform X has become a major venue for openly expressing support and criticism, making it relevant to sentiment analysis. This condition is useful for understanding public perceptions of government policies, such as the Makan Bergizi Gratis (MBG) Programme, which has elicited various public responses since its implementation. Support Vector Machine (SVM) is a widely used method for sentiment classification, but its performance is highly dependent on kernel selection. Using a single kernel type often fails to capture both linear and non-linear patterns in social media texts. Therefore, this study aims to compare the performance of Single Kernel and Multiple Kernel Learning (MKL) in classifying public sentiment from social media X. The research methods included collecting Indonesian language tweets through scraping techniques, text pre-processing, feature extraction using Term Frequency–Inverse Document Frequency (TF–IDF), data division with a ratio of 80:20, and the classification process using SVM with linear kernel, Radial Basis Function (RBF) kernel, and a combination of both through the MKL approach. The results show that MKL based SVM provides the best performance with an accuracy of 93.17%, while Linear and RBF kernels produce accuracies of 91.81% and 92.49%, respectively, on the same dataset and testing scheme.
IMPLEMENTASI WORD EMBEDDING GLOVE PADA SUPPORT VECTOR MACHINE DENGAN PARTICLE SWARM OPTIMIZATION UNTUK ANALISIS SENTIMEN Putu Ayu Indah Nazwa Usia; Isran K Hasan; Siti Nurmardia Abdussamad
SIGMA: JURNAL PENDIDIKAN MATEMATIKA Vol. 18 No. 1: Juni 2026
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/nnc0w522

Abstract

Tujuan: Penelitian ini menerapkan word embedding GloVe pada Support Vector Machine yang dioptimalkan memanfaatkan Particle Swarm Optimization untuk mengevaluasi efektivitas model klasifikasi analisis sentimen ulasan pengguna Indodax di platform media sosial X. Metode: Pada studi ini, data teks diklasifikasikan memanfaatkan pendekatan metodologi kuantitatif. Data berupa 877 cuitan pengguna Indodax di media sosial X yang dikumpulkan melalui teknik scraping menggunakan Python. Tahapan analisis meliputi pengumpulan data, pre-processing data, pelabelan sentimen, word embedding GloVe, pembagian data, Particle Swarm Optimization digunakan guna optimasi parameter, serta Support Vector Machine dimanfaatkan untuk klasifikasi. Hasil: Hasil penelitian menunjukkan bahwa analisis sentiment ulasan pengguna Indodax di media sosial X menghasilkan distribusi sentimen yang relatif seimbang, yaitu sebesar 49,7% sentimen positif dan 50,3% sentimen negatif. Selain itu, melalui skor akurasi sejumlah 82%, presisi 85%, recall 82%, serta f1-score 84%, hasil penilaian model menunjukkan bahwa penerapan word embedding GloVe pada SVM yang dioptimalkan dengan Particle Swarm Optimization dapat menghasilkan performa klasifikasi yang baik. Simpulan: Dengan menggabungkan GloVe word embedding dengan Support vector Machine yang dioptimasi menggunakan PSO, penelitian ini memberikan kontribusi dalam pengembangan metode analisis sentimen berbasis machine learning, serta memberikan implikasi praktis bagi pengelola platform dan pemerintah dalam memahami persepsi pengguna terhadap layanan investasi digital.
Faktor–Faktor yang Berhubungan dengan Kejadian Underweight pada Balita dari Keluarga Petani di Kecamatan Limboto Ni Luh Diyani Swarningsih; Muhammad Rezky Friesta Payu; Amanda Adityaningrum; Rini Wahyuni Mohamad; Vidya Avianti Hadju; Djihad Wungguli; Siti Nurmardia Abdussamad
Griya Journal of Mathematics Education and Application Vol. 6 No. 2 (2026): Juni 2026
Publisher : Pendidikan Matematika FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/griya.v6i2.1050

Abstract

Masalah underweight pada balita masih menjadi tantangan kesehatan masyarakat, khususnya pada komunitas keluarga petani. Kecamatan Limboto merupakan salah satu wilayah dengan prevalensi balita underweight yang tinggi yaitu sebesar 317 kasus pada tahun 2024 dan kembali bertambah menjadi 365 kasus pada tahun 2025. Penelitian ini bertujuan untuk mengetahui hubungan antara faktor kesehatan dan sosial ekonomi dengan kejadian underweight pada balita dari keluarga petani di Kecamatan Limboto. Desain penelitian yang digunakan cross sectional dan teknik sampling purposive sampling. Data diperoleh dari kuesioner yang diisi oleh ibu atau pengasuh utama balita. Analisis data dilakukan menggunakan tabel kontingensi untuk melihat distribusi data dan uji chi-square untuk menguji hubungan antara variabel independen dan kejadian underweight. Hasil penelitian menunjukkan bahwa terdapat hubungan yang signifikan antara riwayat BBLR, riwayat ASI eksklusif, tingkat pengetahuan ibu, pola asuh, dan ketahanan pangan dengan kejadian underweight pada balita. Sementara itu, riwayat penyakit infeksi, tingkat pendidikan ibu dan pendapatan keluarga tidak menunjukkan hubungan yang signifikan. Kesimpulan penelitian ini menunjukkan bahwa faktor kesehatan dan pola pengasuhan memiliki peran penting dalam kejadian underweight pada balita dari keluarga petani, sehingga diperlukan upaya edukasi dan intervensi gizi yang lebih terarah
Perbandingan Jackknife Ridge Regression dan Principal Component Regression dalam Penanganan Kasus Multikolinearitas (Studi Kasus: Indeks Pembangunan Manusia di Indonesia) Nur’ain Manoppo; La Ode Nashar; Djihad Wungguli; Muhammad Rezky F. Payu; Siti Nurmardia Abdussamad; Salmun K. Nasib
Research Review: Jurnal Ilmiah Multidisiplin Vol. 4 No. 1 (2025): Research Review: Jurnal Ilmiah Multidisiplin (Februari 2025 - Juli 2025)
Publisher : Transbahasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54923/researchreview.v4i1.181

Abstract

According to data from Statistics Indonesia, the Human Development Index (HDI) in 2022 reached 72.91, increasing from 72.29 in the previous year. Although Indonesia’s HDI continues to improve, disparities remain among provinces, indicating that HDI distribution is still uneven. Given the importance of HDI in aregion, it is necessary to conduct statistical analysis to identify the factors that significantly influence HDI using regression analysis. In applying multiple linear regression, several classical statistical assumptions must be met, one of which is the central focus of this analysis-addressing the issue of multicollinearity. Several methods have been identified to address multicollinearity, including Jackknife Ridge Regreesion (JRR) and Principal Component Regression (PCR). This study aims to compare the effectiveness of both methods in handling multicollinearity based on Adjusted R2 and Mean Square Error (MSE) and to analyze the factors that significantly influence the HDI level in Indonesia. The data used in this study are secondary data comprising HDI and its related factors for each province in Indonesia in 2022, obtained from bps.go.id. Based on the analysis, the best model uses the JRR method, with an Adjusted R2 value of 96.7% and MSE of 0.033.
Model Regresi Multilevel Negative Binomial Pada Kasus Kronis Filariasis di Indonesia Rizal Usman; Salmun K. Nasib; Djihad Wungguli; Siti Nurmardia Abdussamad
Jambura Journal of Probability and Statistics Vol 6, No 2 (2025): Jambura Journal of Probability and Statistics
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjps.v6i2.31648

Abstract

Filariasis is a contagious disease caused by infection with the parasitic worm Filaria and transmitted through the bite of an infected mosquito. Analysis of the number of chronic filariasis cases in Indonesia often faces statistical problems in the form of overdispersion and excess zero. To overcome this, a Multilevel Negative Binomial Regression model is used which is able to handle data variance that is greater than the average as well as the number of zero values in the data. The results showed that the model was effective in overcoming overdispersion and excess zero problems. Based on the parameter significance test using the Wald test, environmental variables such as the presence of unprotected wells (X4) and household proximity to waste storage (X5) have a significant effect on the number of chronic filariasis cases. In contrast, socioeconomic variables such as percentage of male population (X1), productive age population (X2), proper sanitation (X3), percentage of poor population (X6), and Human Development Index (X7) did not show a significant effect. These findings confirm that environmental factors play an important role in the spread of chronic filariasis cases in Indonesia. 
Implementasi Metode Bidirectional LSTM Dengan Word Embedding FastText Dalam Analisis Sentimen Ulasan Pengguna Aplikasi Maxim Hanz Franklyn Bachruddin Wewengkang; Djihad Wungguli; Nisky Imansyah Yahya; Isran K. Hasan; Siti Nurmardia Abdussamad
Jurnal Riset Mahasiswa Matematika Vol 4, No 5 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i5.33358

Abstract

Aplikasi transportasi online kini menjadi bagian penting dalam kehidupan masyarakat Indonesia. Maxim, sebagai salah satu penyedia layanan, perlu memahami persepsi pengguna untuk meningkatkan kualitas layanannya. Penelitian ini menerapkan metode Bidirectional Long Short-Term Memory (BiLSTM) untuk melakukan klasifikasi sentimen terhadap ulasan pengguna aplikasi Maxim di Google Play Store. Untuk memperkuat representasi kata, digunakan word embedding FastText yang mampu menangkap informasi sub-kata secara lebih baik. Data penelitian diperoleh melalui scraping menggunakan package google-play-scraper pada Python. Model BiLSTM yang dilatih dengan konfigurasi hyperparameter optimal berhasil mengklasifikasikan sentimen ulasan secara efektif, dengan hasil accuracy 94%, precision 96%, recall 95%, dan f1-score 95%. Hasil ini menunjukkan bahwa kombinasi BiLSTM dan FastText mampu mendeteksi sentimen positif dan negatif secara akurat dan seimbang, serta relevan untuk mendukung evaluasi kualitas layanan berbasis opini pengguna.
Empirical Mode Decomposition with Swarm-Optimized Support Vector Regression for Natural Gas Price Forecasting Fajar Putrawan Djabar; Agusyarif Rezka Nuha; Siti Nurmardia Abdussamad
Sciencestatistics: Journal of Statistics, Probability, and Its Application Vol. 4 No. 2 (2026): JULY
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/sciencestatistics.v4i2.12276

Abstract

Natural gas is a strategic energy commodity exhibiting nonlinear and highly volatile price movements due to supply-demand fluctuations, market dynamics, and geopolitical influences. These factors complicate accurate forecasting and necessitate advanced methods capable of modeling complex data patterns. This study proposes a hybrid forecasting model that integrates Empirical Mode Decomposition (EMD), Support Vector Regression (SVR), and Particle Swarm Optimization (PSO) to predict natural gas prices and assess predictive performance. The analysis utilizes a dataset of 1,575 daily closing prices from January 2020 to December 2025. EMD decomposes the original time series into seven Intrinsic Mode Functions (IMFs) and one residual component. Each component is modeled using SVR with a Radial Basis Function (RBF) kernel, and PSO is used to optimize model parameters. Forecasting performance is evaluated using Mean Absolute Percentage Error (MAPE) across three data partitioning schemes. Results indicate that the 70:15:15 partition yields the most accurate model, achieving a MAPE of 2.2641%. The 90-day forecast projects a gradual decline in natural gas prices after a peak in mid-January 2026, followed by relative price stability through March 2026. These findings suggest that the hybrid EMD-SVR-PSO model effectively captures the nonlinear dynamics of natural gas price data and delivers accurate forecasts, positioning it as a valuable decision-support tool for policymakers, industry stakeholders, and investors.
Co-Authors Agusyarif Rezka Nuha Amanda Adityaningrum Djihad Wungguli Fajar Putrawan Djabar Hanz Franklyn Bachruddin Wewengkang Isran K Hasan La Ode Nashar Mohamad, Rini Wahyuni Muhammad Rezky F. Payu Ni Luh Diyani Swarningsih NISKY IMANSYAH YAHYA Nur’ain Manoppo Putu Ayu Indah Nazwa Usia Rizal Usman Salmun K. Nasib Shafiah Poliyama Vidya Avianti Hadju