Article Per Year (5 Year)
p-Index From 2021 - 2026
2.552
P-Index
This Author published in this journals
All Journal Jurnal Sains dan Seni ITS JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Onoma: Pendidikan, Bahasa, dan Sastra bit-Tech Indonesian Journal of Data and Science Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Nusantara Science and Technology Proceedings Djtechno: Jurnal Teknologi Informasi Journal of Renewable Energy, Electrical, and Computer Engineering Journal of Artificial Intelligence and Digital Business SAINTEK Jurnal PETISI (Pendidikan Teknologi Informasi)
Aviolla Terza Damaliana
Data Science Department, Faculty Of Computer Science, Universitas Pembangunan Nasional “Veteran” Jawa Timur, Surabaya 60294, Indonesia
Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Medicine & Pharmacology

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
PERBANDINGAN ALGORITMA HDBSCAN DAN AGGLOMERATIVE HIERARCHICAL CLUSTERING DALAM MENGELOMPOKKAN DATA KETENAGAKERJAAN YANG OUTLIERS Citra Amelia Intan Permadani; Aviolla Terza Damaliana; Mohammad Idhom
Djtechno: Jurnal Teknologi Informasi Vol 6, No 2 (2025): Agustus
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/djtechno.v6i2.7237

Abstract

Ketenagakerjaan merupakan indikator penting dalam mendukung pembangunan ekonomi nasional. Namun, distribusi tenaga kerja di Indonesia masih menunjukkan ketimpangan antarprovinsi. Beberapa provinsi memiliki kontribusi ekonomi dan tingkat pekerjaan formal yang tinggi, sementara yang lain tertinggal. Penelitian ini bertujuan mengidentifikasi pola distribusi ketenagakerjaan antarprovinsi dengan menerapkan analisis klaster menggunakan delapan variabel dari data BPS. Mengingat adanya pencilan dalam data, deteksi outlier dilakukan menggunakan metode Local Outlier Factor (LOF) yang mengidentifikasi enam provinsi sebagai outlier yaitu Jawa Barat, Jawa Tengah, Jawa Timur, DKI Jakarta, Banten, dan Sumatera Utara. Selanjutnya, data dianalisis menggunakan dua pendekatan klasterisasi, yaitu Agglomerative Hierarchical Clustering (Single, Complete, Average Linkage, dan Ward) dan HDBSCAN untuk membandingkan ketahanan metode terhadap data outlier. Validasi kualitas klaster dilakukan dengan Silhouette Coefficient. Hasil menunjukkan bahwa metode Single Linkage memiliki nilai koefisien tertinggi, namun kurang konsisten dalam memisahkan outlier. Sebaliknya, HDBSCAN lebih adaptif terhadap data yang mengandung noise dan pencilan dengan Silhouette Coefficient sebesar 0.546. Dengan demikian, HDBSCAN dinilai lebih efektif dalam analisis klasterisasi data ketenagakerjaan yang kompleks, sementara metode AHC lebih unggul dalam membentuk klaster yang jelas jika pencilan dapat ditangani secara terpisah.
Bahasa Inggris Nasywa Azzah Nabila; Aviolla Terza Damaliana; Shindi Shella May Wara
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12734

Abstract

Floods are among the most frequent natural disasters in Indonesia, with thousands of events causing significant impacts on infrastructure damage and human lives. The substantial increase in the number of victims and flood-related damages in 2024 indicates that flood disaster mitigation efforts in Indonesia remain suboptimal. Consequently, a clustering-based analytical approach is required to understand patterns of flood impact across provinces. This study aims to cluster provinces in Indonesia based on flood-affected indicators using the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) method with Bayesian Optimization to obtain optimal hyperparameters. This study comprises several stages, including data collection, data standardization, statistical test, data reduction, hyperparameter optimization, HDBSCAN algorithm, model evaluation, and analysis of clustering results. The results show that HDBSCAN with Bayesian Optimization yields a well-separated cluster structure with a DBCV value of 0.515. The clustering results consist of three primary clusters and one noise cluster. Cluster 0 (High Displacement & Inundation) consisting of 5 provinces, cluster 1 (High Fatality & Structural Damage) consisting of 4 provinces, cluster 2 (Low Impact) consisting of 21 provinces, and the noise cluster consisting of 8 provinces. These findings are intended to provide a foundation for the government to formulate targeted flood mitigation strategies tailored to the flood impact characteristics of each province.
Implementasi Metode Ensemble ROCK dalam Pengelompokan UMKM di Kabupaten Malang Reza Sadiya Purwadwika; Kartika Maulida Hindrayani; Aviolla Terza Damaliana
JURNAL PETISI (Pendidikan Teknologi Informasi) Vol. 7 No. 1 (2026): JURNAL PETISI (Pendidikan Teknologi Informasi)
Publisher : Universitas Pendidikan Muhammadiyah Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36232/jurnalpetisi.v7i1.3396

Abstract

UMKM memiliki peran penting dalam perekonomian nasional, namun masih menghadapi berbagai permasalahan seperti rendahnya pemanfaatan teknologi, keterbatasan akses permodalan, dan lemahnya daya saing. Kompleksitas karakteristik data UMKM yang mencakup variabel numerik dan kategorikal menjadi tantangan dalam analisis dan pemetaan yang akurat. Penelitian ini bertujuan untuk mengelompokkan UMKM di Kabupaten Malang berdasarkan karakteristik usaha dan pelaku usahanya dengan pendekatan ensemble clustering menggunakan algoritma ROCK. Data terdiri dari 75 entri UMKM yang mencakup variabel numerik (omset, modal, tenaga kerja) dan kategorikal (jenis usaha, penggunaan aplikasi transportasi daring). Clustering dilakukan secara terpisah dengan Agglomerative Hierarchical Clustering untuk data numerik dan ROCK untuk data kategorikal. Hasil kedua metode digabungkan menggunakan pendekatan ensemble untuk memperoleh klaster yang lebih stabil dan representatif. Parameter optimal diperoleh pada theta = 0,05 dan k = 4 dengan nilai Clustering Purity (CP*) sebesar 0,8148 dan Davies-Bouldin Index sebesar 0,3817, menunjukkan pemisahan cluster yang baik. Cluster akhir menunjukkan perbedaan signifikan dalam skala usaha, pemanfaatan teknologi digital, dan performa ekonomi. Temuan ini diharapkan menjadi dasar dalam merancang kebijakan pengembangan UMKM yang lebih tepat sasaran dan berbasis data.
Comparison of the Effectiveness IndoBERT and mBERT for Sentiment Analysis of SME Customer Reviews Selena Nurmanina Afandy; Kartika Maulida Hindrayani; Aviolla Terza Damaliana
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3501

Abstract

This study presents a structured comparative evaluation of IndoBERT and Multilingual BERT (mBERT) for three-class sentiment classification of customer reviews from Pawonkoe Banyuwangi, an Indonesian small and medium-sized enterprise (SME). Motivated by the limited transferability of IndoNLU-style benchmarks to real SME feedback, the central question is whether monolingual versus multilingual transformers remain reliable when fine-tuned on small, domain-specific, and operationally noisy datasets. A total of 365 survey-based reviews (January–December 2024), which is substantially smaller than typical transformer fine-tuning corpora, served as the empirical basis. Models were fine-tuned under matched hyperparameters and evaluated using a single stratified hold-out train–test split (not cross-validation), reporting accuracy, precision, recall, and F1-score. To reflect the deployed pipeline, mBERT additionally incorporates the original 1–5 rating as an auxiliary numeric signal alongside the review text, whereas IndoBERT is trained on text only. The results reveal a substantial performance gap: mBERT achieved 81% test accuracy, whereas IndoBERT reached 48% under the same evaluation setting. Because the label distribution is strongly imbalanced (with very few negative instances), these aggregate scores should be interpreted as overall effectiveness rather than minority-class robustness. Overall, the findings indicate that multilingual representations combined with auxiliary rating information can generalize more effectively in low-resource SME scenarios, while IndoBERT appears more sensitive to data scarcity in this context. The study offers practical guidance for model selection in resource-constrained Indonesian sentiment analytics and contributes evidence on transformer behavior beyond curated benchmarks.
Modeling the Open Unemployment Rate in West Java: A Comparison of Panel Data Regression Models Mohamad Ibnu Fajar Maulana; Aviolla Terza Damaliana; Wahyu Syaifullah J. S.
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3705

Abstract

The Open Unemployment Rate (OUR) across regencies and municipalities in West Java Province reflects substantial structural heterogeneity associated with divergent local socio-economic dynamics. This study addresses the central question of which socio-economic factors systematically explain within-region variations in unemployment over time when unobserved, time-invariant regional heterogeneity is explicitly controlled. Using annual panel data for 27 regencies/cities over the period 2019–2024 (162 observations), a panel regression framework is implemented through a One-Way Fixed Effects (OWFE) model estimated via the Least Squares Dummy Variable (LSDV) approach. The explanatory variables include Regency/City Minimum Wage (UMK), Labor Force Participation Rate (TPAK), and Human Development Index (IPM). Beyond conventional fixed-effects applications, the analysis integrates a backward elimination procedure within the OWFE framework to derive a parsimonious specification; this refinement is treated as an exploratory model-selection strategy and interpreted cautiously with respect to potential sample sensitivity. Model comparison based on the Chow and Hausman tests confirms the superiority of OWFE over pooled and random specifications. The final model demonstrates substantial explanatory power (R² = 0.813) and acceptable predictive accuracy (MAPE = 10.73%), indicating that a large proportion of within-region unemployment variation is captured. Diagnostic tests show no evidence of autocorrelation (Durbin–Watson = 1.777) or heteroskedasticity under the implemented procedures. Empirically, TPAK and IPM exhibit significant negative associations with unemployment, while UMK shows a positive relationship, highlighting human capital, participation dynamics, and wage–employment trade-offs in regional labor markets.
Generalized Autoregressive Conditional Heteroskedasticity Approach for Television Program Viewership Trend Analysis Alyssa Amorita Azzah; Aviolla Terza Damaliana; Wahyu Syaifullah Jauharis Saputra
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3710

Abstract

This study aims to determine whether daily television audience dynamics exhibit statistically significant conditional variance dependence that is systematically overlooked in conventional ARIMA-based broadcasting forecasts and to assess the incremental empirical value of integrating ARIMA with GARCH modeling. Using 1,096 consecutive daily observations (2022–2024) of viewers for a nationally broadcast program, we implement a diagnostic-first framework that jointly evaluates conditional mean and variance processes. Stationarity is confirmed through the Augmented Dickey–Fuller test (ADF = −3.4693, p = 0.0088), and an MA(1) specification is selected for the conditional mean (AIC = 1302.76). Residual diagnostics reveal pronounced ARCH effects (ARCH-LM = 78.4602, p < 0.001), justifying second-moment modeling. Among competing variance specifications, GARCH(2,2) yields the lowest information criterion (AIC = 1060.321) and indicates near-unit volatility persistence (Σα + Σβ = 0.9856), evidencing durable intertemporal uncertainty transmission. Out-of-sample forecast evaluation demonstrates low relative error (MAPE ≈ 1.0%), supporting empirical robustness. Unlike prior ARIMA-centered broadcasting studies that prioritize point accuracy under homoscedastic assumptions, this integration explicitly models volatility clustering as an object of inference, aligning media analytics with established volatility frameworks without overstating cross-domain novelty. The findings show that incorporating conditional variance dynamics provides measurable gains in risk-sensitive forecasting, offering a replicable approach for advertising allocation and scheduling decisions in competitive media environments.
Indonesian Cyberbullying Detection Using IndoBERTweet-BiGRU Model on Class-Imbalanced X (Twitter) Data Fajria Ulumin Nafiah; Aviolla Terza Damaliana; Kartika Maulida Hindrayani
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13686

Abstract

Cyberbullying on social media platforms, particularly X (formerly Twitter), has become a serious issue that negatively affects users' mental health and well-being. Automatic cyberbullying detection in Indonesian remains challenging due to the widespread use of informal language, slang, abbreviations, and highly imbalanced class distributions. This study proposes a hybrid deep learning model that integrates IndoBERTweet with a Bidirectional Gated Recurrent Unit (BiGRU) to improve cyberbullying detection performance on Indonesian tweets. A dataset of Indonesian tweets was collected from X and annotated using a multi-stage dual large language model (LLM) labeling strategy to reduce the time and effort required for manual annotation while maintaining label consistency. To address class imbalance, this study investigates the effectiveness of Focal Loss and label distribution modification through multiple experimental scenarios. The proposed approach was evaluated using accuracy, precision, recall, and F1-score. The best performance was achieved by combining Focal Loss with a modified four-class label configuration consisting of Rude and Vulgar Words, Sexual Harassment, Body Shaming and Hate Speech, and Non-Cyberbullying. This configuration obtained an accuracy of 0.93, precision of 0.90, recall of 0.90, and F1-score of 0.90. These findings demonstrate that integrating contextual language representations with sequential modeling, supported by an efficient LLM-assisted labeling strategy and class imbalance handling, provides an effective approach for Indonesian cyberbullying detection and offers a practical solution for large-scale social media content moderation.
Implementation of a Hybrid TabNet–XGBoost Model Based on Radiosonde Data for Predicting Daily Rainfall Intensity in Surabaya Annabel Gracia Puryani; Aviolla Terza Damaliana; Alfan Rizaldy Pratama
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13767

Abstract

Rainfall prediction plays an important role in supporting hydrometeorological disaster mitigation and weather-related decision-making. However, accurate rainfall prediction remains challenging because atmospheric processes are highly nonlinear and governed by complex interactions among multiple meteorological variables. This study proposes a Hybrid TabNet–XGBoost model for daily rainfall prediction using integrated radiosonde and surface meteorological observations collected at the BMKG Juanda Class I Meteorological Station. The dataset covers the period from 2019 to 2025 and consists of 2,551 daily observations. TabNet was employed to select the fifteen most informative atmospheric variables based on feature importance, while temporal dependencies were incorporated through lag features generated using Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) analyses. Hyperparameter optimization was performed using Optuna with TimeSeriesSplit cross-validation prior to model training. Experimental results on the testing dataset achieved an RMSE of 19.1347 mm, an MAE of 11.9742 mm, a MAPE of 17.62%, and an R² of 0.0449. The proposed model was able to capture the general temporal pattern of daily rainfall and produced satisfactory predictions under the dominant rainfall conditions represented in the dataset. However, the model exhibited reduced sensitivity to high-intensity rainfall events, resulting in the underestimation of extreme rainfall and a relatively low R² value, primarily due to the imbalanced rainfall distribution and the complexity of rainfall processes. The optimized model was subsequently applied to generate daily rainfall projections for 2026 based on historical atmospheric observations. Since the corresponding observational data were unavailable at the time of this study, these projections should be interpreted as model-based forecasts rather than validated prediction results. Overall, the proposed Hybrid TabNet–XGBoost framework demonstrates the potential of integrating radiosonde and surface meteorological observations for daily rainfall prediction while highlighting the need for additional atmospheric and spatial information to improve the prediction of extreme rainfall events.
Co-Authors Abdul Rezha Efrat Najaf Adinda Rusdianti Maulani Putri Alfan Rizaldy Pratama Alyssa Amorita Azzah Anas Ahmadi Annabel Gracia Puryani Brescia Ayundina Yuniarossy Citra Amelia Intan Permadani Dea Putri Pascha Febriyanti Dina Magdalena Manurung Dwi Arman Prasetya Fajria Ulumin Nafiah Ilmatus Sa’diyah Irma Amanda Putri Kartika Maulida Hindrayani M Naswan Izzudin Akmal Mohamad Ibnu Fajar Maulana Mohammad Idhom Mohammad Idhom Muhammad Idhom Muhammad Muharrom Al Haromainy Nabila Rizky Amalia Putri Nasywa Azzah Nabila Permatasari, Reisa Reza Sadiya Purwadwika Rizki Amanda Sandria Amelia Putri Selena Nurmanina Afandy Setiawan Setiawan Shindi Shella May Wara Trimono Trimono Trimono, Trimono Wahyu Syaifullah J. S. Wahyu Syaifullah Jauharis Saputra