Article Per Year (5 Year)
p-Index From 2021 - 2026
1.606
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) JOURNAL OF APPLIED INFORMATICS AND COMPUTING IJID (International Journal on Informatics for Development) MIND (Multimedia Artificial Intelligent Networking Database) Journal JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Scientific Journal of Informatics Journal of Mathematics, Computation and Statistics (JMATHCOS) Indonesian Journal of Statistics and Its Applications Teknobuga : Jurnal Teknologi Busana dan Boga
Cici Suhaeni
IPB University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Mathematics Other

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
Making Sense of Fashion Feedback : Comparing Two Popular Text Analysis Tools Muhammad Syafiq; Wawan Saputra; Carlya Agmis Aimandiga; Cici Suhaeni; Bagus Sartono; Gerry Alfa Dito
TEKNOBUGA: Jurnal Teknologi Busana dan Boga Vol. 13 No. 1 (2025)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/teknobuga.v13i1.25930

Abstract

The rapid expansion of the fashion industry, propelled by digital technology and e-commerce, has resulted in a significant volume of customer-generated reviews. These reviews serve as a valuable source for understanding customer satisfaction and behavior. This study aims to (1) analyze customer sentiment, (2) predict product recommendations, and (3) examine the relationship between sentiment classification and recommendation decisions using text embeddings from Word2Vec and GloVe. The research utilized over 23,000 fashion product reviews sourced from Kaggle. Text data were preprocessed and vectorized using Word2Vec and GloVe, followed by classification and prediction tasks using six machine learning models: Random Forest, SVM, Naïve Bayes, LSTM, Logistic Regression, and Gradient Boosting. The results revealed that Word2Vec consistently outperformed GloVe across all models and tasks, with the Word2Vec-LSTM combination achieving the highest accuracy of 87.35% and F1 score of 92.35% in imbalanced data scenarios. Correlation analysis also confirmed a strong and statistically significant relationship between sentiment and recommendation labels, with Spearman’s Rho of 0.8340 and Kendall’s Tau of 0.8120. These findings suggest that high-quality sentiment representation can effectively support product recommendation systems. This study contributes to the understanding of embedding effectiveness in fashion-related text analysis and opens avenues for hybrid and transformer-based representations in future research.
LDA Topic Modeling Analysis of Public Discourse on Indonesia’s Free Nutritious Meals Program (MBG) Cici Suhaeni; Laily Nissa Atul Mualifah; Hari Wijayanto
IJID (International Journal on Informatics for Development) Vol. 14 No. 1 (2025): IJID June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2025.5211

Abstract

This study investigates public discourse on Indonesia's Free Nutritious Meals (Makan Bergizi Gratis/MBG) program through Latent Dirichlet Allocation (LDA) topic modeling of YouTube comments. Filling a research gap on online public opinion regarding the MBG policy, this study identifies dominant themes and discursive patterns in public perception. A three-topic model, validated through coherence score evaluation and pyLDAvis visualization, reveals key topics: concerns over food prices and distribution, perceived benefits for children and society, and emotionally and politically driven reactions. The findings provide valuable insights into public opinion, while also highlighting challenges in processing Indonesian-language text, such as informal language and noisy data. This study contributes to understanding public perceptions of social policies in digital environments and recommends future research directions, including improved text preprocessing and alternative topic modeling approaches. By shedding light on online public discourse, this research informs policymakers and stakeholders about the effectiveness and potential areas for improvement in the MBG program.
IndoBERT Optimization for Sentiment Analysis on DeepSeek App Reviews Muh. Sunan; Unique Desyrre A. Resiloy; Desy Endriani; Cici Suhaeni; Bagus Sartono; Gerry Alfa Dito
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.107507

Abstract

In the digital era, sentiment analysis is important to evaluate public opinion, especially in the context of Play Store apps with Indonesian-language reviews. This research aims to improve the performance of the IndoBERT model in sentiment analysis of DeepSeek app reviews by using data augmentation and hyperparameter tuning techniques. Data augmentation is done through the back-translation technique, while the hyperparameters tested include the number of epochs, learning rate, and batch size. Experimental results show that the combination of data augmentation with epoch 10, learning rate 2e-5, and batch size 16 produces the highest accuracy of 93.95% and F1-score of 0.94, with better stability than the model without augmentation. The model without augmentation showed fluctuations in performance, indicating overfitting in some configurations. These findings confirm the importance of applying augmentation techniques and hyperparameter tuning in improving the accuracy and stability of sentiment analysis models, and contribute to the development of NLP models for Indonesian and other resource-constrained languages.
Sentiment Classification on the 2024 Indonesian Presidential Candidate Dataset Using Deep Learning Approaches Cici Suhaeni; Hari Wijayanto; Anang Kurnia
Indonesian Journal of Statistics and Applications Vol 8 No 2 (2024)
Publisher : Statistics and Data Science Program Study, SSMI, IPB University, in collaboration with the Forum Pendidikan Tinggi Statistika Indonesia (FORSTAT) and the Ikatan Statistisi Indonesia (ISI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/ijsa.v8i2p83-94

Abstract

This study aims to compare the performance of three deep learning models (LSTM, BiLSTM, and GRU) in the task of sentiment classification for the 2024 Indonesian Presidential Candidate dataset, focusing specifically on the case of Prabowo Subianto. The dataset comprises social media X posts sourced from kaggle, and the analysis investigates the effectiveness of different variants of recurrent neural network architectures in identifying public sentiment. The models were evaluated on accuracy and F1 score. The results demonstrate that BiLSTM outperformed both LSTM and GRU models in all metrics, achieving a testing accuracy of 80.70% and an F1 score of 86.86%, compared to LSTM and GRU which both achieved a testing accuracy of 72.56% and an F1 score of approximately 84%. The higher performance of BiLSTM is attributed to its ability to capture bidirectional context within the text, thereby understanding complex sentiment patterns more effectively. LSTM and GRU models displayed similar performance, therefore BiLSTM is the best model for this dataset. These results indicate that BiLSTM is especially well-suited for analyzing public sentiment towards political figures like Prabowo Subianto, offering significant insights into public discussions surrounding the 2024 Indonesian Presidential Election. This study recommends exploring transformer-based models like BERT or GPT variants to enhance sentiment classification accuracy in this domain.
Klasifikasi Halaman SEO Berbasis Machine Learning Melalui Mutual Information dan Random Forest Feature Importance SITI NURADILLA; KUSMAN SADIK; CICI SUHAENI; AGUS M SOLEH
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 10, No 1 (2025): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v10i1.114-129

Abstract

AbstrakProses optimasi SEO melibatkan banyak faktor yang saling terkait, sehingga sulit bagi tim SEO dalam menentukan halaman mana yang memerlukan perbaikan lebih lanjut. Penelitian ini bertujuan untuk mengembangkan model berbasis machine learning yang tidak hanya akurat dalam mengklasifikasikan halaman, tetapi juga efisien dalam memilih fitur yang paling informatif. Metode yang digunakan dalam penelitian ini melibatkan seleksi fitur menggunakan Mutual Information (MI) dan Random Forest Feature Importance (RFFI) untuk mengidentifikasi faktor-faktor yang paling penting untuk optimasi SEO, yang dimodelkan menggunakan Random Forest dan Weighted Voting Ensemble (WVE). Model dievaluasi berdasarkan Accuracy, Precision, Recall, dan ROC AUC. Hasil penelitian menunjukkan bahwa model Random Forest dengan 20 fitur berdasarkan RFFI, memberikan performa terbaik dengan ROC AUC sebesar 75.87%, Accuracy 77,74%, Precision 60,51%, dan Recall 71.29%. Model mampu membedakan secara efektif halaman yang membutuhkan optimasi SEO atau tidak.Kata kunci: Feature Importance, Random Forest, SEO, Seleksi Variabel, WVEAbstractThe SEO optimization process involves many interrelated factors, making it challenging to identify which pages need further improvement. This study proposes a machine learning-based model that is accurate in classifying web pages and efficient in selecting the most relevant features. Feature selection is performed using Mutual Information (MI) and Random Forest Feature Importance (RFFI) to identify key factors for SEO optimization, followed by modeling with Random Forest and Weighted Voting Ensemble (WVE). The model is evaluated using Accuracy, Precision, Recall, and ROC AUC. Results indicate that the Random Forest model with 20 features selected via RFFI delivers the best performance, achieving a ROC AUC of 75.87%, Accuracy of 77.74%, Precision of 60.51%, and Recall of 71.29%. The model effectively distinguishes between pages that require SEO optimization and those that do not.Keywords: Feature Importance, Random Forest, SEO, Variable Selection, WVE
DETECTION OF ADULTERATION IN COCONUT MILK USING CUCKOO SEARCH-OPTIMIZED XGBOOST ON HIGH-DIMENSIONAL FTIR SPECTRAL DATA I Gusti Ngurah Sentana Putra; Kusman Sadik; Agus Mohamad Soleh; Cici Suhaeni
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 3 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i3.8376

Abstract

Coconut milk adulteration is an important issue because it can reduce food quality and endanger consumers. This study aims to develop a rapid and accurate detection method for coconut milk adulteration using a combination of FTIR spectroscopy technology and the XGBoost machine learning algorithm optimized with the Cuckoo Search Algorithm (CSA). FTIR spectral data from traditional and instant coconut milk samples were analyzed using Standard Normal Variate (SNV) and Savitzky-Golay (SG) preprocessing to reduce noise and clarify spectral features. The XGBoost model was then optimized through CSA with hyperparameter tuning. The results showed that the combination of SNV+SG preprocessing increased the model accuracy by 84.44%, with a precision of 92.73% and an F1-score of 79.94%. In addition, CSA optimization provided a 19.7% increase in accuracy compared to the model without tuning. These findings prove the effectiveness of the CSA-XGBoost approach in analyzing high-dimensional spectral data and is a potential solution in efficiently detecting the authenticity of coconut milk. In conclusion, this approach has the potential to be widely applied to test the authenticity of other food products quickly, non-destructively and accurately.
Performance Evaluation of Word2Vec and FastText Embeddings in a CNN-BiLSTM Model for Sentiment Classification of the LPDP Alumni Controversy Dwi Erzalianti; Joice Junansi Tandirerung; Cici Suhaeni; Bagus Sartono
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.v10i4.13298

Abstract

This study aims to analyze public sentiment toward the LPDP alumni controversy on social media using a deep learning approach. The research data consist of YouTube user comments related to the LPDP issue, which were processed through text preprocessing and automatically labeled using IndoBERT into three sentiment classes: negative, neutral, and positive. This study compares two text representation methods, namely Word2Vec and FastText, implemented within a hybrid CNN–BiLSTM architecture. In addition, data imbalance was addressed using class weighting and undersampling scenarios, while TF-IDF-based Logistic Regression was used as the baseline model. The results show that the baseline achieved an accuracy of 0.83 but was strongly biased toward the negative class as the majority class. The CNN–BiLSTM model improved the ability to detect minority classes. Under the class weighting scenario, FastText demonstrated more stable performance with an accuracy of 0.77 and a macro F1-score of 0.62. Under the undersampling scenario, Word2Vec was more stable, achieving an accuracy of 0.68 and a macro F1-score of 0.67. These findings indicate that both text representation and imbalance-handling strategies substantially affect sentiment classification performance.
Gibbs-BERTopic for Topic Modeling of Short Indonesian Social Media Texts on Artificial Intelligence Issues Nur'aini; Budi Susetyo; Cici Suhaeni
Scientific Journal of Informatics Vol. 13 No. 3: Special Issue
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i3.50254

Abstract

Purpose: This study aims to evaluate whether integrating Gibbs Sampling into BERTopic improves topic modeling of short Indonesian social media texts concerning Artificial Intelligence. Baseline BERTopic is used as the primary comparator, while LDA and Top2Vec are included as external baselines representing probabilistic and embedding-based topic-modeling approaches. Methods: A corpus of 9,585 public posts from platform X, collected from January 2024 to May 2025, was modeled using Latent Dirichlet Allocation (LDA), Top2Vec, Baseline BERTopic, and Gibbs-BERTopic. Model performance was assessed using topic coherence, topic diversity, topic uniqueness, number of topics, and document coverage. The number of outliers was compared specifically between Baseline BERTopic and Gibbs-BERTopic because LDA and Top2Vec do not use an equivalent HDBSCAN-based outlier mechanism. Result: Baseline BERTopic generated 58 topics and 4,674 outliers, with coherence, diversity, and uniqueness scores of 0.480, 0.460, and 0.380. Gibbs-BERTopic generated 15 topics without outliers and achieved the highest corresponding scores of 0.510, 0.880, and 0.870. LDA and Top2Vec produced lower scores, with 58 and 84 topics, respectively. These findings indicate that, within the corpus and configuration examined, Gibbs-BERTopic provided a more coherent and distinctive topic representation, broader document coverage, and a more compact topic structure. Novelty: This study extends the evaluation of Gibbs-BERTopic to short Indonesian social media texts and compares it with probabilistic, embedding-based, and BERTopic-based models. The results highlight the importance of evaluating topic models using multiple complementary metrics rather than relying on a single performance measure.
Performance Comparison of Random Forest and XGBoost Optimized with Cuckoo Search Algorithm for Coconut Milk Adulteration Detection Using FTIR Spectroscopy Sentana Putra I Gusti Ngurah; Kusman Sadik; Agus Mohamad Soleh; Cici Suhaeni
Journal of Mathematics, Computations and Statistics Vol. 8 No. 2 (2025): Volume 08 Nomor 02 (Oktober 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i2.7817

Abstract

Coconut milk has emerged as a strategic food commodity in the global tropical region, with market demand growing at 7.2% per annum since 2021. This increasing demand has led to sophisticated adulteration practices, including dilution with water. Such adulteration not only reduces the nutritional value but also poses serious health risks, including food poisoning and allergic reactions. This study developed an innovative detection method combining Fourier Transform Infrared (FTIR) spectroscopy with a sophisticated machine learning algorithm. We analyzed 719 coconut milk samples (wavelength range 2500-4000 nm) consisting of traditional market products and instant commercial products. This study aims to develop an FTIR-based coconut milk adulteration detection model by optimizing RF and XGBoost parameters using CSA and evaluating the comparative performance of the two models in identifying different types of adulterants. The spectral data underwent rigorous preprocessing using a combination of Standard Normal Variate (SNV) and Savitzky-Golay (SG) techniques to overcome the effects of noise and light scattering, which significantly improved feature extraction. The results show that CSA-optimized XGBoost achieves superior performance with 92% accuracy and 91% F1 score, outperforming Random Forest in all evaluation metrics. The model shows particular strength in precision (98%), indicating its outstanding ability to minimize false positives in adulteration detection. Stability tests through 30 experimental repetitions reveal that the combination of XGBoost+CSA maintains consistent performance with minimal variance, confirming its reliability for industrial applications. Comparative analysis shows that the combination of SNV+SG preprocessing improves the accuracy of the baseline model by 9-12%, while CSA optimization provides an additional performance improvement of 10-15%. This research makes significant contributions to food science and safety. This study demonstrates the effectiveness of CSA in optimizing spectroscopic models, achieving 19.5% higher precision. The combination of SNV+SG preprocessing improves the baseline accuracy by 9-12%, while CSA optimization provides an additional performance improvement of 10-15%. This study not only provides a rapid and non-destructive adulteration detection solution but also proves the effectiveness of the CSA approach in optimizing the spectroscopic model. These findings have important implications for strengthening food safety regulations and developing real-time quality control systems in the coconut milk industry.
Effect of Feature Normalization and Distance Metrics on K-Nearest Neighbors Performance for Diabetes Disease Classification Muhammad Yusran; Kusman Sadik; Agus M Soleh; Cici Suhaeni
Journal of Mathematics, Computations and Statistics Vol. 8 No. 2 (2025): Volume 08 Nomor 02 (Oktober 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i2.8012

Abstract

Diabetes is a global health issue with a steadily increasing prevalence each year. Early detection of the disease is an important step in preventing severe complications. The K-Nearest Neighbors (KNN) algorithm is often used in disease classification, but its performance is highly influenced by the choice of normalization method and distance metric used. This study aims to evaluate the effect of various normalization methods and distance metrics on the performance of the KNN algorithm in diabetes disease classification. The three normalization methods were employed: z-score normalization, min-max scaling, and median absolute deviation (MAD). In addition, the seven distance metrics were assessed: Euclidean, Manhattan, Chebyshev, Canberra, Hassanat, Lorentzian, and Clark. The dataset used is Pima Indians Diabetes which consists of 768 observations and 8 features. The data were split into 80% training data and 20% test data, and using 5-fold cross-validation to determine the optimal k value. The results show that the MAD-Canberra combination produces the highest overall accuracy, recall, and F1-score of 87.32%, 82.33%, and 81.94%, respectively. The highest precision was obtained from the Baseline-Hassanat combination at 86.96%, while the lowest performance was observed for the Z-Score-Chebyshev combination with F1-Score 58.02%. These results highlight that no single combination universally outperforms others, underscoring the need for empirical evaluation. Nonetheless, combining MAD normalization with metrics such as Canberra or Hassanat can serve as a strong starting point for developing KNN-based classification systems, especially in medical contexts that are sensitive to misclassification.
Co-Authors Agus M Soleh Agus Mohamad Soleh Anang Kurnia Bagus Sartono Budi Susetyo Carlya Agmis Aimandiga Desy Endriani Dwi Erzalianti Gerry Alfa Dito Hari Wijayanto I Gusti Ngurah Sentana Putra Joice Junansi Tandirerung Kusman Sadik Laily Nissa Atul Mualifah Muh. Sunan Muhammad Syafiq Muhammad Yusran Nur'aini Sentana Putra I Gusti Ngurah SITI NURADILLA Unique Desyrre A. Resiloy Wawan Saputra