Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Scientific Journal of Informatics Journal of Intelligent Computing, Systems, and Applications (JICSA)
Nila Prasetya Aryani
Universitas Negeri Semarang
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Improving Sentiment Analysis with a Context-Aware RoBERTa–BiLSTM and Word2Vec Branch Wahyu Hardyanto; Nila Prasetya Aryani; Defin Andestian; Sugiyanto; Wahyu Setyaningrum; M Fadil Mardiansyah; Muhamad Anbiya Nur Islam; Aji Purwinarko
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.35918

Abstract

Purpose: We improve the accuracy of Twitter/X sentiment analysis with a hybrid model combining Word2Vec and the Robustly Optimized BERT Pretraining Approach (RoBERTa). However, Twitter/X text is noisy (slang/OOV) and ambiguous, so the performance of the pre-trained transformer decreases. Word2Vec is also limited to local contexts. Integrative studies of both are still limited. The idea is that Word2Vec is strong for slang/novel vocabulary (distributional semantics), while RoBERTa excels in contextual meaning; combining the two mitigates each other's weaknesses. Methods: The Sentiment140 dataset contains 1.6 million balanced tweets. The split is stratified; Word2Vec is trained solely on the training data. RoBERTa is pretrained (frozen in the first stage, then fine-tuned with some layers in the second stage). The Word2Vec and RoBERTa vectors are concatenated and processed using Bidirectional Long Short-Term Memory (BiLSTM) with sigmoid activation. Training utilizes TensorFlow and the Adam optimizer, incorporating dropout and early stopping. The decision threshold is optimized during the validation process. Result: The hybrid model achieved an accuracy of 88.09%, an F1-score of 88.09%, and an Area Under the Curve (AUC) ≈ 95.19% on the Receiver Operating Characteristic (ROC). No overfitting was observed, and the hybrid model outperformed both single baselines. The confusion matrix and ROC curve corroborate the findings. Novelty: The novelty lies in the fusion of distributional and contextual representations with a structured fusion mechanism. Limitations: Computational requirements and hyperparameter tuning are not yet extensive. Further directions: Systematic hyperparameter search and cross-validation across other large sentiment datasets to assess generalization.
A CTMC-Based Parameter Estimation and Optimal Control Framework for Covid-19 Transmission Andhika Dwi Anggara; Nila Prasetya Aryani
Journal of Intelligent Computing, Systems, and Applications (JICSA) Vol. 1 No. 02 (2026): March 2026
Publisher : Penerbit Institut Teknologi Del

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54074/jicsa.v1i02.29

Abstract

Covid-19 is a disease that infects the respiratory tract caused a corona virus. This disease has infected human populations around the world which causing a pandemic. The Covid-19 pandemic has become the focus of research on lately. This study aims to construct the latest mathematical model related to the transmission of Covid-19 in the human population. The model that is formed is constructed by considering several epidemiological parameters that are very identical to the actual conditions. In the formation of the model there are many unknown parameters. Therefore, the maximum likelihood method is used to estimate the parameters of the model that is formed. At the start the Covid-19 epidemic model was constructed without control with given assumptions and based on the facts obtained. Then from the model would formed equilibrium point, and basic reproduction number. The next discussion is to designed an optimal control using the Pontryagin Minimum Principle which is applied to reduce the number of people Covid-19 infected by using the backward-forward sweep algorithm. The results of the numerical simulation will later produce an optimal control strategy that is suitable to prevent Covid-19 to be more effective.
Co-Authors Aji Purwinarko, Aji Andhika Dwi Anggara Defin Andestian M Fadil Mardiansyah Muhamad Anbiya Nur Islam Sugiyanto Wahyu Hardyanto Wahyu Setyaningrum