Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Unnes Science Education Journal UPEJ Unnes Physics Education Journal Scientific Journal of Informatics
Aryani, Nila Prasetya
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Physics

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
UPAYA PENINGKATAN KUALITAS PEMBELAJARAN FISIKA MELALUI PELATIHAN DIGITAL IMAGE CREATOR FOR OPTICAL MICROSCOPE (DIGICOM) PADA GURU FISIKA BATANG Subali, Bambang; Alvian, Alvian; Ellianawati, Ellianawati; Yulianti, Ian; Aryani, Nila Prasetya; Susilo, Susilo
UPEJ Unnes Physics Education Journal Vol 9 No 1 (2020)
Publisher : UPEJ Unnes Physics Education Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (444.432 KB) | DOI: 10.15294/upej.v9i1.38281

Abstract

Teaching physics by utilizing technology becomes a necessity for high school physics teachers to master. DIGICOM is an innovation in teaching physics that utilizes multi-technology. Interface-connected camera technology can help explain microscopic phenomena observed through a microscope. A total of 19 physics teachers in Batang Regency, Central Java received training on DIGICOM-based science learning. From the preliminary data it is known that almost all teachers have never carried out learning using multi-technology and only 50% of teachers or schools have digital microscopes and digital cameras in their schools. But after getting DIGICOM training in physics learning, teachers already have sufficient knowledge and they have the confidence to be able to implement the results of this training in learning physics in their classrooms.
DEVELOPMENT OF MULTIMEDIA WEB-BASED PHYSICS LEARNING TOOLS TO STRENGTHEN STUDENTS’ CHARACTERS Akhlis, Isa; Aryani, Nila Prasetya
Unnes Science Education Journal Vol 7 No 2 (2018): July 2018
Publisher : Department of Integrated Science, Faculty of Mathematics and Natural Sciences, Universitas Negeri Semarang in Collaboration with Perkumpulan Pendidikan IPA Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/usej.v7i2.26707

Abstract

This research intended to obtain an initial description of students and environment on peace-loving, environmental caring, learning methods, learning materials, and learning media applied in Physics lesson at a high school; moreover, to examine the validity of high school physic learning materials and multimedia web-based physics learning tools in strengthening the students’ characters. The data collection methods employed were (1) documentation, to get the prior data of high school physic materials; (2) observation, to collect the data of students’ initial characters; (3) questionnaire, to obtain the data of learning method, teaching materials, and learning media adopted in the learning process; and (4) validation, to test the developed learning tools’ validity. The results showed that generally, the students have possessed the character of peace-loving, while they rarely owned the environmental caring. In addition, the developed learning tools achieved a good assessment and were declared valid.
Improving Sentiment Analysis with a Context-Aware RoBERTa–BiLSTM and Word2Vec Branch Hardyanto, Wahyu; Aryani, Nila Prasetya; Andestian, Defin; Sugiyanto; Setyaningrum, Wahyu; Mardiansyah, M Fadil; Islam, Muhamad Anbiya Nur; Purwinarko, Aji
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 sentiment analysis with a hybrid model combining Word to Vector (Word2Vec) and the Robustly Optimized BERT Pretraining Approach (RoBERTa). 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/Study design/approach: 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. The process supports caching and training resumes. Result/Findings: 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/Originality/Value: The novelty lies in the fusion of distributional and contextual representations with resource-efficient fine-tuning. 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.
Co-Authors Aji Purwinarko, Aji Alvian, Alvian Andestian, Defin Bambang Subali Ellianawati, Ellianawati Ian Yulianti, Ian Isa Akhlis Islam, Muhamad Anbiya Nur Mardiansyah, M Fadil SUGIYANTO Susilo Susilo Wahyu Hardyanto Wahyu Setyaningrum