Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Innovation in Research of Informatics (INNOVATICS) Jurnal Pendidikan Sang Surya
Pawestri, Sheraton
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 3 Documents
Search

 1 
Sarcasm Detection: A Comparative Analysis of RoBERTa-CNN vs RoBERTa-RNN Architectures Pawestri, Sheraton; Murinto, Murinto; Auzan, Muhammad
INNOVATICS: Innovation in Research of Informatics Vol 6, No 2 (2024): September 2024
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v6i2.11921

Abstract

Increasingly advanced technology and the creation of social media and the internet can become a forum for people to express things or opinions. However, comments or views from users sometimes contain sarcasm making it more difficult to understand. News headlines, sometimes contain sarcasm which makes readers confused about the content of the news. Therefore, in this research, a model was created for sarcasm detection. Many methods are used for sarcasm detection, but performance still needs to be improved. So this research aims to compare the performance of two text classification methods, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), in detecting sarcasm in English news headlines using RoBERTa text transformation.  RoBERTa produces a fixed-size vector of numbers 1x768. The research results show that CNN has better performance than RNN. CNN achieved the highest average accuracy of 0.891, precision of 0.878, recall of 0.874, and f1-score of 0.876, with a loss of 0.260 and a processing time of 508.1 milliseconds per epoch. On the contrary, RNN shows an accuracy of 0.711, precision of 0.692, recall of 0.620, f1-score 0.654, and loss of 0.564, with a longer processing time of 116500 milliseconds per epoch. The 10-fold cross-validation evaluation method ensures the model performs well and avoids overfitting. So it is recommended to use the combination of RoBERTa and CNN in other text classification applications that require high speed and accuracy. Further research is recommended to explore deeper CNN architectures or other architectural variations such as Transformer-based models for performance improvements.
Analisis Perbandingan Metode Similarity untuk Kemiripan Dokumen Bahasa Indonesia pada Deteksi Kemiripan Teks Bahasa Indonesia Pawestri, Sheraton; Suyanto, Yohanes
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7648

Abstract

Ease of accessing information brings diverse benefits, including the ability to develop models that can detect similarities between documents, a plagiarism-checking system, automatic summarization, classification, etc. The various benefits of word similarity detection make research on similarity detection between documents an important area to develop. However, studies regarding similarity detection specifically for Indonesian language documents are still relatively small and the performance can still be developed. Therefore, this research aims to conduct a comparative analysis of the performance of Doc2Vec compared to the Jaccard Coefficient, Cosine Similarity, and Euclidean Distance in detecting the similarity of documents with Indonesian text. Three datasets are used in this analysis, with the first dataset consisting of 200 news from Google News, the second dataset from IndoNLU, and the third dataset from TaPaCo. The findings from this study show that overall Cosine Similarity has better performance than Jaccard Coefficient and Euclidean Distance for average performance. The superior performance was with accuracy of 0.98, precision of 0.84, recall of 0.95, and F-1 score of 0.89, with the model formed in 10.56 seconds using the Cosine Similarity algorithm on the Google News dataset. This is because doc2vec is better suited to datasets with higher dimensions than datasets that only contain a few words.
EKSPLORASI PENGGUNAAN ARTIFICIAL INTELLIGENCE DALAM PEMBELAJARAN OLEH MAHASISWA PPKN UAD Marzuqi, Yasir; Pawestri, Sheraton; Triwahyuningsih
Jurnal Pendidikan Sang Surya Vol. 11 No. 1 (2025): Jurnal Pendidikan Sang Surya
Publisher : LPPM Universitas Muhammadiyah Bulukumba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56959/jpss.v11i1.432

Abstract

Perkembangan teknologi Artificial Intelligence (AI) telah mengubah paradigma pembelajaran di perguruan tinggi. Bagi mahasiswa Pendidikan Pancasila dan Kewarganegaraan (PPKn), pemanfaatan AI tidak hanya meningkatkan efisiensi belajar, tetapi juga berdampak pada pembentukan etika akademik dan kemampuan berpikir kritis sebagai calon pendidik. Penelitian ini menggunakan pendekatan kualitatif dengan metode studi kasus yang difokuskan pada mahasiswa PPKn Universitas Ahmad Dahlan. Data diperoleh melalui kuesioner tertutup, wawancara mendalam, observasi, dan dokumentasi, kemudian dianalisis dengan model Miles dan Huberman melalui tahapan reduksi, penyajian, dan penarikan kesimpulan. Triangulasi teknik dan sumber digunakan untuk memastikan validitas. Hasil menunjukkan bahwa mahasiswa secara aktif memanfaatkan AI untuk mencari informasi, menyelesaikan tugas, dan merangkum materi. Sebagian besar responden merasakan peningkatan pemahaman dan produktivitas belajar. Namun, temuan juga mengungkap adanya tantangan, seperti potensi plagiarisme, ketergantungan, dan melemahnya interaksi sosial serta daya berpikir kritis. Penelitian ini menegaskan bahwa AI memiliki potensi sebagai alat pembelajaran inovatif, asalkan digunakan secara bijak. Integrasi literasi digital dan etika teknologi dalam kurikulum menjadi penting agar mahasiswa dapat memanfaatkan AI secara efektif dan bertanggung jawab.
Co-Authors Auzan, Muhammad Marzuqi, Yasir Murinto Murinto Triwahyuningsih Yohanes Suyanto