Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Pakem : Jurnal Pengabdian Kepada Masyarakat Computer Architecture and Signal Processing
Almira Agwinanda
Universitas Negeri Semarang
Agriculture, Biological Sciences & Forestry Arts Humanities Chemistry Economics, Econometrics & Finance Education Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Public Health Social Sciences Other

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

Found 2 Documents
Search

 1 
Comparative Analysis of Hyperparameter Optimization Methods for ChineseBERT-Based Weibo Sentiment Classification Kartika Fanya; Almira Agwinanda
Computer Architecture and Signal Processing Vol. 1 No. 2 (2026): June: Computer Architecture and Signal Processing
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/casp.v1i2.531

Abstract

Sentiment analysis has become an important research area in natural language processing (NLP), particularly for analyzing user opinions on social media platforms such as Sina Weibo. Transformer-based models have significantly improved sentiment classification performance, including ChineseBERT, which integrates glyph and pinyin information for Chinese language understanding. However, the performance of transformer models is highly influenced by hyperparameter configurations. Therefore, this study aims to compare the effectiveness of two hyperparameter optimization methods, namely Genetic Algorithm and Optuna, on ChineseBERT for Weibo sentiment classification using the WeiboSenti100k dataset. The experiments were conducted by fine-tuning the ChineseBERT model using baseline hyperparameters and optimized hyperparameters generated by both optimization methods. The optimized parameters include learning rate, dropout rate, batch size, and number of epochs. Model performance was evaluated using accuracy, precision, recall, and F1-score, with a primary focus on classification accuracy. The experimental results show that the baseline ChineseBERT model achieved an accuracy of 97.6%. Meanwhile, ChineseBERT optimized using Genetic Algorithm achieved an accuracy of 97.2%, while ChineseBERT optimized using Optuna achieved the highest accuracy of 98.2%. These results indicate that Optuna provides more effective hyperparameter optimization performance compared to Genetic Algorithm for ChineseBERT-based Weibo sentiment classification. Overall, this study demonstrates that appropriate hyperparameter optimization can improve the performance of transformer-based models for Chinese sentiment analysis tasks.
OPTIMALISASI PERSONAL BRANDING DAN KOMUNIKASI BAHASA ASING BERBANTUAN LIDERA-AI DI BLK MAGELANG Ayudhia Ratna Wijaya; Almira Agwinanda; Khairiyah Eka Januaristi; Nailur Rahmawati
PAKEM: Jurnal Pengabdian Kepada Masyarakat Vol 6 No 3 (2026): Pakem : Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Pattimura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/pakem.6.3.374-384

Abstract

The service and tourism industries demand prospective workers who not only master technical skills but are also able to demonstrate their competence professionally. Job training participants often possess adequate operational skills, but are not yet optimal in compiling CVs, building professional profiles, and using foreign languages as added value in the recruitment process. This community service activity aims to optimize the personal branding and foreign language communication of BLK Magelang City participants through the application of LIDERA-AI. The activity method uses participatory training and practical mentoring implemented in four stages: strengthening professional personal branding, using LIDERA-AI to develop achievement narratives, practicing achievement-based CVs and cover letters, and practicing basic foreign language communication in a work context. Evaluation was carried out through pre- and post-tests, practical observations, and participant outcome assessments. The evaluation results of 31 participants showed an increase in the average score from 94.77 in the pre-test to 97.48 in the post-test. Participants also produced concrete outcomes in the form of achievement-based CVs, professional profile summaries, and draft self-introductions for interview purposes. This activity demonstrates that the integration of personal branding, application documents, LIDERA-AI, and foreign language communication can be a practical strategy to strengthen the work readiness of training participants in the service and tourism sectors.
Co-Authors Ayudhia Ratna Wijaya Kartika Fanya Khairiyah Eka Januaristi Rahmawati, Nailur