EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Trade-off Evaluation: BERT, RoBERTa, and DistilBERT for IMDb Sentiment Analysis on a Tesla T4 Google Colab Free Runtime

Asih Setiyorini, Ema Utami

Jurnal Informatika dan Teknologi Pendidikan · 08.10.2026 · 6 (2) · 77-86

DOI: 10.59395/jitp.v6i2.225 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal Informatika dan Teknologi Pendidikan, online erschienen am 08.10.2026. Verfasst von Asih Setiyorini und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study addressed resource-constrained sentiment classification by balancing predictive quality with computational cost and stochastic variability. This study applied a five-stage structured evaluation protocol to compare BERT, RoBERTa, and DistilBERT on the 50,000-review IMDb dataset. The original experiment covered 27 configurations formed by three models, three random seeds, and three maximum sequence lengths. Architecture-level robustness was summarized using mean ± standard deviation across seeds, while one validation-selected configuration per architecture was retained only for confirmatory profiling on a uniform Tesla T4 Google Colab Free runtime. Performance was evaluated using accuracy, macro-F1, AUC-ROC, and MCC, and efficiency was assessed through checkpoint size, inference latency, and peak VRAM. Paired McNemar tests, bootstrap confidence intervals, classical TF-IDF baselines, Pareto analysis, and manual error inspection complemented the comparison. At sequence length 512, mean test macro-F1 was 0.95403 ± 0.00139 for RoBERTa, 0.94016 ± 0.00042 for BERT, and 0.93569 ± 0.00086 for DistilBERT. In the representative confirmatory runs, RoBERTa achieved the highest macro-F1 (0.9516), whereas DistilBERT provided the smallest checkpoint (256.10 MB), lowest BS16 latency (14.86 ms/sample), and lowest training VRAM (2399.80 MB). The results supported scenario-based model selection rather than a single universally optimal model.

Zitieren

APA

Setiyorini, A., & Utami, E. (2026). Trade-off Evaluation: BERT, RoBERTa, and DistilBERT for IMDb Sentiment Analysis on a Tesla T4 Google Colab Free Runtime. Jurnal Informatika dan Teknologi Pendidikan, 6(2), 77-86. https://doi.org/10.59395/jitp.v6i2.225

Vancouver

Setiyorini A, Utami E. Trade-off Evaluation: BERT, RoBERTa, and DistilBERT for IMDb Sentiment Analysis on a Tesla T4 Google Colab Free Runtime. Jurnal Informatika dan Teknologi Pendidikan. 2026;6(2):77-86. doi:10.59395/jitp.v6i2.225

BibTeX
@article{Setiyorini2026,
  author = {Setiyorini, Asih and Utami, Ema},
  title = {Trade-off Evaluation: BERT, RoBERTa, and DistilBERT for IMDb Sentiment Analysis on a Tesla T4 Google Colab Free Runtime},
  journal = {Jurnal Informatika dan Teknologi Pendidikan},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {77--86},
  doi = {10.59395/jitp.v6i2.225}
}
Kostenlos starten →