Open access Journal SINTA 3
EVALUATING ROBERTA AND GPT-BASED MODELS FOR SDG MULTICLASS TEXT CLASSIFICATION ACROSS DIFFERENT DOCUMENT LENGTHS
BAREKENG: Jurnal Ilmu Matematika dan Terapan · Vol. 20 No. 3 (2026) · pp. 2645–2664
- ISSN
- 2615-3017, 1978-7227
- Published
- 2026-04-08
- Publisher
- PATTIMURA UNIVERSITY
- Language
- eng
Abstract
Multiclass text classification remains a difficult task, primarily due to semantic ambiguity and differences in input length. This study evaluates RoBERTa and GPT-based models for multiclass text classification, focusing on how prompting strategies and document length affect accuracy and robustness. Experiments were conducted using the OSDG Community Dataset, which contains approximately 15,000 labeled samples. The dataset was partitioned into four subsets based on input length: short, medium, long, and all combined. Three GPT variants (zero-shot, few-shot, and fine-tuned) were compared against a RoBERTa baseline. Fine-tuning was implemented via OpenAI’s supervised API with prompt-response formatting. Performance was assessed through F1-score, precision, recall, and balanced accuracy. Fine-tuned GPT achieved the strongest results in all settings, with a macro F1-score of 0.9204 on the all-combined dataset, representing a 4.61% improvement over RoBERTa. Consistent gains were also observed across short (8.63%), medium (3.83%), and long (20.31%) texts. The largest improvement occurred on long documents, while medium-length inputs provided the most stable performance across models. These findings highlight the effectiveness of task-specific fine-tuning in enhancing GPT’s capability to classify SDG-related texts across diverse input lengths.
Collaboration network of the authors
40 authors · 118 co-authorship links · 15 across different organisations · showing the 40 most connected
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- IPB University
- University of Brawijaya
- Universitas Amikom Purwokerto
- Universitas Muhammadiyah Jakarta
- Universiti Putra Malaysia
- University of Bengkulu
- Politeknik Statistika STIS
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Bagus Sartono | IPB University | 7 |
| I Made Sumertajaya | IPB University | 4 |
| Asep Saefuddin | IPB University | 4 |
| ERFIANI ERFIANI | IPB University | 4 |
| Hari Wijayanto | IPB University | 3 |
| Anik Djuraidah | IPB University | 3 |
| Kusman Sadik | IPB University | 3 |
| Gerry Alfa Dito | IPB University | 2 |
| INDAHWATI INDAHWATI | IPB University | 2 |
| Anang Kurnia | IPB University | 2 |
| Khairil Anwar Notodiputro | IPB University | 2 |
| Alfa Nugraha Pradana | IPB University | 2 |
| Ade Nurhopipah | Universitas Amikom Purwokerto | 1 |
| Muh. Sunan | IPB University | 1 |
| Unique Desyrre A. Resiloy | IPB University | 1 |
| Desy Endriani | IPB University | 1 |
| Imam Cholissodin | University of Brawijaya | 1 |
| Lintang Resita Mayangsari | University of Brawijaya | 1 |
| Andhica Pratama | University of Brawijaya | 1 |
| Leni Anggraini Susanti | IPB University | 1 |
| Pradnya Sri Rahayu | IPB University | 1 |
| Nabila Ghoni Trisno Hidayatulloh | IPB University | 1 |
| Sachnaz Desta Oktarina | IPB University | 1 |
| Ismah Ismah | Universitas Muhammadiyah Jakarta | 1 |
| Sim Hui Xin | Universiti Putra Malaysia | 1 |
| Andi Harismahyanti A. | IPB University | 1 |
| Farit Mochamad Afendi | IPB University | 1 |
| Kusnaeni Kusnaeni | IPB University | 1 |
| Anggita Rizky Fadilah | IPB University | 1 |
| Maulida Fajrining Tyas | IPB University | 1 |
| Husnun Nashir | IPB University | 1 |
| Ni Gusti Ayu Putu Puteri Suantari | IPB University | 1 |
| Kristuisno Martsuyanto Kapiluka | IPB University | 1 |
| Indra Rivaldi Siregar | IPB University | 1 |
| Herlin Fransiska | University of Bengkulu | 1 |
| Ita Wulandari | Politeknik Statistika STIS | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.