E-government complaint routing systems face extreme class imbalance under which standard transformer fine-tuning leaves most minority agencies without correct routings. This study compares two cost...
<p><strong>Tác giả:</strong> Dewi Agustini Santoso, Heni Indrayani, Karis Widyatmoko, Farrikh Alzami, Iswahyudi Iswahyudi</p>
<p>E-government complaint routing systems face extreme class imbalance under which standard transformer fine-tuning leaves most minority agencies without correct routings. This study compares two cost-sensitive loss modification methods, inverse-frequency class weighting and focal loss, for long-tail intent classification in Indonesian government complaint routing. The dataset comprises 56,068 Indonesian-Javanese-English code-mixed complaints across 86 government agencies with an imbalance ratio...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.19139/soic-2310-5070-4091" target="_blank" rel="noopener">https://doi.org/10.19139/soic-2310-5070-4091</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.19139/soic-2310-5070-4091" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex