数据与计算发展前沿2026，Vol.8Issue(1)：158-167,10.DOI:10.11871/jfdc.issn.2096-742X.2026.01.013
基于PolyLoss函数的不平衡犯罪隐语文本增强方法
An Implicit Transcript Enhancement Method for Unbalanced Crimes Based on PolyLoss Function
摘要
Abstract
[Objective]This study aims to address the imbalance issue in the criminal cant dataset and fur-ther improve the classification performance of criminal cant texts.[Method]For long texts,we present SimPoly,while for short texts,EDAPoly is proposed.[Result]Experimental results demonstrate that SimPoly and EDAPoly significantly improve classification model perfor-mance on imbalanced criminal cant datasets,achieving notable gains in accuracy,recall,and F1-score compared to baseline methods without text augmentation.[Conclusion]The proposed method not only provides an effective solution for the practical application of criminal cant rec-ognition technology,but also offers new ideas and support for similar imbalanced text classifi-cation tasks.关键词
犯罪隐语/文本增强/损失函数/不平衡文本处理Key words
criminal cant/text augmentation/loss function/unbalanced text processing引用本文复制引用
李文邦,颜靖华,董泽..基于PolyLoss函数的不平衡犯罪隐语文本增强方法[J].数据与计算发展前沿,2026,8(1):158-167,10.基金项目
高校基本科研业务费项目"基于仿真的指挥效能评估"(2022JKF02038) （2022JKF02038）
