用多模态数据检测学术不端，准确率达74.33%
BMDetect: A Multimodal Deep Learning Framework for Comprehensive Biomedical Misconduct Detection
- 融合期刊信息、文本嵌入与模型挖掘的异常特征进行综合判断
- 识别出期刊影响力与统计异常是主要预测指标，准确率超基线8.6%
- 适用于医学各领域，适合科研诚信审查人员使用
生物医学研究中的学术不端检测仍面临算法局限和分析流程碎片化问题。我们提出BMDetect，一个融合期刊元数据（如SJR）、语义嵌入（PubMedBERT）及GPT-4o挖掘的文本属性（方法统计数据、数据异常）的多模态深度学习框架。核心创新包括：(1) 领域特异性特征的多模态融合，降低检测偏差；(2) 量化特征重要性，发现期刊权威指标（如SJR指数）和文本异常（如统计异常）为主要预测因子；(3) 构建了BioMCD数据集，包含13,160篇撤稿文章与53,411个对照样本。BMDetect取得74.33% AUC，优于单一模态基线8.6%，并在不同生物医学子领域展现良好可迁移性。该工作推动了可扩展、可解释的研究诚信保障工具发展。
原文摘要 · Abstract (English)
Academic misconduct detection in biomedical research remains challenging due to algorithmic narrowness in existing methods and fragmented analytical pipelines. We present BMDetect, a multimodal deep learning framework that integrates journal metadata (SJR, institutional data), semantic embeddings (PubMedBERT), and GPT-4o-mined textual attributes (methodological statistics, data anomalies) for holistic manuscript evaluation. Key innovations include: (1) multimodal fusion of domain-specific features to reduce detection bias; (2) quantitative evaluation of feature importance, identifying journal authority metrics (e.g., SJR-index) and textual anomalies (e.g., statistical outliers) as dominant predictors; and (3) the BioMCD dataset, a large-scale benchmark with 13,160 retracted articles and 53,411 controls. BMDetect achieves 74.33% AUC, outperforming single-modality baselines by 8.6%, and demonstrates transferability across biomedical subfields. This work advances scalable, interpretable tools for safeguarding research integrity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。