With the growing importance of sustainable development goals (SDGs), various labeling systems have emerged for effective monitoring and evaluation. This study assesses six labeling systems across 1.85 million documents at both paper level and topic level. Our findings indicate that the SDGO and SDSN systems are more aggressive, while systems such as Auckland, Aurora, SIRIS, and Elsevier exhibit significant topic consistency, with similarity scores exceeding 0.75 for most SDGs. However, similarities at the paper level generally fall short, particularly for specific SDGs like SDG 10. We highlight the crucial role of contextual information in keyword-based labeling systems, noting that overlooking context can introduce bias in the retrieval of papers (e.g., variations in "migration" between biomedical and geographical contexts). These results reveal substantial discrepancies among SDG labeling systems, emphasizing the need for improved methodologies to enhance the accuracy and relevance of SDG evaluations.

翻译：随着可持续发展目标（SDGs）的重要性日益凸显，多种标注系统应运而生以支持有效的监测与评估。本研究在论文层面和主题层面对六种标注系统进行了评估，涵盖185万篇文献。研究发现，SDGO和SDSN系统标注更为积极，而奥克兰、奥罗拉、SIRIS和爱思唯尔等系统则表现出显著的主题一致性，在多数可持续发展目标上的相似度得分超过0.75。然而，论文层面的相似度普遍不足，特别是在SDG 10等具体目标上。我们强调了上下文信息在基于关键词的标注系统中的关键作用，指出忽略语境可能导致文献检索偏差（例如生物医学与地理学语境中“迁移”一词的语义差异）。这些结果揭示了不同可持续发展目标标注系统间存在显著差异，凸显了改进方法论以提升可持续发展目标评估准确性与相关性的迫切需求。