Classifying and Tracking International Aid Contribution Towards SDGs

2025-05-21

AI Summary

International aid data suffer from labor-intensive annotation, incomplete documentation, and high heterogeneity, impeding systematic classification and tracking of contributions to the Sustainable Development Goals (SDGs). Method: This paper proposes an AI framework integrating SDG-domain semantics with large language model (LLM) priors. It innovatively combines SDG ontology embedding, LLM fine-tuning, multi-task learning, and time-series analysis to enable fine-grained, interpretable, multi-label classification of aid projects. Contribution/Results: Evaluated on a multi-year real-world aid dataset, the framework achieves significant gains in classification accuracy. It is the first to systematically identify cross-SDG aid synergies and structural gaps—validated by government partners—and supports policy simulation and evidence-based decision optimization.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Application Domains: Humanities & Computational Social Science

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

International aid is a critical mechanism for promoting economic growth and well-being in developing nations, supporting progress toward the Sustainable Development Goals (SDGs). However, tracking aid contributions remains challenging due to labor-intensive data management, incomplete records, and the heterogeneous nature of aid data. Recognizing the urgency of this challenge, we partnered with government agencies to develop an AI model that complements manual classification and mitigates human bias in subjective interpretation. By integrating SDG-specific semantics and leveraging prior knowledge from language models, our approach enhances classification accuracy and accommodates the diversity of aid projects. When applied to a comprehensive dataset spanning multiple years, our model can reveal hidden trends in the temporal evolution of international development cooperation. Expert interviews further suggest how these insights can empower policymakers with data-driven decision-making tools, ultimately improving aid effectiveness and supporting progress toward SDGs.

Problem

• Tracking international aid contributions to SDGs is challenging due to data issues
• AI model improves aid classification accuracy and reduces human bias
• Revealing hidden trends in international development cooperation aids policymaking

Innovation

• AI model for aid classification and bias reduction
• SDG-specific semantics and language model integration
• Comprehensive dataset analysis for hidden trend discovery