Nature-Inspired Optimization Techniques for Extractive Multi-Document Summarization: A State-of-the-Art Survey

The rapid growth of digital textual content has made Automatic Text Summarization (ATS) an essential research area within Natural Language Processing (NLP). Among existing approaches, extractive summarization remains widely used due to its computational efficiency and practical applicability. However, conventional heuristic and statistical methods often face challenges related to redundancy, coherence, and contextual relevance. This review presents a comprehensive survey of metaheuristic-based extractive multi-document summarization techniques, with particular emphasis on optimization algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Teaching–Learning-Based Optimization (TLBO), Firefly Algorithm, and Biogeography-Based Optimization (BBO). The paper systematically reviews summarization classifications, traditional statistical and graph-based methods, machine learning approaches, and recent optimization-driven techniques. Benchmark datasets including DUC 2005 and DUC 2006 are discussed, along with evaluation metrics such as ROUGE and BLEU. The reviewed studies demonstrate that metaheuristic-based approaches effectively enhance summary quality by improving relevance, coherence, and scalability across multilingual and domain-specific scenarios. This survey highlights the potential of metaheuristic optimization as a robust and promising direction for future research in large-scale and real-time text summarization systems.