Exploration of Scientific Documents through Unsupervised Learning-Based Segmentation Techniques

• Cherradi , Mohamed ^[1] ; El Haddadi, Anass ^[1]
  1. [1] Data Science and Competetive Intelligence Team (DSCI), ENSAH. Abdelmalek Essaâdi University (UAE). Tetouan, Morocco
• Localización: Seminars in Medical Writing and Education, ISSN-e 3008-8127, Vol. 3, Nº. 0, 2024 (Ejemplar dedicado a: Seminars in Medical Writing and Education)
• Idioma: inglés
• Enlaces
  • Texto completo
• Dialnet Métricas: 3 Citas
• Resumen

  • Navigating the extensive landscape of scientific literature presents a significant challenge, prompting the development of innovative methodologies for efficient exploration. Our study introduces a pioneering approach for unsupervised segmentation, aimed at revealing thematic trends within articles and enhancing the accessibility of scientific knowledge. Leveraging three prominent clustering algorithms—K-Means, Hierarchical Agglomerative, and DBSCAN—we demonstrate their proficiency in generating meaningful clusters, validated through assessment metrics including Silhouette Score, Calinski-Harabasz Index, and Davies-Bouldin Index. Methodologically, comprehensive web scraping of scientific databases, coupled with thorough data cleaning and preprocessing, forms the foundation of our approach. The efficacy of our methodology in accurately identifying scientific domains and uncovering interdisciplinary connections underscores its potential to revolutionize the exploration of scientific publications. Future endeavors will further explore alternative unsupervised algorithms and extend the methodology to diverse data sources, fostering continuous innovation in scientific knowledge organization