Automated PESTEL-Based News Stream Analysis for SME Sustainability Assessment

Small and medium-sized enterprises (SMEs) operate in a dynamic external environment where economic, political, regulatory, technological, social, and environmental changes can influence decision-making regarding sustainable development. This study presents an artificial intelligence-based approach to transform continuously collected external information into structured PESTEL signals and to assess their strategic direction and potential impact on SMEs in Kazakhstan. The developed methodology combines automated news gathering, PESTEL classification, event characterization (opportunities, threats, or neutral factors), alignment with Sustainable Development Goals (SDGs), and quantitative impact assessment. The empirical analysis is based on 309 publications from 32 national and international sources, covering industry assessments in the manufacturing, trade, and service sectors. The results showed that economic factors constitute the largest category of external signals, while the strategic direction of the identified events varies significantly across PESTEL model dimensions. Opportunities predominated in the analyzed information landscape, whereas the legal aspect exhibited the greatest relative balance between threats and opportunities. Sectoral analysis revealed differences in the projected impact of similar external signals on companies across the three profiles examined. Expert validation confirmed a classification accuracy of 92% for PESTEL categories and threat/opportunity distinctions, and sensitivity analysis demonstrated that the impact index remained relatively stable despite variations in weighted factors. The proposed approach provides a structural framework for integrating external environmental monitoring into sustainability-oriented analysis and can facilitate the interpretation of strategically important external signals for SMEs.