SkillNER: Mining and mapping soft skills from any text

In today's digital world, there is an increasing focus on soft skills. On the one hand, they facilitate innovation at companies, but other, are unlikely to be automated soon. Researchers struggle with accurately approaching quantitatively study of skills due lack data-driven methods retrieve them. This limits possibility for psychologists and HR managers understand relation between humans digitalisation. paper presents SkillNER, a novel method automatically extracting from text. It named entity recognition (NER) system trained support vector machine (SVM) corpus more than 5000 scientific papers. We developed this by measuring performance our approach against different training models validating results together team psychologists. Finally, SkillNER was tested in real-world case using job descriptions ESCO (European Skill/Competence Qualification Occupation) as textual source. The enabled detection communities profiles based their shared profiles. demonstrates that tool can large efficient way, proving useful firms, institutions, workers. open available online foster quantitative