engleski

The NLP Powered BI Toolkit: The Case of MESOC

In this paper, we present a business intelligence (BI) toolkit based on natural language processing (NLP) methods for the arts and culture domain, collected in the Measuring the Social Dimension of Culture (MESOC) project. The main NLP methods in the underlying pipeline are keyword extraction, multi-label classification of texts, and detection of potential social impacts of cultural policies and practices, all trained on texts from open- access academic publications. The MESOC Toolkit is a georeferenced visualization tool for analyzing impact on social value creation in the areas of health and well-being, urban regeneration, and social cohesion, and enables semantic search for content in the MESOC domain. Therefore, the presented research can serve as a prototype for measuring societal value by identifying recurrent pathways of transformational processes in society that reach beyond the selected field of art and culture.

societal impact ; natural language processing ; business intelligence ; keyword extraction: text classification ; semantic search

nije evidentirano