BUSINESS INSOLVENCY: National and international bibliometric study supported by text mining

• Autor(a) principal: Menezes, Lenio Vitor Oliveira
• Data de Publicação: 2023
• Outros Autores: de Oliveira, José Sérgio Casé
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Revista Universo Contábil
• Texto Completo: https://ojsrevista.furb.br/ojs/index.php/universocontabil/article/view/e2022102
• topic: Business insolvency; Bibliometry; ProKnow-C; Information mining; Insolvencia empresarial; Bibliometría; ProKnow-C; Minería de información; Insolvência empresarial; Insolvência Empresarial; Bibliometria; Mineração de informações.; ProKnow-C; Mineração de informações

The main objective of this article was to understand and compare the most discussed topics in the national and international literature on business insolvency. It used a technique for systematizing the selection of academic papers, the Knowledge Development Process-Constructivist, and text mining techniques supported by the Iramuteq software. We identified an expansion in national and international academic production after 2008, coinciding with the North American subprime mortgage crisis reflected worldwide. We identified differences between the topics covered by national and international literature. The national literature showed a greater interest in understanding the bankruptcy process of small and medium enterprises, using mainly statistical techniques and interviews, while the international literature proved to be quite heterogeneous in the segments studied, using statistical techniques but also manifesting an interest in machine learning techniques. As an academic contribution, this work synthesized the main lines of study developed in business insolvency, an area of knowledge of multidisciplinary interest that still does not have a conclusive theory. The work also contributes as a source for the identification of research gaps, that is, in the identification of discussions still little explored in the national scenario, such as the discussion of the relationship between earnings management and corporate insolvency and the use, with greater consistency, of machine learning techniques such as Support Vector Machine and Artificial Neural Networks.