Ciência-IUL
Publicações
Descrição Detalhada da Publicação
13th Iberian Conference on Information Systems and Technologies (CISTI)
Ano (publicação definitiva)
2018
Língua
Inglês
País
Estados Unidos da América
Mais Informação
Web of Science®
Esta publicação não está indexada na Web of Science®
Scopus
Google Scholar
Abstract/Resumo
IT incident management process requires a correct categorization to attribute incident tickets to the right resolution group and obtain an operational system as quickly as possible, having the lowest possible impact on the business and costumers. In this work, we introduce a module to automatically categorize incident tickets, turning the responsible teams for incident management more productive. This module can be integrated as an extension into an incident ticket system (ITS), which contributes to reduce the time wasted on incident ticket route and reduce the amount of errors on incident categorization. To automate the classification, we use a support vector machine (SVM), obtaining an accuracy of 89%, approximately, on a dataset of real-world incident tickets.
Agradecimentos/Acknowledgements
--
Palavras-chave
Machine learning,Automated incident categorization,SVM,Incident management,Incident management process,Categorization
Classificação Fields of Science and Technology
- Ciências Físicas - Ciências Naturais