A case study on the use of machine learning techniques for supporting technology watch
作者：
Highlights：
• Different models are proposed to find the optimal one for automatic classification.
• Models differ in input parameters and Artificial Intelligence algorithms.
• Input parameters are text (from documents and experts) and semantic annotations.
• The data catalogue used in the research comes from a real industrial context.
• The result are compared in terms of accuracy and reduction of human workload.
摘要
•Different models are proposed to find the optimal one for automatic classification.•Models differ in input parameters and Artificial Intelligence algorithms.•Input parameters are text (from documents and experts) and semantic annotations.•The data catalogue used in the research comes from a real industrial context.•The result are compared in terms of accuracy and reduction of human workload.
论文关键词：Text mining,Knowledge management applications,Multi-classification,Technology watch automation,Semantic annotations
论文评审过程：Received 8 March 2016, Revised 15 June 2018, Accepted 1 August 2018, Available online 4 August 2018, Version of Record 13 October 2018.
论文官网地址：https://doi.org/10.1016/j.datak.2018.08.001
