Overview and analysis of the text mining applications in the construction industry

The data generation in the construction industry has increased dramatically. The major portion of the data in the architecture, engineering and construction (AEC) domain are unstructured textual documents. Text mining (TM) has been introduced to the construction industry to extract underlying knowledge from unstructured data. However, few articles have comprehensively reviewed applications of TM in the AEC domain. Thus, this study adopts a qualitative-quantitative method to conduct a state-of-the-art survey on the articles related to applications of TM in the construction industry which published between the year of 2000 and 2021. VOSviewer software was applied to provide an overview of TM applications regarding to the publication trend, active countries and regions, productive authors, and co-occurrence of keywords perspectives. Eight prime application fields of TM were discussed and analyzed in detail. Five key challenges and three future directions have been proposed. This review can help the research community to grasp the state-of-the-art of TM applications in the construction industry and identify the directions of further research.