Using Classification Techniques for Assigning Work Descriptions to Task Groups on the Basis of Construction Vocabulary

Abstract

Construction project management produces a huge amount of documents in a variety of formats. The efficient use of the data contained in these documents is crucial to enhance control and to improve performance. A central pillar throughout the project life cycle is the Bill of Quantities (BoQ) document. It provides economic information and details a collection of work descriptions describing the nature of the different works needed to be done to achieve the project goal. In this work, we focus on the problem of automatically classifying such work descriptions into a predefined task organization hierarchy, so that it can be possible to store them in a common data repository. We describe a methodology for preprocessing the text associated to work descriptions to build training and test data sets and carry out a complete experimentation with several well-known machine learning algorithms.