Text Mining Risk Assessment–Based Model to Conduct Uncertainty Analysis of the General Conditions of Contract in Housing Construction Projects: Case Study of the NSW GC21

Abstract

Construction contracts are known to be the most effective factor to address the challenging subject of risk-sharing between key stakeholders in a project. This study will be conducted for the early recognition of sources of uncertainty in construction contracts that are crucial to avoid when meeting the project objectives. To achieve this goal, a two-stage approach will be used. First, a text analysis method will be developed following previous research to identify key commitments. This rule-based method will rely on a lexicon database that includes promisor-determiner nouns (PDN) and obligation-maker verbs (OMV). Second, to estimate the effects of uncertainties on project objectives, a two-stage risk analysis technique based upon probability and impact estimation will be adapted. The proposed text analysis framework will be validated using MATLAB. The major contribution of knowledge from this study will be to present a text mining risk analysis-based model to assess the patterns of the risk-sharing under general conditions of contract between parties. To quantify the risks of contract obligations, the clauses of general conditions of the New South Wales Government of Australia GC21 (NSW GC21) contract will be analyzed against five project objectives. The results show that the proposed method could be effectively used to identify the main obligations of the other party in the types of contracts to develop the contract strategy for the client and the contractor.