The adoption of building information modeling (BIM) is accelerating globally, accompanied by a proliferation of BIM protocols. These protocols facilitate structured collaboration, standardized information management and interoperability among stakeholders in the architecture, engineering and construction (AEC) industry. Despite their growing importance, BIM implementation faces challenges that hinder successful integration. The purpose of this research is to develop a framework that utilizes Natural Language Processing (NLP) techniques and recommendation systems to analyze and address critical challenges in BIM protocols.
This research proposes a framework that uses natural language processing (NLP) techniques and recommendation systems to examine critical BIM challenges across three widely used protocols: the Ohio BIM Protocol (2010), the AEC (UK) BIM Protocol (2012) Version 2.0 and the Construction Industry Council BIM Protocol Second Edition (2018). The framework comprises three modules: the BIM Challenges Identification Module, the Challenge Similarity Module and the Tailored Recommendation Module. The Challenge Similarity Module applies term frequency–inverse document frequency with three similarity measures: cosine similarity, Euclidean distance and Manhattan distance to assess the alignment of challenges with protocols.
Results show that while each method provides distinct insights, they consistently identify specific protocols as more closely related to certain challenges, demonstrating the robustness of the approach. The Tailored Recommendation Module introduces an innovative recommendation system that leverages similarity to match user-defined preferences such as data security, collaboration or adherence to BIM standards with protocol features. This ensures that stakeholders receive a customized, data-driven recommendation aligned with project needs.
This study contributes to both theory and practice by providing a systematic, preference-driven approach to BIM protocol selection, thereby enhancing the efficiency and effectiveness of BIM adoption.
