Yeon Ju Shin

Ms. Yeon Ju Shin

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 March 2025 in Buildings
Verified
Journal Article
Open access
PDF file
EKEu Wang Kim
Eu Wang Kim
YSYeon Ju Shin
Yeon Ju Shin
KKKyong Ju Kim
Kyong Ju Kim
SKSehoon Kwon
Sehoon Kwon
Construction contract review demands specialized expertise, requiring comprehensive understanding of both technical and legal aspects. While AI advancements offer potential solutions, two problems exist: LLMs lack sufficient domain-specific knowledge to analyze construction contracts; existing RAG approaches do not effectively utilize domain expertise. This study aims to develop an automated contract review system that integrates domain expertise with AI capabilities while ensuring reliable analysis. By transforming expert knowledge into a structured knowledge base aligned with the SCF classification, the proposed structured knowledge-integrated RAG pipeline is expected to enable context-aware contract analysis. This enhanced performance is achieved through three key components: (1) integrating structured domain knowledge with LLMs, (2) implementing filtering combined with hybrid dense–sparse retrieval mechanisms, and (3) employing reference-based answer generation. Validation using Oman’s standard contract conditions demonstrated the system’s effectiveness in assisting construction professionals with contract analysis. Performance evaluation showed significant improvements, achieving a 52.6% improvement in Context Recall and a 48.3% improvement in Faithfulness compared to basic RAG approaches. This study contributes to enhancing the reliability of construction contract review by applying a structured knowledge-integrated RAG pipeline that enables the accurate retrieval of expert knowledge, thereby addressing the industry’s need for precise contract analysis.

29 April 2024 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
KKKyong Ju Kim
Kyong Ju Kim
DKDeok Soo Kim
Deok Soo Kim
KKKyoungmin Kim
Kyoungmin Kim
EKEu Wang Kim
Eu Wang Kim
YSYeon Ju Shin
Yeon Ju Shin
Bid-rigging has long been a problem in the construction area. This research identified the existing problems in evaluating damages from bid-rigging in Design-Bid-Build (DBB) and lowest-bid construction projects. Traditional econometric assessment based on stochastics requires sufficient historical data to obtain reliable estimates. Thus, it is crucial to collect and analyze data from pertinent projects for its utilization. To ensure the accuracy of the estimation, a substantial amount of data on the outcomes of DBB bids should have been gathered. In many construction projects, that requirement could not be met. Furthermore, econometric analysis cannot reflect the differences caused by the details of individual projects. This study proposes an alternative approach based on detailed cost estimates, weights of major work groups and their historical bid rates when historical data from similar projects are scarce. This approach can reflect the distinct characteristics of individual projects. The proposed model was applied to 23 gas pipeline construction projects under DBB and the lowest bid. This study identified the impacts of the different compositions of major work groups. Bid rates of the main work groups could not only be used to evaluate the damages caused by bid-rigging, but could also be used to determine reliable bid prices and provide a bidding strategy to aid the bidder’s decision-making process in future bids for similar projects.

17 December 2025 in Administrative Sciences
Verified
Journal Article
Open access
PDF file
EKEu Wang Kim
Eu Wang Kim
KKKyong Ju Kim
Kyong Ju Kim
YSYeon Ju Shin
Yeon Ju Shin
NCNamho Cho
Namho Cho
DSDong Cheol Shin
Dong Cheol Shin
Many Korean local governments have enacted ordinances that enable resident participation in the supervision of public construction projects, yet an implementation gap persists between the legal framework and actual engagement. This study thus examined causes of and strategies for residents’ participation in defect reporting and the role of resident supervisor using a sequential embedded design. Administrative data from local governments were analyzed, followed by 94 survey data from resident representatives. Awareness about the defect reporting and role of resident supervisor was low, while support and intention for participation were higher. Awareness, perceived ordinance effectiveness, and support for resident participation were associated with intention, whereas financial rewards showed no significant association. These results suggest that insufficient awareness and trust—not lack of motivation—are the primary barriers, indicating the need to shift from offering rewards to targeted communication, procedural transparency, and capacity-building. This study’s contribution is its mixed-methods empirical assessment of this gap, informing the design of resident-participation policies by prioritizing awareness campaigns, procedural transparency, and training for resident supervisors.