Using natural language processing for automated construction contract review during risk assessment at the bidding stage

Download

gorkem_phd.v15.pdf

Date

2022-12

Author

Eken, Görkem

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

759
views

509
downloads

Construction sector contains various risks, and construction projects are open to failure due to their nature and the involvement of multiple parties. Contracts are legal documents that are used to define the responsibilities of parties in a project. Risks that are taken by a party are highly related to their positions in the contracts. However, contracts are prepared by clients, and contractors generally do not have enough time to review their responsibilities before preparing their bids. Moreover, contracts may not always be clear in terms of all subjects. As a result, it may lead to ambiguities. Advances in information technology (IT) may provide solutions to the construction sector in this area. Natural Language Processing (NLP) focuses on using computers to understand, process, and manipulate natural language text to achieve a variety of objectives. NLP can be used to review contract documents within seconds depending on the volume of the documents and available processing power. In this study, FIDIC standard forms of contracts were selected and all sentences were labeled with sentence type and ownership in order to create a training dataset for machine learning applications. In addition to the training dataset, the test dataset was created by using a contract of the real construction project. By using created datasets, 5 different machine learning algorithms were trained with different NLP techniques. The results of 12 machine learning models were evaluated, and the selected ones were combined by the ensemble method. In conclusion, sentence types in a FIDIC contract were categorized 89% accurately as heading, definition, obligation, risk, and right. Additionally, related parties for sentences that imply risk right and obligation were predicted 83% accurately. The proposed method can be used by contractors to quickly classify the contract text in order to identify the contractual risks required to decide risk premiums in the tender preparation phase.

Subject Keywords

Construction contract review, Machine learning, Natural language processing, Text classification, Deep learning

URI

https://hdl.handle.net/11511/101793

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Automating Coordination Efforts for Reviewing Construction Contracts with Multilabel Text Classification Candas, Ali Bedii; Tokdemir, Onur Behzat (2022-06-01) Construction projects involve multiple company departments and disciplines. The departments follow certain rules in implementing a project, also referred to as requirements in a construction contract. Current administration practices do not show which discipline or department is related to any requirement in the contracts. Thus, all departments need to review contract requirements but typically only from their perspective and with minimal communication with one another. In addition to the tendency of this m...
A Multi agent risk analysis and sharing platform for international construction projects Dağkıran, Gülşah; Dikmen Toker, İrem; Tanyer, Ali Murat; Department of Civil Engineering (2015) The risks and complexities that are naturally inherent with construction projects and the diverging interests of the parties involved, cause deviations from the project objectives and make claims an unavoidable consequence in construction projects. Risk management is accepted as one of the critical success factors to handle the claim management process effectively. In construction management literature, while there are several studies to develop a mechanism for risk management, decision making and dispute r...
Preventing and correcting quality issues in construction with intelligent knowledge management Saygılı, Murathan; Tokdemir, Onur Behzat; Department of Civil Engineering (2022-6-21) The construction industry relies on the successful execution of what is planned. Project cost, schedule, and other performance criteria are set and written on a contract, by which all parties are obligated to abide. Similarly, corporate processes are defined by the procedures of companies. However, projects and corporate processes suffer from various obstacles in practice, some of which arise from certain events that might seem insignificant, causing significant deviations from the plan. These obstacles are...
A Relational Database for Construction Delay Bilgin, Gözde; Eken, Görkem; Dikmen Toker, İrem; Birgönül, Mustafa Talat (2015-05-30) Construction projects are open to risks due to their multi-partied, environmentally dependent and complex nature. Unexpected situations generally lead to delays resulting considerable time and money losses. This makes delay and delay analysis to be the core subject matter during execution of construction projects. Therefore project participants should not only be focused on project control but also be able to clarify some project specific issues at the planning stage. At this point, past project data may be...
Determination of instantaneous breaking rate by Geological Strength Index, Block Punch Index and power of impact hammer for various rock mass conditions Aksoy, C. O.; Ozacar, V.; Demirel, Nuray; Ozer, S. C.; Safak, S. (Elsevier BV, 2011-07-01) In mining and construction industries, selection of appropriate excavation method and equipment significantly affects the project feasibility. In the selection, the most important parameters are the geomechanical properties of the rock mass in the excavation route as extensively reviewed in literature. The most widely used geomechanical parameter is uniaxial compressive strength (UCS). However, UCS laboratory test requires time consuming and expensive sampling and core sample preparation processes, which ca...

Citation Formats

G. Eken, “Using natural language processing for automated construction contract review during risk assessment at the bidding stage,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.