A Naïve Bayes approach for ews detection by text mining of unstructured data: a construction project case

Alsubaey, Mohammed; Asadi, Ahmad; Makatsoris, Charalampos

doi:10.1109/intellisys.2015.7361140

Cited by 10 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study related to the topic of this paper is that of Alsubaey et al. (2015) who data mined unstructured text from the project site meeting minutes of 46 projects.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Text mining thus allows for the identification of valuable information that project personnel might oversee. While Alsubaey et al. (2015) focused on data mining four lines of text to search for certain words and then use it in a single classifier, this paper uses the text as well as other identified factors to create prediction models by using various types of data mining algorithms.…”

Section: Literature Reviewmentioning

confidence: 99%

“…This paper investigates if data contained in site meeting minutes can be used as a source of project information to predict final duration of an active project. Alsubaey et al. (2015) was unsuccessful to develop an early warning system on project outcomes (duration) by data mining unstructured text from project site meeting minutes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The value of data from construction project site meeting minutes in predicting project duration

Niekerk

Wium

Koker

2022

BEPAM

View full text Add to dashboard Cite

PurposeConstruction projects generate large volumes of data which can be used for better management of projects. In this paper, key project data is manually extracted from project site meeting minutes. Knowledge discovery technologies are then used to predict the final project duration of active projects.Design/methodology/approachProject planning and effective leadership/governance were identified from literature as the most significant factors that impact the duration of projects. These factors were hence considered as the main features for a data mining process. Items supporting these factors were extracted from site meeting minutes to create a database of 27 civil engineering projects executed over the last ten years. Data mining algorithms were used to predict from this data whether or not an active project will be completed on time.FindingsThe research showed that information from project site meetings can be used to predict final project duration of active projects with accuracy of above 80% when using random forest algorithms from Orange and RapidMiner data mining applications. The value of data to predict project duration from project site meeting minutes is demonstrated but it only becomes practically useable if the format of minutes is suitably standardised.Practical implicationsSome of the data mining algorithms provided accuracies of above 80% in predicting final project duration and proved the value of project data from site meeting minutes. The random forest algorithms are particularly suited to this type of data. The factors with the highest impact on the prediction of the project duration are those related to the progress of the project.Originality/valueThis study for the first time shows that data from site meeting minutes of past and current projects can be used to make accurate predictions of final project duration of active projects and serve as a project management tool to activate remedial measures.

show abstract

“…A study related to the topic of this paper is that of Alsubaey et al. (2015) who data mined unstructured text from the project site meeting minutes of 46 projects.…”

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

The value of data from construction project site meeting minutes in predicting project duration

Niekerk

Wium

Koker

2022

BEPAM

View full text Add to dashboard Cite

show abstract

“…In the study of [16], a view-based method was used, with metadata models to convert documents to structured data. Alsubaey et al presented a Naïve Bayes text mining approach to identify early warnings of failure from meeting records [24]. Kim and Chi developed a system based on natural language processing (NLP) to extract hidden knowledge from construction accident cases [25].…”

Section: Unstructured Data Processingmentioning

confidence: 99%

ACS: Construction Data Auto-Correction System—Taiwan Public Construction Data Example

Tsai

2021

Sustainability

View full text Add to dashboard Cite

This study aims to develop an automatic data correction system for correcting the public construction data. The unstructured nature of the construction data presents challenges for its management. The different user habits, time-consuming system operation, and long pretraining time all make the data management system full of data in an inconsistent format or even incorrect data. Processing the construction data into a machine-readable format is not only time-consuming but also labor-intensive. Therefore, this study used Taiwan’s public construction data as an example case to develop a natural language processing (NLP) and machine learning-based text classification system, coined as automatic correction system (ACS). The developed system is designed to automatically correct the public construction data, meanwhile improving the efficiency of manual data correction. The ACS has two main features: data correction that converts unstructured data into structured data; a recommendation function that provides users with a recommendation list for manual data correction. For implementation, the developed system was used to correct the data in the public construction cost estimation system (PCCES) in Taiwan. We expect that the ACS can improve the accuracy of the data in the public construction database to increase the efficiency of the practitioners in executing projects. The results show that the system can correct 18,511 data points with an accuracy of 76%. Additionally, the system was also validated to reduce the system operation time by 51.69%.

show abstract

“…Although construction projects create huge amounts of unstructured data, however, data mining is not yet widespread in construction projects (Alsubaey et al, 2015). In addition, as project data expands, data processing becomes more difficult.…”

Section: Research Backgroundmentioning

confidence: 99%

Analyzing project data in BIM with descriptive analytics to improve project performance

Marzouk

Enaba

2019

BEPAM

View full text Add to dashboard Cite

Purpose The purpose of this paper is to expand the benefits of building information modeling (BIM) to include data analytics to analyze construction project performance. BIM is a great tool which improves communication and information flow between construction project parties. This research aims to integrate different types of data within the BIM environment, then, to perform descriptive data analytics. Data analytics helps in identifying hidden patterns and detecting relationships between different attributes in the database. Design/methodology/approach This research is considered to be an inductive research that starts with an observation of integrating BIM and descriptive data analytics. Thus, the project’s correspondence, daily progress reports and inspection requests are integrated within the project 5D BIM model. Subsequently, data mining comprising association analysis, clustering and trend analysis is performed. The research hypothesis is that descriptive data analytics and BIM have a great leverage to analyze construction project performance. Finally, a case study for a construction project is carried out to test the research hypothesis. Findings The research finds that integrating BIM and descriptive data analytics helps in improving project communication performance, in terms of integrating project data in a structured format, efficiently retrieving useful information from project raw data and visualizing analytics results within the BIM environment. Originality/value The research develops a dynamic model that helps in detecting hidden patterns and different progress attributes from construction project raw data.

show abstract

A Naïve Bayes approach for ews detection by text mining of unstructured data: a construction project case

Cited by 10 publications

References 17 publications

The value of data from construction project site meeting minutes in predicting project duration

The value of data from construction project site meeting minutes in predicting project duration

ACS: Construction Data Auto-Correction System—Taiwan Public Construction Data Example

Analyzing project data in BIM with descriptive analytics to improve project performance

Contact Info

Product

Resources

About