TY - GEN
T1 - A corpus database for cybersecurity topic modeling in the construction industry
AU - Yao, Dongchi
AU - de Soto, Borja García
N1 - Funding Information:
The authors want to thank the Center for Cyber Security at New York University Abu Dhabi (CCS-AD) for the support provided.
Publisher Copyright:
© ISARC 2023. All rights reserved.
PY - 2023
Y1 - 2023
N2 - In the digitalized era of Construction 4.0, ensuring the confidentiality, availability, and integrity of digital assets through cybersecurity is crucial for the construction industry. Although more than 75% of respondents from a Forrester survey who are in the construction, engineering, and infrastructure industries reported to have experienced a cyber-incident in the past 12 months, only 0.25% of cybersecurity publications focus on the construction industry until Jan 2023. Considering the significance of ensuring cybersecurity in construction, this study uses Latent Dirichlet Allocation (LDA) Topic Modeling technique to identify potential research directions in cybersecurity in the construction industry, based on various text sources collected, including news, articles & blogs, academic publications, books, standards, and company reports. The results of the study identify eight topics for future research: Perform Risk Analysis, Prevent the Increasing Cyber Incidents, Detect Ransomware, Strengthen Management Process, Protect Network Devices, Regulate Information Storage and Sharing, Protect Privacy, and Improve Authentication Process. Additionally, the corresponding action is proposed for addressing each topic. These findings can be used by researchers, practitioners, and policymakers in the construction industry to address the challenges and opportunities in cybersecurity.
AB - In the digitalized era of Construction 4.0, ensuring the confidentiality, availability, and integrity of digital assets through cybersecurity is crucial for the construction industry. Although more than 75% of respondents from a Forrester survey who are in the construction, engineering, and infrastructure industries reported to have experienced a cyber-incident in the past 12 months, only 0.25% of cybersecurity publications focus on the construction industry until Jan 2023. Considering the significance of ensuring cybersecurity in construction, this study uses Latent Dirichlet Allocation (LDA) Topic Modeling technique to identify potential research directions in cybersecurity in the construction industry, based on various text sources collected, including news, articles & blogs, academic publications, books, standards, and company reports. The results of the study identify eight topics for future research: Perform Risk Analysis, Prevent the Increasing Cyber Incidents, Detect Ransomware, Strengthen Management Process, Protect Network Devices, Regulate Information Storage and Sharing, Protect Privacy, and Improve Authentication Process. Additionally, the corresponding action is proposed for addressing each topic. These findings can be used by researchers, practitioners, and policymakers in the construction industry to address the challenges and opportunities in cybersecurity.
KW - Construction Industry
KW - Cybersecurity
KW - Deep Learning
KW - Natural Language Processing
KW - Topic Modeling
UR - http://www.scopus.com/inward/record.url?scp=85156137471&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85156137471&partnerID=8YFLogxK
U2 - 10.22260/ISARC2023/0072
DO - 10.22260/ISARC2023/0072
M3 - Conference contribution
AN - SCOPUS:85156137471
T3 - Proceedings of the International Symposium on Automation and Robotics in Construction
SP - 537
EP - 544
BT - Proceedings of the 40th International Symposium on Automation and Robotics in Construction, ISARC 2023
A2 - Garcia de Soto, Borja
A2 - Gonzalez, Vicente
A2 - Brilakis, Ioannis
PB - International Association for Automation and Robotics in Construction (IAARC)
T2 - 40th International Symposium on Automation and Robotics in Construction, ISARC 2023
Y2 - 5 July 2023 through 7 July 2023
ER -