Can a chatbot enhance hazard awareness in the construction industry?

Abstract

Safety training enhances hazard awareness in the construction industry. Its effectiveness is a component of occupational safety and health. While face-to-face safety training has dominated in the past, the frequent lockdowns during COVID-19 have led us to rethink new solutions. A chatbot is messaging software that allows people to interact, obtain answers, and handle sales and inquiries through a computer algorithm. While chatbots have been used for language education, no study has investigated their usefulness for hazard awareness enhancement after chatbot training. In this regard, we developed four Telegram chatbots for construction safety training and designed the experiment as the treatment factor. Previous researchers utilized eye-tracking in the laboratory for construction safety research; most have adopted it for qualitative analyses such as heat maps or gaze plots to study visual paths or search strategies via eye-trackers, which only studied the impact of one factor. Our research has utilized an artificial intelligence-based eye-tracking tool. As hazard awareness can be affected by several factors, we filled this research void using 2-way interaction terms using the design of experiment (DOE) model. We designed an eye-tracking experiment to study the impact of site experience, Telegram chatbot safety training, and task complexity on hazard awareness, which is the first of its kind. The results showed that Telegram chatbot training enhanced the hazard awareness of participants with less onsite experience and in less complex scenarios. Low-cost chatbot safety training could improve site workers' danger awareness, but the design needs to be adjusted according to participants' experience. Our results offer insights to construction safety managers in safety knowledge sharing and safety training.

Evaluating the Influence of Foreign Exchange Policy Regime on the Construction Sector in Nigeria

“…In explaining the models, the analysis of variance is adopted as a special regression analysis of the dependent and independent variables. Analysis of variance is basically used for ascertaining the difference in means of samples (Asamaoh & Offei-Nyako, 2013) and relationships in modelling (Zhu et al, 2022). For the time series data obtained for this study, the analysis of variance (ANOVA) and analysis of covariance (ANCOVA) was used for the regression estimations.…”

Artificial intelligence and machine learning applications in the project lifecycle of the construction industry: A comprehensive review

“… [ 80 , 111 ] ML Can a chatbot enhance hazard awareness in the construction industry? 2022 Hazard awareness enhancement by chatbot training [ 79 ] AI Big Data Technology in Construction Safety Management: Application Status, Trend and Challenge 2022 Construction safety management [ 112 ] AI Integration of Building Information Modeling and Artificial Intelligence Systems to Create a Digital Twin of the Construction Site 2022 Hazard identification and risk management [ 113 ] …”

“…In another study by Ref. [ 79 ], Telegram chatbot safety training and task complexity on hazard awareness were investigated. Results indicated that Telegram chatbot training positively influenced hazard awareness, particularly for participants with limited onsite experience and in less complex scenarios.…”

Willingness to accept metaverse safety training for construction workers based on extended UTAUT

“…Such complications are affected by numerous factors, including risk-taking behavior attitude, risk perception, unsafe construction equipment, geological exploration design, technical management, safety management, and construction site conditions (30)(31)(32). In this regard, many studies have suggested that chatbots and virtual training platforms can enhance the training effect (4,33). The new technology promotes the updating and upgrading training content, and ST based on virtual reality plays an increasingly important role.…”