Predicting Construction Workers’ Intentions to Engage in Unsafe Behaviours Using Machine Learning Algorithms and Taxonomy of Personality
, Vicente A. González 2,*, Tak Wing Yiu 3, Guillermo Cabrera-Guerrero 4 and Ruiqi Deng 5
Round 1
Reviewer 1 Report
Comment #1: This study used a machine learning approach to understand worker intentions to engage in un-safe behavior. A sample of 268- and five-ML were used to answer the main question of the study. Although this research provides valuable results, the reviewer has the following comments:
Comment #2: The reviewer suggests combined conceptual model and research method into one section, as it seems a lot of information in the conceptual model is more related to the method section.
Comment # 3: The authors stated that (in line 82-83) “conduct a literature review to investigate the predictors for workers’ unsafe behavioural intentions at the individual level;”. However, the information provided in the literature review section is very limited.
Comment # 4: Researchers used too many acronyms (i.,e., BP-NN , TPB, SDT, DT, SVM, MLR, KNN, CNN, NRMSE, MAPE, NEO-FFI, NEW-PI-R, FOR-BFI, SCI-WHSB, SDQ, WSS, SBS, SPS) which make it difficult to follow these terms.
Comment # 5: As a reader, I see this paper is more methodological paper (i.e., method section well addressed in this paper) rather than investigating worker intentions to engage in un-safe behavior. If the authors agree with this comment, I would suggest revising the structure of this paper.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The article presents the problem of predicting the behavior of construction workers in terms of occupational safety in an interesting way. My questions are provided below.
1. The literature review regarding the subject of the research conducted by the authors is carried out briefly. Have similar studies, resulting in the development of a model for predicting dangerous behavior of construction workers, been carried out earlier? Please provide this information in the literature review.
2. Does the article propose a completely new method of predicting the dangerous behavior of construction workers? If there were already studies similar to those presented in the article, please refer to them.
3. Is it currently possible to compare it with other machine learning research in the field of construction safety?
4. Can the authors compare their research (using the machine learning algorithms) with other research aimed at predicting human behavior in areas other than construction, e.g. predicting criminal behavior?
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
