A Machine Learning Approach to Understanding Sociodemographic Factors in Electric Vehicle Ownership in the U.S.
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe manuscript uses data from the 2022 National Household Travel Survey (NHTS) to analyze socio-demographic factors affecting electric vehicle ownership in the U.S. using binary logistic regression models and three machine learning models (Naïve Bayes, Support Vector Machines, and Random Forest). The study finds that the Pacific region has the highest rate of electric vehicle ownership; higher household income and homeownership are significantly associated with increased electric vehicle adoption, and policy recommendations are made. Below are my suggestions for revisions that I hope will help you improve the quality of the manuscript.
1. In the introduction section, the manuscript mentions that the adoption of electric vehicles is being encouraged in order to meet the challenges of environmental issues, etc. Please expand further on the environmental benefits it brings, such as by providing specific data or citing existing studies to highlight the role and importance of electric vehicles for the environment and the low-carbon energy transition.
2. In the Literature Review section, the manuscript summarizes the inequitable distribution of EV charging infrastructure through the literature review, and suggests to further elucidate the current policy research on this aspect and compare the differences and innovations between this study and the related studies. In the Built Environment section, there is a lack of summarization and critical thinking about the literature, and it is recommended that the methodologies, results and interpretations of existing studies be critically analyzed to point out their limitations.
3. In the Data and Analysis section, the manuscript uses binary logistic regression models and three machine learning models, but does not explain why these models were chosen and how they fit the characteristics of the data. It is recommended that the reasons for choosing the models and the advantages and disadvantages of each model be explained.
4. The authors used accuracy, precision, recall, and F1-scores to evaluate the models, but did not discuss the limitations of these metrics in this study and whether other, more appropriate metrics existed for evaluation; it is recommended that additional discussion of evaluation metrics be added.
5. Please make sure that the written language in the manuscript is scrutinized to ensure that it is clear and correct, and instances of misspellings should not be expected, such as the title of the Methods and Data section, where data is misspelled as dara.
6. The manuscript compares the Random Forest Model with models such as SVM and suggests further discussion on how how the results presented by models such as the Random Forest Model affect the adoption of electric vehicles.
7. In the conclusion section, the manuscript provides some policy recommendations, but they are rather general and brief. Please refine the recommendations to make them more specific, detailed and feasible, such as how to promote the adoption of electric vehicles in low-income households and rural areas through financial subsidies and the construction of charging facilities.
8. To improve the overall clarity and comprehensibility of the manuscript, it is recommended that authors incorporate visual aids such as graphs, charts, or diagrams. These visuals can help illustrate key concepts, methods, or findings and can significantly enhance the richness of the manuscript and promote a better understanding of the authors' work.
Author Response
Thank you for your time and the effort you spent in reviewing our paper. Please find the attached word file titled "Response to Reviewer 1 comments" for the detailed responses.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe article has too much duplication. Please see the attachment for other comments.
Comments for author File: Comments.pdf
Author Response
Thank you for your time and the effort you spent in reviewing our paper. Please find the attached word file titled "Response to Reviewer 2 comments" for the detailed responses.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsAll suggestions are gathered in the attached file
Comments for author File: Comments.pdf
Author Response
Thank you for your time and the effort you spent in reviewing our paper. Please find the attached word file titled "Response to Reviewer 3 comments" for the detailed responses.
Author Response File: Author Response.pdf
Reviewer 4 Report
Comments and Suggestions for Authors 1) This paper talks about a machine learning approach to understanding socio-demographic Factors in Electric Vehicle Ownership in the U.S. 2) It discusses electric vehicles which are rapidly gaining popularity due to their environmental benefits, such as reducing greenhouse gas emissions. Considering the sociodemographic factors that influence the adoption of EVs is essential when developing equitable and efficient transportation policies. This article leverages the NHTS 2022 data to analyze the sociodemographic factors influencing 16 the adoption of EVs in the U.S. A binary logistic regression model and three machine learning models were employed to predict EV ownership in the U.S. The results of the regression model suggested that the Pacific division leads in EV adoption, most likely due to legislation and improved infrastructure, while regions such as East South Central suffer from lower EV adoption. The findings indicate that higher household income and home ownership significantly correlate with increased EV adoption. In contrast, renters and rural households exhibit lower adoption rates suggesting an increase in charging facilities in these regions can promote EV adoption. The Random Forest model outperforms others with an accuracy of 82.72%, suggesting its robustness in handling complex relationships between variables. Policy implications include the need for financial incentives for low-income households and increased charging infrastructure in rural and underserved urban areas to promote equitable EV adoption. 3) This paper has potential. However, it requires a revision. 4) Any abbreviations or acronym shall be well-defined before utilizing them directly. NHTS is used directly in the abstract. Please make sure this mistake is not repeated in the whole manuscript. 5) The keywords can be improved. Moreover, short forms shall not be directly used in keywords. 6) The words like "we, I, they" are utilized in the work. This is a colloquial language and it should be avoided towards a research paper. 7) The introduction section is the weakest of this work. This works claims alot. However, it is not properly defined in the introduction section. The detail of elements missing in the introduction section can be seen in the following comments. 8) What is the contribution of the paper ? It must be clearly mentioned in the introduction. So far, this elements is not obvious in the introduction. 9) What is the motivation of the paper ? It must be clearly mentioned in the introduction. So far, this elements is not obvious in the introduction. 10) What is the scope of the paper ? It must be clearly mentioned in the introduction. So far, this elements is not obvious in the introduction. 11) What are the preceding affined articles in this research area. A table shall be drawn showing the limitations of the previous works in this area and what new you are bringing for the readers ? Or it is yet another paper ? 12) Before the results section, there should be a pseudo code to convolute the proposed scheme. Pseudo codes are usually considered for mathematical formulation driven work. In this work, a possible pseudo code could be designed for practitioners to understand things smoothly. The variables of input and output are required to be defined in the pseudo code. And then that defined language is required to be used in the rest of the lines. Please follow the above steps accordingly. 13) The y-axis and x-axis are not visible in Fig. 1. It lacks pixel quality too. Please replace fig. 1 and divide these 4 subfigures by giving them separate labels of a,b,c,d and explain their details in the main caption. 14) For a Journal paper talking about EV ownership and demographic factors, the introduction section and references could be thoroughly improved. How the trend of EV came into the market ? Why renewable energy integration is required in the new world and how EV is supporting this factors towards transportation electrification ? These are important factors to discuss to widen the spectrum of audience. Some of the suggested references are as follows: 1) 'Energy Storage Technologies: An Integrated Survey of Developments, Global Economical/Environmental Effects, Optimal Scheduling Model, and Sustainable Adaption Policies,' 2) 'Parameter estimation of vehicle batteries in V2G systems: An exogenous function-based approach,' 3) 'Bidirectional Charging in V2G Systems: An In-Cell Variation Analysis of Vehicle Batteries’. 15) Format of references also literally require an overall. The format is not consistent. In some references, the page number is reflected at the end and in others, year is reflected in the end. Similarly, in some references, the title is inverted commas and some it is now. Also, in some, the first letter of the title of the paper is only capital. In others, all first letters of the titles of the paper are capital. Please visit the styling again and maintain consistency. Comments on the Quality of English LanguageThe quality of English can be improved.
Author Response
Thank you for your time and the effort you spent in reviewing our paper. Please find the attached word file titled "Response to Reviewer 4 comments" for the detailed responses.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThe author used a binary logistic regression model and three machine learning models to analyze the socio-demographic factors that influence electric vehicle ownership in the US. Subsequent to incorporating feedback, the manuscript underwent substantial improvements, and the content is more detailed and logical. Now this time it has reached the standard for publication in Sustainability.
Reviewer 2 Report
Comments and Suggestions for AuthorsThe article has been modified to meet the requirements of journal publication.
Reviewer 4 Report
Comments and Suggestions for AuthorsThe work has been revised well. All the comments have been addressed adequately. I recommend the acceptance of this work in its current form.
