Transparent Peer Review By Scholar9
SMART PHONES COMPULSIVE USAGE PREDICTED BY MACHINE LEARNING MODELS
Abstract
As more and more people exhibit the symptoms of smartphone addiction such as obsessive phone use, lower productivity and even physical and mental health issues-concern over smart phone addiction has escalated in recent years. Therefore, it is necessary to create efficient technique for predicting smart phone addiction and identifying people who are at risk. In this study we developed a Machine Learning model that can predict the risk of smart phone addiction using data collected from a survey of smart phone users. The study covered a wide range of psychological traits such as stress, anixity and depression in addition to demographics and phone use patterns. Our model with the help of popular and effective machine learning method. By preprocessing the data, which included encoding categorical categories and normalizing numerical variables, we made sure the model could train successfully. We employed a number of metrics, such as accuracy, to evaluate the model's performance after using a portion of the data to train it. Our results showed that the model was very accurate in predicting smart phone addiction. Our built model has several potential applications. It could be used by medical professionals to identify the individuals who are most at risk of developing a smart phone addiction and to provide the appropriate support. It might be used by app developers to make less addictive apps that promote wiser phone usage habits. In conclusion, our study shows that it is both possible and successful to predict smart phone addiction using machine learning models. Further research is needed to validate our findings on larger and more diverse datasets and explore the potential applications of this model in different contexts.
Rajas Paresh Kshirsagar Reviewer
10 Oct 2024 10:42 AM
Approved
Relevance and Originality
The research article addresses a pressing issue—smartphone addiction—by employing machine learning to predict and identify individuals at risk. As smartphone use continues to rise, understanding addiction and its implications is increasingly vital. The originality of this study is notable, as it combines psychological traits with demographic factors and phone usage patterns to develop a predictive model. This multifaceted approach contributes to the existing literature and provides a fresh perspective on leveraging technology to combat a contemporary societal problem.
Methodology
The methodology outlined in the article should detail the specific machine learning techniques used, such as the algorithms chosen and the rationale behind these choices. While the preprocessing steps, including data encoding and normalization, are briefly mentioned, a more comprehensive explanation of the data collection process, including survey design and participant selection, would enhance the methodology section. Additionally, discussing how the dataset was split into training and testing subsets, along with any cross-validation techniques employed, would further strengthen the robustness of the study.
Validity & Reliability
To establish the validity and reliability of the findings, the article should provide clear metrics to evaluate model performance, such as accuracy, precision, recall, and the confusion matrix. It would also be beneficial to discuss the limitations of the study, such as potential biases in the sample or the generalizability of the results to different populations. Including comparisons with existing predictive models for smartphone addiction would help contextualize the model's effectiveness and robustness.
Clarity and Structure
The article is generally well-structured, moving logically from the introduction to the methodology and conclusions. However, clarity could be improved by avoiding jargon and ensuring that all technical terms are clearly defined. Using headings and subheadings effectively can guide the reader through the paper more smoothly. Additionally, visual aids, such as charts or graphs depicting model performance, could enhance understanding and engagement with the content.
Result Analysis
While the article reports high accuracy in predicting smartphone addiction, a more detailed analysis of the results would enhance the discussion. Presenting specific data points or examples that illustrate how the model identifies at-risk individuals would provide more context. Furthermore, discussing potential applications of the model in practical scenarios, such as in clinical settings or app development, would enrich the conclusion. The suggestion for further research is valid; however, outlining specific future studies or methodologies could provide clearer guidance for subsequent work in this area.
IJ Publication Publisher
Done Sir
Rajas Paresh Kshirsagar Reviewer