The Use of Ensemble Classification and Clustering Methods of Machine Learning in the Study of Internet Addiction of Students

Клочко, Оксана; Fedorets, Vasyl; Klochko, Vitalii; Kormer, M. V.

doi:10.5220/0010923500003364

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two hundred sixty-two students majoring in computer science and coming from different regions of Ukraine participated in the experimental study. The data set is presented in the ARFF format and consists of 8 attributes (figure 1) [25]. The data set contains the fields described in table 1.…”

Section: Selection Of Methods and Diagnosticsmentioning

confidence: 99%

Empirical comparison of clustering and classification methods for detecting Internet addiction

Klochko,

Fedorets,

Klochko

2024

CTE Workshop Proc.

View full text Add to dashboard Cite

Machine learning methods for clustering and classification are widely used in various domains. However, their performance and applicability may depend on the characteristics of the data and the problem. In this paper, we present an empirical comparison of several clustering and classification methods using WEKA, a free software for machine learning. We apply these methods to the data collected from surveys of students from different majors, aiming to detect the signs of Internet addiction (IA), a behavioural disorder caused by excessive Internet use. We use Expectation Maximization, Farthest First and K-Means for clustering, and AdaBoost, Bagging, Random Forest and Vote for classification. We evaluate the methods based on their accuracy, complexity and interpretability. We also describe the models developed by these methods and discuss their implications for identifying the respondents with IA symptoms and risk groups. The results show that these methods can be effectively used for clustering and classifying IA-related data. However, they have different strengths and limitations when choosing the best method for a specific task.

show abstract

Section: Selection Of Methods and Diagnosticsmentioning

confidence: 99%

Empirical comparison of clustering and classification methods for detecting Internet addiction

Klochko,

Fedorets,

Klochko

2024

CTE Workshop Proc.

View full text Add to dashboard Cite

show abstract

“…However, not all methods can be used for solving a specific task. The article "The use of ensemble classification and clustering methods of machine learning in the study of Internet addiction of students" [97] describes the technology of empirical comparison of methods of clustering and classification problems solving using WEKA free software for machine learning. Empirical comparison of data clustering methods was based on the results of a survey https://doi.org/10.55056/etq.53 conducted among students majoring in Computer Studies and dedicated to detecting signs of Internet Addiction (IA) (Internet Addiction is a behavioural disorder that occurs due to Internet misuse).…”

Section: Session 1: Artificial Intelligence In Educationmentioning

confidence: 99%

1st Symposium on Advances in Educational Technology: Outlook

Семеріков

Osadchyi²,

Kuzminska

2021

Educ. Technol. Q.

View full text Add to dashboard Cite

show abstract

“…According to the results of the study, it was found that the issues of robotic vision for recognizing actions, gestures and moving them in the space of human movement, as well as for ensuring interaction between a robot and a person, demonstration of actions to a person, training and social communication [10] were most often investigated. The scientific interests of researchers are increasingly correlated with issues of health problems related, in particular, to the mental state of a person in the process of HCI, the emergence of computer addiction [11,12].…”

Section: Introductionmentioning

confidence: 99%

Anthropologically oriented strategies of interaction in the Human-Computer system

Klochko,

Fedorets,

Klochko

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The article, based on the application of anthropological methodology, reveals the phenomenology of the physical-mental interaction between a person and a computer. Ways of integrative use of the concept of Umwelt by J. J. von Uexküll and the theory of movements construction are represented, and Umwelt-oriented strategies for improving computer technologies are presented. The Umwelt, as the world of perception and the world of human activity (in particular, cognitive), can be represented as an anthropo-computer world. On the basis of the current features of the body-mental Umwelt, ways of anthropologically directed improvement of HCI are determined. Using the questionnaire developed by the authors and applying cluster analysis, a survey of students of higher education institutions was conducted in order to determine the physical and mental orientation in Umwelt oriented interaction in the human-computer system. The interpretation of the research results indirectly indicates the systematicity, equality of interaction in the human-computer system. This determines the possibility of distinguishing typical ways of interaction in the human-computer system, among which the bodily and mental-psychological ones are significant, which correspond to certain levels that characterize the systemic, spatio-temporal and structural-functional organization of motor activity in the theory of movements construction.

show abstract

The Use of Ensemble Classification and Clustering Methods of Machine Learning in the Study of Internet Addiction of Students

Cited by 3 publications

References 0 publications

Empirical comparison of clustering and classification methods for detecting Internet addiction

Empirical comparison of clustering and classification methods for detecting Internet addiction

1st Symposium on Advances in Educational Technology: Outlook

Anthropologically oriented strategies of interaction in the Human-Computer system

Contact Info

Product

Resources

About