The consumption of alcohol, tobacco and other drugs is considered a public health problem, being one of the main causes of academic failure of university students. The objective of this research was to identify psychosocial characteristics in clusters of alcohol, tobacco and other drug consumers. A sample of 3741 college students from Ecuador who complete a psychosocial questionnaire was used. Sparse K-means algorithm showed three clusters. Cluster CLNA1 represents students with low consume of tobacco and alcohol. Apparently, they do not have depression and are comfortable with their lives. CLNA2 presents low consume of tobacco and alcohol. This group shows signals of depression and they consider that there are aspects of their life to improve and small but significant problems of their life. CLNA3 presents the higher consume of tobacco and alcohol.
|Title of host publication
|Applied Technologies - 1st International Conference, ICAT 2019, Proceedings
|Miguel Botto-Tobar, Marcelo Zambrano Vizuete, Pablo Torres-Carrión, Sergio Montes León, Guillermo Pizarro Vásquez, Benjamin Durakovic
|Number of pages
|Published - 1 Jan 2020
|1st International Conference on Applied Technologies, ICAT 2019 - Quito, Ecuador
Duration: 3 Dec 2019 → 5 Dec 2019
|Communications in Computer and Information Science
|1st International Conference on Applied Technologies, ICAT 2019
|3/12/19 → 5/12/19
Bibliographical noteFunding Information:
This experiment worked with a sample of 3741 college students from Ecuador who validly answered a psychosocial questionnaire. The 23 variables detailed below were selected. The data are obtained as part of the “CEPRA XII-2018-05 Prediction of drug use” project funded by CEDIA (Ecuadorian Corporation for Research Development and the Academy, by Spanish acronym), and in which researchers from three Ecuadorian and two Spanish universities: Universidad Técnica Particular de Loja, Universidad Técnica del Norte, Universidad Politécnica Salesiana, Universidad de Salamanca and Universidad Loyola Andalucía. The collection of information is carried out through web-based questionnaires previously selected based on three criteria: brevity, psychometric properties, and open for research purposes. Both the questionnaires and the database with the answers were hosted on the web server of the observatory created for this purpose. For the purpose of the evaluation and commissioning of the prediction and classification models, the HPC server technology available at CEDIA is used for high-performance computing. The data has gone through a filtering and cleaning, separating all those that presented anomalies. From the questionnaire that consist of 10 test, 23 variables detailed in Table 1 were selected.
This research was carried out with the funds of the project “CEPRA XII-2018-05 Prediction of Drug Consumption”, winner of the CEPRA contest of CEDIA-Ecuador. The researchers thank CEDIA for their contribution in the development management of the project.
© 2020, Springer Nature Switzerland AG.
- Cluster analysis