Learning Style Preferences of College Students Using Big Data

Available online at www.sciencedirect.com Available online at www.sciencedirect.com

ScienceDirect ScienceDirect

Procediaonline Computer 00 (2019) 000–000 Available at Science www.sciencedirect.com Procedia Computer Science 00 (2019) 000–000

ScienceDirect

www.elsevier.com/locate/procedia www.elsevier.com/locate/procedia

Procedia Computer Science 160 (2019) 461–466

The 4th International workshop on Big Data and Networks Technologies (BDNT 2019) The 4th International workshop on4-7, Big2019, Data and Networks Technologies (BDNT 2019) November Coimbra, Portugal November 4-7, 2019, Coimbra, Portugal

Learning Style Preferences of College Students Using Big Data Learning Style Preferences of Collegeb Students Using Big Datac a Amelec Viloriaa*, Ingrid Regina Petro Gonzalezb, Omar Bonerge Pineda Lezamac Amelec Viloria *, Ingrid Regina Petro Gonzalez , Omar Bonerge Pineda Lezama Universidad de la Costa, St. 58 # 55 – 66, Barranquilla 080001, Colombia b Universidad Pereira, Pereira 660001, Colombia Universidad de laLibre Costa,Seccional St. 58 # 55 – 66, Barranquilla 080001, Colombia c UniversidadbUniversidad TecnológicaLibre Centroamericana (UNITEC), San660001, Pedro Sula 21101, Honduras Seccional Pereira, Pereira Colombia c Universidad Tecnológica Centroamericana (UNITEC), San Pedro Sula 21101, Honduras a a

Abstract Abstract Learning styles is one of the most studied topics in the field of education and the research results have generated relevant changes in the teaching-learning thereinarethe several theoretical explain the characterization development Learning styles is one ofprocess. the mostCurrently, studied topics field of educationmodels and thethat research results have generated and relevant changes in teaching-learning several theoretical thatwhile explain the characterization and The development of the learning styles from process. differentCurrently, points of there view,are some of them share models concepts, others completely differ. research of learning styles from styles different pointseducation of view, students some offor them share concepts, while others completely differ. Theuniversity. research focuses on the learning of higher improving the quality of the educational process at the The results allow the recognize learning style students preferences of college the students from different careers, and enable to focuses on the learning styles of the higher education for improving quality of the educational process at the teachers university. The results allow recognize the learning style the preferences of college students differenttocareers, enable to properly guide thethe learning activities by selecting best teaching strategies, thus from contributing raise theand quality of teachers education. properly guide the learning activities the best teaching strategies, thus contributing to raise the quality of education. The results are expected to be relevantby forselecting further researches. The results are expected to be relevant for further researches. © 2019 The Authors. Published by Elsevier B.V. © 2019 The Authors. Published by Elsevier B.V. © 2019 The Authors. by Elsevier This is an open accessPublished article under the CC B.V. BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the Conference Program Chairs. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the Conference Program Chairs. Peer-review under responsibility of the Conference Program Chairs. Keywords: Learning styles, college students, different college careers. Keywords: Learning styles, college students, different college careers.

1. Introduction 1. Introduction The knowledge construction process is not the same for all students. The experience in the classroom offers The knowledge construction processfactors, is not students the sameinteract for all students. The experience classroom that offers evidence that, according to different in a different way with in thethe information is evidence that, according to different factors, students interact in a different way with the information that is presented to them, representing different learning styles. These styles differ in the way of selecting and processing presented to them, representing different learning styles. These styles differ in the way of selecting and processing information, the predominant learning channels, and the forms of social interaction [1]. information, the predominant learning channels, and the forms of social interaction [1].

* Corresponding author. Tel.: +57-3046238313. E-mail address:author. [email protected] * Corresponding Tel.: +57-3046238313. E-mail address: [email protected] 1877-0509 © 2019 The Authors. Published by Elsevier B.V. This is an open access under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) 1877-0509 © 2019 Thearticle Authors. Published by Elsevier B.V. Peer-review under responsibility of the Conference Program Chairs. This is an open access article under CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the Conference Program Chairs. 1877-0509 © 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the Conference Program Chairs. 10.1016/j.procs.2019.11.064

Author name / Procedia Computer Science 00 (2018) 000–000 Amelec Viloria et al. / Procedia Computer Science 160 (2019) 461–466

2 462

Based on these assumptions, the following research question emerged: What are the learning style preferences of students from different careers at the University of Mumbai? In the Higher Education system, knowing the preferences for learning styles in students can help build environments where effective learning takes place. So, this research aims to analyze the learning style preferences of students from different careers at the University of Mumbai. Learning style is a very important element to promote quality teaching. Researches conducted in the past few years provide evidence that learning styles are closely related to the way in which students learn, teachers teach, and how they interact in a teaching-learning relationship [2] [3] [4]. The interest for improving the educational conditions of students for achieving a quality education does not focus just on the teaching conditions, but in pedagogical or internal aspects of students, allowing to develop greater competencies in them. This interest arises from changes in the educational content that require not only to memorize, but to manage multiple sources of information in order to transform, relate and apply them. The results of international researches on learning styles have served to generate significant changes in the teaching process. In this sense, Hernández and Hervás report that some universities systematically apply the identification of learning styles in order to design teaching strategies in relation to the profiles of the students [5] [6] [7]. 2. Method This research presents a mixed approach which is non-experimental and comparative in scope with a crosssectional design. The sample was composed of 1854 male and female college students from different careers as Psychology, Journalism, Arts, Philosophy, History, Education Sciences at the University of Mumbai in India whose ages range from 22 to 32 years, obtained using the proportional stratified probability sampling. The Honey-Alonso questionnaire (CHAEA) adapted by [8] was applied for collecting the data on learning styles. Normality and homoscedasticity tests were applied to determine the statistics according to each objective. The identification of the learning styles of college students was analyzed using descriptive statistics techniques. The differentiation of the styles according to each career was carried out with Analysis of Variance test (ANOVA) [9]. [10]. 3. Results The participants were selected according to their careers in Psychology, Journalism, Arts, Science, Education, History, and Philosophy, taking into account that the members of different groups were similar in their characteristics in terms of age, gender, and course. The selection of the sample was performed using the proportional stratified sampling being composed of 12.524 students distributed as shown in Table 1. Table 1. Descriptive statistics of learning styles N

Minimum

ACTIVIST

12.524

2

REFLECTOR

12.524

8

THEORIST

12.524

PRAGMATIST

12.524

N valid (according to list)

12.524

Maximu m 21

Mean

Typ. Dev.

11.12

3.235

22

14.65

3.785

4

22

12.74

3.364

0

22

11.10

3.852

The results obtained show that college students have greater preferences for the reflector learning style, followed by the theorist, pragmatist, and activist styles. In terms of [11], it would seem that attitudes, activities, and cognitive styles of scientific communities that represent a specific discipline are related to the characteristics and structure of the fields of knowledge with what they are professionally committed (see Table 2). Considering the distribution of styles depending on the career, it is globally observed that, in all the analyzed careers [12] [13], the reflector

Author name / Procedia Computer Science 00 (2018) 000–000 Amelec Viloria et al. / Procedia Computer Science 160 (2019) 461–466



3 463

learning style is clearly dominant above all others (see Table 3). The variance analysis test determined that there are statistically significant differences between the activist, theorist, and pragmatist learning styles according to the different careers (see Table 4). Table 2. Descriptive statistics of learning styles according to career Career

ACTIVIST

THEORIST

PRAGMATIST

13.47

REFLECTO R 14.36

Psychology

12.36

13.12

Journalism

11.74

14.10

12.41

12.96

Arts

11.10

16.63

14.35

12.75

Education Sciences

11.82

14.47

13.47

14.64

History

10.14

15.96

12.96

12.23

Philosophy

8.25

16.47

9.47

4.67

Total

11.87

15.96

12.65

12.52

Table 3. F-test of Analysis of Variance (ANOVA)

ACTIVIST

REFLECTOR

THEORIST

PRAGMATIST

Intergroups

Sum of squares 415.475

gl 6

half quadratic 82.365

Intragroups

3207.658

254

11.147

Total Inter-groups

3668.071 157.058

295 6

29.685

Intragroups

2571.611

255

11.235

Total Intergroups Intragroups Total Intergroups Intragroups

3042.669 398.820 3719.904 4107.724 1514.352 2922.751

282 6 285 290 6 285

Total

4436.574

290

F 7.6

Sig. ,000

2.85

,010

77.148 13.875

5.87

,000

302.247 10.354

29.2

,000

Table 4. Descriptive statistics of learning styles depending on the genre ACTIVIST

REFLECTOR

THEORIST

PRAGMATIST

Genre Female

N 5000

Mean 11.35

Typ. Dev 3.245

Mean Typ. Error ,242

Male

7524

10.24

3.778

,357

Female

5000

14.75

3.325

,278

Male

7524

15.41

3.012

,252

Female

5000

12.75

3.347

,285

Male

7524

12.14

4.378

,496

Female

5000

12.45

2.745

,210

Male

7524

10.75

5.025

,4

Author name / Procedia Computer Science 00 (2018) 000–000 Amelec Viloria et al. / Procedia Computer Science 160 (2019) 461–466

4 464

Considering the gender distribution, the results show that male students have obtained better averages in the reflector learning style, compared to female students who obtained higher scores in the theorist, pragmatist, and activist learning styles (see Table 5) [14] [15]. The results show that there is a statistically significant difference between the activist and the pragmatist learning styles of feminine gender compared to masculine gender (see Table 6). Table 5. F-test of Analysis of Variance (ANOVA)

ACTIVIST

REFLECTOR

THEORIST

PRAGMATIST

Sum of squares

gl

Intergroups

182.341

2

half quadratic 181.365

Intragroups

3441.122

388

11.947

Total

3623.851

389

Intergroups

61.685

5

61.685

Intragroups

2946.324

388

10.252

Total

3007.769

289

Intergroups

22.361

8

22.347

Intragroups

4085.663

389

14.196

Total

4107.824

389

Intergroups

362.352

2

362.514

Intragroups

4064.479

387

14.145

Total

4426.931

384

F

Sig.

15.752

,000

6.786

,015

1.856

,212

25.581

,000

Table 6. Descriptive statistics of learning styles Styles

Psychology

Journalism

Arts

History

Philosophy

10.98

Education Sciences 11.68

Activist

12.68

11.70

10.68

9.35

Reflector

14.74

14.96

15.35

14.47

14.74

17.54

Theorist

12.96

12.35

14.47

13.12

11.35

9.67

Pragmatist

12.90

12.25

12.85

13.35

13.47

2.35

By analyzing each style [16] [17], it can be observed that, with regard to the activist style, the highest score was obtained in Psychology students and the lowest score in Philosophy students. Regarding the reflector style, the highest scores were obtained in Philosophy students who were the highest-rated. In relation to the theorist style, the highest scores were observed in Arts and Education Sciences, and the lowest score was obtained in Philosophy. Regarding the pragmatist style, the highest score was observed in Education Sciences and the lowest score in Philosophy.



Author name / Procedia Computer Science 00 (2018) 000–000 Amelec Viloria et al. / Procedia Computer Science 160 (2019) 461–466

5 465

4. Conclusión The results obtained after analyzing the preferences for learning styles of students from different careers allowed to conclude that college students have greater preferences for the reflector learning style followed by the theorist, pragmatist, and activist styles in students from different careers. The overall results show that reflector learning style clearly predominates over all the others in all analyzed careers. Even when a unique learning style was not found, students of Psychology, Education and History coincide in preferring the reflector style followed by the pragmatist, while students of Journalism, Arts, and Philosophy prefer the reflector style, followed by the theorist. In all careers, the lower score was obtained by the activist learning style. In order to establish differences in learning styles of students according to the career, the results show that there are statistically significant differences between activist, theorist and pragmatist learning styles. In relation to the learning style and gender, the results show that male students obtained higher averages in the reflector learning style, while female students obtained higher scores in pragmatist, theorist, and activist styles. In relation to the differences between genders, results show that there is a statistically significant difference between the activist and the pragmatist learning styles for feminine gender compared to the masculine gender. The optimum learning situation requires the combination of all teaching strategies considering the learning styles for obtaining academic excellence. This combination will allow students to enhance their cognitive skills to raise their maximum potential and be successful in their lives and professions. It is important to continue studying on learning styles since they conform a wide field of knowledge that is in constant change and adaptation according to the contents, students, and the context in which they develop. References [1] Ebrahimzadeh, I., Shahraki, A., Shahnaz, A. y Myandoab, A. (2016) Progressing urban development and life quality simultaneously. City, Culture and Society 7, (3), 186-193. 9. [2] Węziak-Białowolska, D. (2016) Quality of life in cities – Empirical evidence in comparative European perspective. Cities, 58, 87-96. 10.Putra, K. y Sitanggang, J. (2016). The Effect of Public Transport Services on Quality of Life in Medan City. Procedia - Social and Behavioral Sciences, 234, 383-389. [3] Pineda Lezama, O., Gómez Dorta, R.: Techniques of multivariate statistical analysis: An application for the Honduran banking sector. Innovate: Journal of Science and Technology, 5 (2), 61-75 (2017). [4] Viloria A., Lis-Gutierrez JP., Gaitán-Angulo M., Godoy A.R.M., Moreno G.C., Kamatkar S.J.: Methodology for the Design of a Student Pattern Recognition Tool to Facilitate the Teaching - Learning Process Through Knowledge Data Discovery (Big Data). In: Tan Y., Shi Y., Tang Q. (eds) Data Mining and Big Data. DMBD 2018. Lecture Notes in Computer Science, vol 10943. Springer, Cham (2018). [5] A Lee, P Taylor, J Kalpathy-Cramer, A Tufail Machine learning has arrived!. Ophthalmology, 124 (2017), pp. 1726-1728 [6] Yao L (2006). The present situation and development tendency of higher education quality evaluation in Western Countries. Priv. Educ. Beef. (2006). [7] Gregorutti B, Michel B, Saint-Pierre P (2015) Grouped variable importance with random forests and application to multiple functional data analysis. Comput Stat Data Anal 90:15–35. [8] Torres-Samuel, M., Vásquez, C., Viloria, A., Lis-Gutiérrez, J.P., Borrero, T.C., Varela, N.: Web Visibility Profiles of Top100 Latin American Universities. In: Tan Y., Shi Y., Tang Q. (eds) Data Mining and Big Data. DMBD 2018. Lecture Notes in Computer Science, Springer, Cham, vol 10943, 1-12 (2018). [9] Jain, A. K., Mao, J., Mohiuddin, K. M.: Artificial neural networks: a tutorial. IEEE Computer 29 (3), 1- 32 (1996) [10] Lee, S.-Y. (2007). Structural equation modeling: A Bayesian approach. West Sussex, England: John Wiley & Sons, Ltd. [11] Haykin, S.: Neural Networks a Comprehensive Foundation. Second Edition. Macmillan College Publishing, Inc. USA. ISBN 9780023527616 (1999). [12] R. Melero y F. Abad, «Revistas Open Access: Características, modelos económicos y tendencias,» Lámpsakos, pp. 12-23, 2001. [13] M. Pinto, J. C. J. Alonso, V. Fernández, C. García, J. Garía, C. Gómez, F. Zazo y A.-V. Doucet, «Análisis cualitativo de la visibilidad de la investigación en las Universidaes españolas a través de su página Web,» Rev. Esp. Doc., pp. 345-370, 2004. [14] M. Torres-Samuel, C. Vásquez, A. Viloria, L. Hernández-Fernandez y R. Portillo-Medina, «Analysis of patterns in the university Word Rankings Webometrics, Shangai, QS and SIR-Scimago: case Latin American» de Lectur Notes in Computer Science (Including subseries Lectur Notes in Artificial Intelligent and Lectur Notes in Bioinformatics, 2018.

6466

Author name / Procedia 00Science (2018) 000–000 Amelec Viloria et al. /Computer Procedia Science Computer 160 (2019) 461–466

[15] C. Vásquez, M. Torres-Samuel, A. Viloria, J. Lis-Gutierrez, T. Crissien, N. Valera, D. Cabrera y M. Gaitán-Angulo, «Efficiency analysis of the visibility of Latin American universities and theri impact on the Ranking Web,» de Lectur Notes in Computer Science (Including subseries Lectur Notes in Artificial Intelligent and Lectur Notes in Bioinformatics), 2018. [16] Wickramarachchi D, Robertson B, Reale M, Price C, Brown J (2016) HHCART: an oblique decision tree. Comput Stat Data Anal 96:12–23. [17] Hong, S., Yang, D., Park, B., et al.: An efficient intra-mode decision method for HEVC. SIViP 10(6), 1–9 (2016).