Exploration of student behavior patterns through digital footprints
DOI:
https://doi.org/10.26577/JMMCS-2019-3-25Keywords:
digital footprints, Data Mining, clustering, principal components analysis, R languageAbstract
In this experimental work, a set of Data Mining methods were used to reveal student behavior patterns by analyzing their digital footprints in social Web. Data were gathered from open social profiles of students learning at one of the universities in Kazakhstan. For this case study, 25 publications appeared in the students’ social feeds were selected, and students’ digital footprints (namely, information about their likes on these publications) were fixed. Patterns extracted via analysis of these footprints were compared with the results of psychological tests that were carried out before; and finally, the degree to which both these findings corroborated and complemented each other was assessed. Therefore, conducted experiments provided by R ecosystem demonstrated the potential of proposed methods to analyze digital footprints for the sake of educational analytics. Despite the fact that a very small set of data was used, the case study results are quite illustrative.
References
[2] Weaver S.D. and Gahegan M., "Constructing, visualizing, and analyzing a digital footprint." , Geographical Review vol. 97, no 3 (2007): 324-350.
[3] Kosinski M., et al., "Mining big data to extract patterns and predict real-life outcomes." , Psychological methods vol. 21, no 4 (2016): 493.
[4] Ledovaya Ya., Tikhonov R., Bogolyubova O., "Sotsialnyye seti kak novaya sreda dlya mezhdistsiplinarnykh issledovaniy povedeniya cheloveka [Social networks as a new medium for interdisciplinary research of human behavior]" , Vestnik Sankt-Peterburgskogo universiteta. vol 16. Psihologiya. Pedagogika. vol. 7, no 3 (2017).
[5] Kosinski M., Stillwell D. and Graepel T., "Private traits and attributes are predictable from digital records of human behavior" , Proceedings of the National Academy of Sciences (PNAS). vol. 110, no 15 (2013): 5802-5805.
[6] Hinds J. and Joinson A., "Human and computer personality prediction from digital footprints" , Current Directions in Psychological Science. vol. 2, no 8(2) (2018): 204-211.
[7] McCrae R. R. and Costa P. T., "A five-factor theory of personality. In L. A. Pervin & O. P. John (Eds.)" , Handbook of personality theory and research vol. 2 (1999): 139-153.
[8] Hall J. A., Pennington N. and Lueders A, "Impression management and formation on Facebook: A lens model approach" , New Media & Society. vol. 16, no 6 (2014): 958-982.
[9] Youyou W., Kosinski M. and Stillwell D., "Computer-based personality judgments are more accurate than those made by humans" , Proceedings of the National Academy of Sciences. vol. 112, no 4 (2015): 1036-1040.
[10] Azucar D., Marengo D. and Settanni M., "Predicting the Big 5 personality traits from digital footprints on social media: A meta-analysis" , Personality and individual differences. vol. 124 (2018): 150-159.
[11] Krainikovsky S., Melnikov M. Y. and Samarev R., "Estimation of psychometric data based on image preferences" , WEI. (2019): 75.
[12] Hinds J. and Joinson A.N., "What demographic attributes do our digital footprints reveal? A systematic review" , PloS one. vol. 13, no 11 (2018): e0207112.
[13] Chen Y. J. et al., "Predicting Consumers’ Decision-Making Styles by Analyzing Digital Footprints on Facebook" , International Journal of Information Technology & Decision Making (IJITDM). vol. 18, no 02 (2019): 601-627.
[14] Bechmann A. and Vahlstrup P.B., "Studying Facebook and Instagram data: The Digital Footprints software" , First Monday. vol. 20, no 12 (2015).
[15] Sciandra A., "Social media big data: state of the art of some methodological challenges" , Data Science & Social Research Book of Abstracts. (2019): 117.
