Collecting and Using Students' Digital Well-Being Data in Multidisciplinary Teaching

Hannu Moilanen, Sami Äyrämö, Susanne Jauhiainen, Marja Kankaanranta, Chei-Chang Chiou

Research output: Contribution to journalArticle

Abstract

This article examines how students (N=198; aged 13 to 17) experienced the new methods for sensor-based learning in multidisciplinary teaching in lower and upper secondary education that combine the use of new sensor technology and learning from self-produced well-being data. The aim was to explore how students perceived new methods from the point of view of their learning and did the teaching methods provide new information that could promote their own well-being. We also aimed to find out how to collect digital well-being data from a large number of students and how the collected big data set can be utilized to predict school success from the students' well-being data by using machine learning methods (lasso regression and multilayer perceptron). Results showed that sensor-based learning can promote students' learning and well-being. All upper secondary school (n=37) and 87% of lower secondary school pupils (n=161) argued that when data are produced by their bodies, learning is more interesting, and they mostly found that well-being analysis was useful (upper secondary 97%; lower secondary 78%) and can improve personal well-being (upper secondary 78%; lower secondary 67%). The predictive powers with lasso regression and multilayer perceptron (MLP) were quite weak (correlation:-0.14 and 0.34, respectively).

Original languageEnglish
Article number3012079
JournalEducation Research International
Volume2018
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

well-being
Teaching
learning
student
secondary school pupil
regression
school success
learning method
secondary education
teaching method
new technology
secondary school

All Science Journal Classification (ASJC) codes

  • Education

Cite this

Moilanen, Hannu ; Äyrämö, Sami ; Jauhiainen, Susanne ; Kankaanranta, Marja ; Chiou, Chei-Chang. / Collecting and Using Students' Digital Well-Being Data in Multidisciplinary Teaching. In: Education Research International. 2018 ; Vol. 2018.
@article{a0f7c50f4bb84bd5be605efebc0307d8,
title = "Collecting and Using Students' Digital Well-Being Data in Multidisciplinary Teaching",
abstract = "This article examines how students (N=198; aged 13 to 17) experienced the new methods for sensor-based learning in multidisciplinary teaching in lower and upper secondary education that combine the use of new sensor technology and learning from self-produced well-being data. The aim was to explore how students perceived new methods from the point of view of their learning and did the teaching methods provide new information that could promote their own well-being. We also aimed to find out how to collect digital well-being data from a large number of students and how the collected big data set can be utilized to predict school success from the students' well-being data by using machine learning methods (lasso regression and multilayer perceptron). Results showed that sensor-based learning can promote students' learning and well-being. All upper secondary school (n=37) and 87{\%} of lower secondary school pupils (n=161) argued that when data are produced by their bodies, learning is more interesting, and they mostly found that well-being analysis was useful (upper secondary 97{\%}; lower secondary 78{\%}) and can improve personal well-being (upper secondary 78{\%}; lower secondary 67{\%}). The predictive powers with lasso regression and multilayer perceptron (MLP) were quite weak (correlation:-0.14 and 0.34, respectively).",
author = "Hannu Moilanen and Sami {\"A}yr{\"a}m{\"o} and Susanne Jauhiainen and Marja Kankaanranta and Chei-Chang Chiou",
year = "2018",
month = "1",
day = "1",
doi = "10.1155/2018/3012079",
language = "English",
volume = "2018",
journal = "Education Research International",
issn = "2090-4002",
publisher = "Hindawi Limited",

}

Collecting and Using Students' Digital Well-Being Data in Multidisciplinary Teaching. / Moilanen, Hannu; Äyrämö, Sami; Jauhiainen, Susanne; Kankaanranta, Marja; Chiou, Chei-Chang.

In: Education Research International, Vol. 2018, 3012079, 01.01.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Collecting and Using Students' Digital Well-Being Data in Multidisciplinary Teaching

AU - Moilanen, Hannu

AU - Äyrämö, Sami

AU - Jauhiainen, Susanne

AU - Kankaanranta, Marja

AU - Chiou, Chei-Chang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This article examines how students (N=198; aged 13 to 17) experienced the new methods for sensor-based learning in multidisciplinary teaching in lower and upper secondary education that combine the use of new sensor technology and learning from self-produced well-being data. The aim was to explore how students perceived new methods from the point of view of their learning and did the teaching methods provide new information that could promote their own well-being. We also aimed to find out how to collect digital well-being data from a large number of students and how the collected big data set can be utilized to predict school success from the students' well-being data by using machine learning methods (lasso regression and multilayer perceptron). Results showed that sensor-based learning can promote students' learning and well-being. All upper secondary school (n=37) and 87% of lower secondary school pupils (n=161) argued that when data are produced by their bodies, learning is more interesting, and they mostly found that well-being analysis was useful (upper secondary 97%; lower secondary 78%) and can improve personal well-being (upper secondary 78%; lower secondary 67%). The predictive powers with lasso regression and multilayer perceptron (MLP) were quite weak (correlation:-0.14 and 0.34, respectively).

AB - This article examines how students (N=198; aged 13 to 17) experienced the new methods for sensor-based learning in multidisciplinary teaching in lower and upper secondary education that combine the use of new sensor technology and learning from self-produced well-being data. The aim was to explore how students perceived new methods from the point of view of their learning and did the teaching methods provide new information that could promote their own well-being. We also aimed to find out how to collect digital well-being data from a large number of students and how the collected big data set can be utilized to predict school success from the students' well-being data by using machine learning methods (lasso regression and multilayer perceptron). Results showed that sensor-based learning can promote students' learning and well-being. All upper secondary school (n=37) and 87% of lower secondary school pupils (n=161) argued that when data are produced by their bodies, learning is more interesting, and they mostly found that well-being analysis was useful (upper secondary 97%; lower secondary 78%) and can improve personal well-being (upper secondary 78%; lower secondary 67%). The predictive powers with lasso regression and multilayer perceptron (MLP) were quite weak (correlation:-0.14 and 0.34, respectively).

UR - http://www.scopus.com/inward/record.url?scp=85060910831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060910831&partnerID=8YFLogxK

U2 - 10.1155/2018/3012079

DO - 10.1155/2018/3012079

M3 - Article

AN - SCOPUS:85060910831

VL - 2018

JO - Education Research International

JF - Education Research International

SN - 2090-4002

M1 - 3012079

ER -