Publication detail

A Methodology for Multimodal Learning Analytics and Flow Experience Identification within Gamified Assignments

PASTUSHENKO, O. OLIVEIRA, W. HRUŠKA, T.

Original Title

A Methodology for Multimodal Learning Analytics and Flow Experience Identification within Gamified Assignments

English Title

A Methodology for Multimodal Learning Analytics and Flow Experience Identification within Gamified Assignments

Type

conference paper

Language

en

Original Abstract

Much research has sought to provide a flow experience for students in gamified educational systems to increase motivation and engagement. However, there is still a lack of quantitative research for evaluating the influence of the flow state on learning outcomes. One of the issues related to flow experience identification is that used techniques are often invasive or not suitable for massive applications. The current paper suggests a way to deal with this challenge. We describe a methodology based on multimodal learning analytics, aimed to provide automatic students flow experience identification in the gamified assignments and measuring its influence on the learning outcomes. The application of the developed methodology showed that there are correlations between learning outcomes and flow state, but they depend on the initial level of the user. This finding suggests adding dynamic difficulty adjustment to the gamified assignment.

English abstract

Much research has sought to provide a flow experience for students in gamified educational systems to increase motivation and engagement. However, there is still a lack of quantitative research for evaluating the influence of the flow state on learning outcomes. One of the issues related to flow experience identification is that used techniques are often invasive or not suitable for massive applications. The current paper suggests a way to deal with this challenge. We describe a methodology based on multimodal learning analytics, aimed to provide automatic students flow experience identification in the gamified assignments and measuring its influence on the learning outcomes. The application of the developed methodology showed that there are correlations between learning outcomes and flow state, but they depend on the initial level of the user. This finding suggests adding dynamic difficulty adjustment to the gamified assignment.

Keywords

gamification, flow theory, multimodal learning analytics, automatic identification, educational systems

Released

25.04.2020

Publisher

Association for Computing Machinery

Location

Honolulu

ISBN

978-1-4503-6819-3

Book

Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

1

Pages to

9

Pages count

9

URL

Documents

BibTex


@inproceedings{BUT168473,
  author="Olena {Pastushenko} and Tomáš {Hruška}",
  title="A Methodology for Multimodal Learning Analytics and Flow Experience Identification within Gamified Assignments",
  annote="Much research has sought to provide a flow experience for students in gamified
educational systems to increase motivation and engagement. However, there is
still a lack of quantitative research for evaluating the influence of the flow
state on learning outcomes. One of the issues related to flow experience
identification is that used techniques are often invasive or not suitable for
massive applications. The current paper suggests a way to deal with this
challenge. We describe a methodology based on multimodal learning analytics,
aimed to provide automatic students flow experience identification in the
gamified assignments and measuring its influence on the learning outcomes. The
application of the developed methodology showed that there are correlations
between learning outcomes and flow state, but they depend on the initial level of
the user. This finding suggests adding dynamic difficulty adjustment to the
gamified assignment.",
  address="Association for Computing Machinery",
  booktitle="Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems",
  chapter="168473",
  doi="10.1145/3334480.3383060",
  edition="NEUVEDEN",
  howpublished="online",
  institution="Association for Computing Machinery",
  year="2020",
  month="april",
  pages="1--9",
  publisher="Association for Computing Machinery",
  type="conference paper"
}