Large Scale Evaluation of Learning Flow

Personalized and adaptive learning is the fastest growing field in e-learning. Adaptive e-learning systems are typically well suited for real-world heterogeneous users, which exhibit different levels of motivation and knowledge. Furthermore, students learn best when they are in flow, i.e. when the level of difficulty is perfectly adjusted to their individual abilities. A personalized, adaptive, and intelligent learning environment can provide each student with this learning experience. In this paper, we present a large-scale evaluation of learning in flow within an adaptive and personalized system, the Adaptemy system. The paper presents the results of two studies: an objective study with 7,614 Irish secondary school students in math classes assessing their learning flow, and a subjective study with 80 students assessing their perceived learning experience. The results from the objective study show that 88% of the students worked within the flow channel. In the subjective study, 70% of students reported a perceived improvement in their math skills after the exercise studying with the adaptive and intelligent learning system.

[1]  Chaoyun Liang,et al.  Is game-based learning better in flow experience and various types of cognitive load than non-game-based learning? Perspective from multimedia and media richness , 2017, Comput. Hum. Behav..

[2]  Di Mascio Tania,et al.  The silent reading supported by adaptive learning technology , 2016 .

[3]  Pedro F. Hernández-Ramos,et al.  How do presence, flow, and character identification affect players' empathy and interest in learning from a serious computer game? , 2016, Comput. Hum. Behav..

[4]  Youngkyun Baek,et al.  Exploring how individual traits influence enjoyment in a mobile learning game , 2017, Comput. Hum. Behav..

[5]  Rosella Gennari,et al.  The silent reading supported by adaptive learning technology: Influence in the children outcomes , 2016, Comput. Hum. Behav..

[6]  Eugenijus Kurilovas,et al.  Recommending suitable learning paths according to learners' preferences: Experimental research results , 2015, Comput. Hum. Behav..

[7]  Teamwork and flow proneness mitigate the negative effect of excess challenge on flow state , 2018 .

[8]  R. D. De Ayala,et al.  An introduction to mixture item response theory models. , 2017, Journal of school psychology.

[9]  M. Csíkszentmihályi.  Beyond boredom and anxiety , 1975 .

[10]  M. Csíkszentmihályi,et al.  The Concept of Flow , 2014 .

[11]  Ioana Ghergulescu,et al.  Learning Effectiveness of Adaptive Learning in Real World Context , 2016 .

[12]  Herman Dwi Herman Dwi.  The Evaluation of a Moodle Based Adaptive e-Learning System , 2014 .

[13]  Edward Palmer,et al.  Personalising learning: Exploring student and teacher perceptions about flexible learning and assessment in a flipped university course , 2015, Comput. Educ..

[14]  K. Kiili.  Digital game-based learning: Towards an experiential gaming model , 2005, Internet High. Educ..

[15]  Boris Aberšek,et al.  TECH8 intelligent and adaptive e-learning system: Integration into Technology and Science classrooms in lower secondary schools , 2015, Comput. Educ..