What do we mean by personalised learning, what does the research tell us and how do we move forward in this area? Join the Computers and Learning Research Group (CALRG) to hear about the latest research from speakers Elizabeth FitzGerald, Garron Hillaire and Alex Mikroyannidis and to discuss how this research can be used to drive personalised learning at the OU.
Venue: Ambient Lab, ground floor, Jennie Lee Building
10.00 Introduction (Eileen Scanlon, LTI-Academic/IET)
10.05 Dimensions of Personalisation in Technology-enhanced Learning: a Framework and Implications for Design (Elizabeth FitzGerald, LTI-Academic/IET)
10.35 Responsive Open Learning Environments (Alexander Mikroyannidis, KMi)
11.05 Emotion and personalized learning experiences (Garron Hillaire, IET)
11.35 Discussion: How can this research be used to support the OU’s new Teaching and Learning Strategy? (Facilitated by Will Woods, LTI)
Everyone is welcome. Abstracts below:
Presentation 1: Dimensions of Personalisation in Technology-enhanced Learning: a Framework and Implications for Design
Elizabeth FitzGerald, LTI-Academic/IET
In this talk, I will present work published recently in a BJET paper of the same title*, that seeks to categorise the way in which personalisation has been – and can be – designed into TEL. In the paper, we proposed a framework encompassing six different dimensions of personalisation, namely:
• what is being personalised
• type of learning
• personal characteristics of the learner
• who/what is doing the personalisation
• how personalisation is carried out
• impact / beneficiaries
In this special CALRG session, I will give examples of how these dimensions have been exemplified in existing TEL projects and also discuss how it might be used in the future to create new TEL interventions, and possibly as part of a more formalised Learning Design process.
*Full reference: FitzGerald, Elizabeth; Kucirkova, Natalia; Jones, Ann; Cross, Simon; Ferguson, Rebecca; Herodotou, Christothea; Hillaire, Garron and Scanlon, Eileen (2017). Dimensions of personalisation in technology-enhanced learning: a framework and implications for design. British Journal of Educational Technology (In press).
ORO link || Available to download from ResearchGate || Official BJET link
Presentation 2: Responsive Open Learning Environments
Alexander Mikroyannidis, KMi
In this talk, I will present the outcomes of four years of educational research in the EU-supported project called ROLE (Responsive Online Learning Environments). ROLE technology is centered around the concept of self-regulated learning that creates responsible learners, who are capable of critical thinking and able to plan their own learning processes. ROLE allows learners to independently search for appropriate learning resources and then reflect on their own learning process and progress. To accomplish this, ROLE’s main objective is to support the development of open personal learning environments (PLEs). ROLE provides a framework consisting of “enabler spaces” on the one hand and tools, content, and services on the other. Utilizing this framework, learners are invited to create their own controlled and preferred learning environments to trigger and motivate self-regulated learning.
Related reference: Kroop, Sylvana; Mikroyannidis, Alexander and Wolpers, Martin eds. (2015). Responsive Open Learning Environments: Outcomes of Research from the ROLE Project. Cham, Switzerland: Springer International Publishing. Open access book available at: http://www.springer.com/gp/book/9783319023984
Presentation 3: Emotion and personalized learning experiences
Garron Hillaire, IET
We are just starting to see emotion emerge in personalised learning experiences (Herold, 2016). A small project proposal from the Open World Learning (OWL) research project outlined the intersection of the focus of two PhD Candidates: Francisco Iniesto’s work on accessibility and Garron Hillaire’s work on emotion. The result was a research question that fits into the category of whole person personalization as outlined in the dimensions of personalisation (Fitzgerald et al., 2017). The core research question was: What would it mean for learning material to be considered emotionally accessible?
From this question the investigation started by examining the emotional delivery of text through the existing accessibility technology of screen readers. A screen reader reads text from text on a computer, like text on a web page, and uses a synthetic voice to generate speech from the text. By using emotion detection software that interprets the prosody of speech screen readers, we examined the variable delivery of text on the dimension of emotion between 2 synthetic voice options on a screen reader technology across text samples from three online courses. The results indicated that the emotional expression did not align with the emotional rating of text as coded by three researchers. A third voice with configurable emotional expression is currently being explored to see if it can provide a malleable emotional delivery that can be better aligned with the emotional content of the text.
In contributing to the emotional personalization work we can look to a recent investigation of 6 case studies (Blanchard, Baker, Ocumpaugh, & Brawner, 2013) on emotional instructional strategies mapped to the modal model of emotion regulation: Situation Selection, Situation Modification, Attentional Deployment, Cognitive Change, & Response Modulation (Gross & Thompson, 2007). By considering how the emotional expression could be used as an emphasis on text this work could connect to the response modulation to emotion in the modal model. This would be similar work to the work being carried out in the AutoTutor research that investigates synthetic voices delivering instructional materials in intelligent tutoring research (D’Mello et al., 2008).
The next proposed step for this investigation is to conduct a pilot study where we interview frequent users of screen readers to both explore how their background knowledge of screen reader voices aligns with the initial finding of emotional variability within voices and to see if voices with intentional expression are detected by people familiar with screen reader technology. While this work is at the early stages, the general research topic or personalized emotion is expected to have impact within the next 10 years (Herold, 2016; Sharples et al., 2015).
Blanchard, N., Baker, R., Ocumpaugh, J., & Brawner, K. (2013). I Feel Your Pain : A Selective Review of Affect-Sensitive Instructional Strategies (pp. 1–16). Montreal, Canada.
D’Mello, S., Jackson, T., Craig, S., Morgan, B., Chipman, P., White, H., … Graesser, A. (2008). AutoTutor Detects and Responds to Learners Affective and Cognitive States. In Workshop on Emotional and Cognitive Issues in ITS held in conjunction with the Ninth International Conference on Intelligent Tutoring Systems. Montreal, Canada.
Fitzgerald, E., Kucirkova, N., Jones, A., Cross, S., Ferguson, R., Herodotou, C., … Hillaire, G. (2017). Dimensions of personalisation in technology-enhanced learning : A framework and implications for design, 0(0). http://doi.org/10.1111/bjet.12534
Gross, J. J., & Thompson, R. A. (2007). Emotion Regulation : Conceptual Foundations. In Handbook of Emotion Regulation (pp. 3–24). New York: Guilford Press.
Herold, B. (2016). Personalized Learning Based on Students’ Emotions : Emerging Research to Know. Retrieved from http://blogs.edweek.org/edweek/DigitalEducation/2016/01/personalized_learning_student_emotion_research.html
Sharples, M., Adams, A., Alozie, N., Ferguson, R., FitzGerald, E., Gaved, M., … Yarnall, L. (2015). Innovating Pedagogy 2015: Open University Innovation Report 4. Milton Keynes.