learning analytics - george siemens

Learning Analytics:its emergence, trends, and systemic impact

George Siemens

University of Michigan

January 23, 2017

Emergence

❖ A quick background:

❖ LAK11

❖ LASI

❖ JLA

❖ Organizational structure

❖ Also, it’s cold in Banff in February.

The Practice of Analytics in Education

UTA’s University Analytics

UTA Experience

❖ University Analytics

❖ New University Unit of 25 FTE

❖ Data Scientists for Data Mining, Analytics Across the

Campus Academic and Business Enterprise

❖ Learning Innovation and Networked Knowledge (LINK)

Lab

❖ Research Facility of 20 including Faculty, Staff,

Postdocs, and Graduate-level Researchers

Data-Enriched Educational Products

❖ Online courses that enable the constant logging and

tracking of learners through their clickstream data;

❖ E-textbooks that can ‘learn’ from how they are used;

❖ Adaptive learning systems that enable materials to be

tailored to each student’s individual needs through

automated real-time analysis;

As time goes on…

❖ New forms of data analytics that are able to harvest data

from students’ actions, learn from them, and generate

predictions of individual students’ probable future

performances;

❖ Automated personal tutoring software that monitors

students and gives constant real-time support and shapes

the pedagogic experience.

—Mayer-Schönberger & Cukier (2014),

Learning with Big Data: The Future of Education

And emerging today…

❖ New forms of data analytics that are able to harvest

data from students’ affective states, social and cognitive

engagement;

❖ More recently: machine learning drives AI tools such as

chatbots, “smart” discussion fora, automated coaching,

etc.

❖ “Smart Campus UTA”

Behind it all…

❖ …are models and “training

data” for

❖ personal profiles

❖ e-curriculum pathways

❖ models of student activity,

engagement, affective

states

❖ models for natural-language

interaction with learners

What data are feeding our models?

❖ At UTA, primary sources are our Student Information System (SIS)

and Learning Management System (LMS).

❖ Additional Campus Systems: Student Affairs, Library, Housing

and Food Services

❖ Federation of data from neighboring two-year colleges is/will be

taking place.

❖ Expanding Geographical Context: Arlington and the DFW

Metroplex as “Smart Cities”

❖ Later will add live-stream data from research apps or “wearables.”

UA Hardware and Toolsets

❖ Civitas Learning

❖ Multivariate Modeling of Student Persistence, Graduation

❖ IaaS around Student Data

❖ SAS

❖ Visual Analytics

❖ Enterprise Miner

❖ Prediction Suite

❖ Viya Machine Learning/Neural Network Modeling

❖ 450 Core Server Farm (Planned)

UTA “Big Data Questions”

❖ How will big data and new models provide a more complex

understanding of the learner in higher education today?

❖ How can universities use big data to improve student success

(retention and successful progress to graduation)?

❖ Can higher education develop new, more multivariate models of

student engagement? How might these models drive faculty, staff,

and coaches to improve student cognitive and social presence in

formal coursework?

❖ How can we better understand learners of diversity and personalize

the educational experience for engagement and success?

LMS Data in UTA/Civitas Model

Sample Student Persistence Model Output

SAS Toolset

Learning Analytics Maturity Model

Siemens, G., Dawson, S., & Lynch, G. (2013

New Approach(es)

Cope & Kalantzis (2016), “Big Data Comes to School”

NLP Frontier

Intercultural Frontier

Research of Analytics

Projects - Smart Science Network

$5.2M Bill and Melinda Gates Foundation (Co-PI)

linkresearchlab.org/research


BIGDATA: Collaborative Research

$1.6M NSF (Co-PI)


http://linkresearchlab.org/research

Corporate Partnerships

Broadening and expanding the data inputs for LA

Holistic & Integrated

New tools & techniques

Openness, ethics & scope

Broadening scope of data

Siemens, G. (2012)

Working with Santa Fe Institute

Boeing, NASA, Microsoft, Google

Affective and social computing work led by Dr. Catherine

Spann at UTA:

Heart Rate Variability

❖ Vagus nerve is the single most important nerve in the body (Tracey, 2002)

❖ Master regulator: regulates inflammatory processes, glucose regulation, and hypothalamic-pituitary-adrenal (HPA) function (Thayer, Yamamoto, & Brosschot, 2010)

❖ It helps contain acute inflammation and prevents the spread of inflammation to the bloodstream

❖

Tracey, K. J. (2002). The inflammatory reflex. Nature, 420(6917), 853–859.

Thayer, J. F., Yamamoto, S. S., & Brosschot, J. F. (2010). The relationship of autonomic imbalance, heart rate variability and cardiovascular disease risk factors. International Journal of Cardiology,

141(2), 122–131. https://doi.org/10.1016/j.ijcard.2009.09.543

Heart Rate Variability

❖ Attention and Self-Control (Thayer, 2009)

❖ Supports social engagement (Porges, 2011) and mental well-being (Kemp & Quintana, 2013)

❖ Important in longer term physical health (Kemp & Quintana, 2013)

❖ Positive emotions (Geisler et al., 2010 ; Oveis et al., 2009)

❖ Psychological flexibility and resilience (Kashdan & Rottenberg, 2010)

❖ Lower HRV associated with depression and anxiety (Kemp, Quintana, Felmingham, Mathews, & Jelinek, 2012)

❖

Current Study: Self-Control at the Museum

• Methods• Participants

• Museum visitors

• 7 yrs. and older

• Attention and self-control measures• Dimensional Change Card Sort task

• Self-regulation questionnaire

• Self-Assessment Manikin for mood and arousal

• Physiological data (via E4 wristband)• Heart rate variability

• Skin conductance

• Accelerometer

Psychophysiology

❖ “The body is the medium of experience and the

instrument of action. Through its actions we shape and

organize our experiences and distinguish our

perceptions of the outside world from sensations that

arise within the body itself.” (Miller, 1978, p. 14)

Psychophysiology and learning

Mental effort linked to physiological arousal (Hansen et al.,

2003; Luft et al., 2009)

Mental states influence autonomic nervous system (ANS)