WSEEG 2014 - Workshop on Utilizing EEG Input in Intelligent Tutoring Systems

ITS2014 Workshop on Utilizing EEG Input in Intelligent Tutoring Systems
Workshop on Utilizing EEG Input in Intelligent Tutoring Systems
June 5 -AT- Honolulu, Hawaii
12th International Conference on Intelligent Tutoring Systems Workshops
Overview
The ultimate intelligent tutoring system could peer directly into students' minds to identify their mental states (e.g. engagement, cognitive load, competencies, intentions) and decide accordingly what and how to teach at each moment. Recent advances in brain imaging technologies have lead to several portable EEG headsets that are commercially-available and show promise for use in intelligent tutoring systems.
The EEG signal is a voltage signal that can be measured on the surface of the scalp, arising from large areas of coordinated neural activity manifested as synchronization (groups of neurons firing at the same rate). This neural activity varies as a function of development, mental state, and cognitive activity, and the EEG signal can measurably detect such variation. Using signals recorded from low-cost, portable EEG devices, Chang et al. trained machine learning classifiers to detect reading difficulty in an intelligent tutoring systems (Chang, Nelson, Pant, & Mostow, 2013), student confusion while watching course material (Wang, 2013), and user frustration while using a spoken dialog interface (Sridharan, Chen, Chang, & Rudnicky, 2012). Frasson et al. also used EEG to model learners' reactions in ITS (Blanchard, Chalfoun, & Frasson, 2007), detect learners' emotions (Heraz & Frasson, 2007), assess learners' attention (Derbali, Chalfoun, & Frasson, 2011), and more recently to show that subliminal cues were cognitively processed and have positive influence on learners' performance and intuition (Chalfoun & Frasson, 2012; Jraidi, Chalfoun, & Frasson, 2012). Szafir and Mutlu demonstrated that ARTFul, an adaptive review technology for flipped learning that monitors student's attention during educational presentations and adapts reviewing lesson content, can improve student recall abilities by 29% and in less time (Szafir & Mutlu, 2013). Azcarraga and Suarez used a combination of EEG brainwaves and mouse behavior to predict the level of academic emotions, such as confidence, excitement, frustration, and interest (Azcarraga & Suarez, 2012). These early results shows promise for augmenting intelligent tutoring systems with EEG signals.
Advances in EEG-ITS require close collaboration between education researchers, machine learning scientists and computational neuroscientists. To this end, an interdisciplinary workshop can play a key role in advancing existing and initiating new research. Our workshop would be the first of this type to be held at the ITS conference. We hope that it will attract an interdisciplinary target audience consisting of researchers in education, machine learning, and neurosciences.
Topics of Interest
As an unobtrusive measure, EEG has the potential to provide continuous, data-dense, longitudinal measures of mental states without disrupting the flow of instruction, practice, and learning. To the extent that brain operation during these processes is domain-independent, a wide variety of learning contexts can exploit mental state information.
- Education Focus
- Identify cognitive states that are relevant to learning: knowledge state, workload, …
- Identify affective states that affect learning outcome: emotion, attention, engagement, …
- Machine Learning Focus
- Decoding of cognitive states from neural activity
- Feature selection and data mining techniques for decoding cognitive states
- Neural Science Focus
- Experimenting with different brain imaging techniques: from portable, consumer-friendly EEG devices to laboratory EEG, fMRI, MEG, NIRS devices
Important Dates
March 1, 2014: Call for Papers
March 20, 2014: Deadline for submission of workshop papers
April 20, 2014: Notification of acceptance
May 5, 2014: Camera-ready papers due
June 5, 2014: Workshop date
Shared Dataset and Toolkit
Submissions based on any data-sets or tasks are welcomed, and originality of approach is encouraged. However, to assist researchers who are new to this topic, we are providing some EEG data, as well as a toolkit to help process the EEG data. We welcome exploratory or innovative submissions that reveal patterns of correspondence between learning models and brain activity.
This dataset consists of ~3 years of tutor usage data collected in vivo at a primary school. The tutor is Project LISTEN's Reading Tutor and EEG was recorded with NeuroSky BrainBands. The Reading Tutor helps students learn how to read by listening (using Automated Speech Recognition) to them read story aloud. We annotated the time-course of a reading session with the sentence that the student was reading. Our EEG data was recorded using NeuroSky's API. NeuroSky generated 12 channels: Rawwave, PoorSignal (Signal Quality), Delta, Theta, Alpha1, Alpha2, Beta1, Beta2, Gamma1, Gamma2, Attention, and Meditation. Our toolkit is a re-implementation of the pipeline used in Chang et al. with some minor differences. The dataset consists of roughly 169 hours of EEG recording and 200,000 sentences.
Paper Submission
We invite position and research papers that advance theory, methods, practice, and design of intelligent tutoring systems with portable EEG devices. We seek for submission of original (previously unpublished) research papers. The length of the submitted papers should not exceed 6 pages in Springer LNCS format. Submission of previously published work is possible as well, but the authors are required to mention this explicitly. Previously published work can be presented at the workshop, but will not be included into the workshop proceedings (which are considered peer-reviewed publications of novel contributions). Moreover, the authors are welcome to present their novel work but choose to opt out of the workshop proceedings in case they have alternative publication plans.
Schedule
The morning session will begin with a very brief introduction to portable EEG technologies, and computational neuroscience approaches of relevance to ITS. This will be followed by invited talks. The afternoon session will begin with a short introduction/tutorial to the shared task data-sets and the toolkit, followed by selected submissions. The workshop will conclude with an open discussion of future directions.
Organizers
Kai-min Kevin Chang, Carnegie Mellon University, USA
Claude Frasson, University of Montreal, Canada
Program Committee
Judith Azcarraga, De La Salle University, Manila, Philippines
Tiffany Barnes, University of North Carolina at Charlotte, USA
Carole Beal, University of Arizona, USA
Maher Chaouachi, University of Montreal, Canada
Lotfi Derbali, University of Montreal, Canada
Karola Dillenburger, Queen's University Belfast, UK
Imène Jraidi, University of Montreal, Canada
Jack Mostow, Carnegie Mellon University, USA
Brian Murphy, Queen's University Belfast, UK
Bilge Mutlu, University of Wisconsin?Madison, USA
Daniel Sza?r, University of Wisconsin?Madison, USA
Martin Talbot, Warner Bros, Canada
Merlin Teodosia Suarez, De La Salle University, Manila, Philippines
Yanbo Xu, Carnegie Mellon University, USA
Links
Workshop website https://sites.google.com/site/its2014wseeg/
Call for Paper (text version) https://sites.google.com/site/its2014wseeg/textcfp... (Please feel free to distribute the CFP to all the interested persons and groups.)