[on behalf of Nia Dowell]
Dear Colleagues,
I would like to invite you to contribute to the following special issue for
the Journal of Learning Analytics (JLA).
*Title*: Collaboration Analytics
<https://epress.lib.uts.edu.au/journals/index.php/JLA/announcement/view/157>
*GUEST EDITORS*
- Bertrand Schneider, Harvard University, USA.
- Kate Thompson, Queensland University of Technology, Australia.
- Nia Dowell, University of California Irvine, USA.
*TIMELINE*
- *April 10, 2020: Deadline to submit papers*
- July, 2020: First round of reviews returned to authors
- Sept 2020: Resubmissions due from authors
- Dec 2020: Second (final) round of reviews returned to authors
- Jan 2021: Final editorial decisions
- Spring 2021: Anticipated Publication
*AIMS & SCOPE*
Innovation is vital for economic competitiveness, quality of life, and
national security. This has resulted in an increasing reliance on both
physical and virtual teams and their collaborative efforts, to solve
complex environmental, social and public health problems (Fiore, Graesser,
& Greiff, 2018). To contend with these dynamic conditions, collaborative
competencies have taken a principal role in educational policy, research,
and technology (Graesser et al., 2018). The availability of naturally
occurring educational data within existing and emerging collaborative
environments presents a unique opportunity to make significant advances in
our understanding of learners’ social, cognitive and affective interaction
dynamics and collaborative ecologies.
We invite contributions to a special issue of the Journal of Learning
Analytics (JLA) on Collaboration Analytics. The goal of this special issue
is to build upon promising multimodal sensing technologies, collaborative
tools and emerging data analytics techniques to provide researchers with a
new lens for understanding human collaboration in a variety of settings.
Recent developments in data collection techniques now allow researchers and
practitioners to collect vast amounts of process data on small groups -
from click streams to multimodal sensor data (Blikstein & Worsley, 2016),
including eye-tracking, natural language processing, motion sensing, or
physiological data. This opens new doors to both better understand
collaborative mechanisms, and support them in a rigorous and data-driven
fashion (Wise & Schwarz, 2017). These opportunities are at the core of this
special issue: how can fine-grained data from small groups be leveraged to
1) design better models of collaboration; 2) support interactions between
students (e.g., through awareness tools); 3) design innovative ways of
teaching collaborative skills, and 4) contribute to theory building (e.g.,
by expanding current frameworks)? These new opportunities have the
potential to radically change research on small groups in education, and in
the social sciences more generally.
Collecting additional types of data in new contexts to explore social
interactions between students, however, brings new challenges. Data privacy
and ethics has become a central topic in the learning analytics community
(and beyond), particularly when the data is shared between students within
a group, but also because the data collected is from students in learning
situations which can be challenging, frustrating, and involves students in
vulnerable situations. The quality of the data is also a major concern,
when “cheap” data is easily available this can influence researchers to
focus on less relevant constructs (without leveraging existing learning
theories, see concerns raised by Wise & Shaffer, 2015), and common
standards for collecting and reporting on learning data do not currently
exist. Finally, new approaches also come with new biases (O'Neil, 2016),
from black box models that are fine-tuned for specific samples of students
and underperform for others, to researchers’ attention being drawn to
incomplete or misleading information (i.e., street light effect - Ochoa &
Worsley, 2016). These challenges are of special interest for this special
issue, especially for contributions that tackle them directly in the
context of small groups.
*TOPICS OF INTEREST*
We welcome contributions from various settings, including: empirical (lab)
studies, online platforms, and ecological settings (e.g., classrooms,
informal learning environments, workplaces). Possible foci of the
submissions include, but are not limited to the following:
- *From data to constructs:* innovative methods for capturing
educational constructs of interest related to students’ collaboration.
- *Leveraging new data streams:* new ways of capturing collaboration
constructs, for example using multimodal sensor data (e.g., eye-tracking,
motion, physiological, etc.)
- *Computational models:* submissions that use new computational
algorithms to model collaboration, using various data streams
- *Interventionist studies:* work that goes beyond describing
collaboration and uses data analytics to support collaboration
- *Contribution to theory:* frameworks or empirical work that employ
collaboration analytics to contribute to theory building
- *Ethics and privacy:* considerations of users’ privacy and ethics
when using collaborative analytics in real-world settings, and how it might
prevent adoption (e.g., Kitto & Knight, 2019)
*SUBMISSION INSTRUCTIONS*
Prospective authors may contact the section editors with queries. Final
submissions will take place through JLA’s online submission system at
http://learning-analytics.info When submitting a paper, select the section
“Special Section: Collaboration Analytics". All submissions should follow
JLA’s standard manuscript guidelines and template available on the journal
website, and will undergo double-blind peer review.
*Contact Information*:
For questions regarding the special issue please contact the
coordinators: *bertrand_schneider@xxxxxxxxxxxxx
<bertrand_schneider@xxxxxxxxxxxxx>*, *k46.thompson@xxxxxxxxxx
<k46.thompson@xxxxxxxxxx>* and *nia.dowell@xxxxxxx <nia.dowell@xxxxxxx>*
--
*Guest Editor* for a Special Section on Collaboration Analytics in the
Journal of Learning Analytics [ CfP
<https://epress.lib.uts.edu.au/journals/index.php/JLA/announcement/view/157>
]
Nia Marcia Maria Dowell
Assistant Professor
School of Education <http://education.uci.edu>
EDUC 3361A
University of California, Irvine
Google Scholar
<https://scholar.google.com/citations?user=lIBxWgsAAAAJ&hl=en> | @NiaDowell
<https://twitter.com/NiaDowell>| niadowell.com