On 25ht of March 2014 the 2nd workshop at the Learning Analytics & Knowledge Conference 2014, Indianapolis, Indiana, USA took place.
Again we wanted to know what analytics on learning analytics tell us? How can we make sense of this emerging field’s historical roots, current state, and future trends, based on how its members report and debate their research?
The aim of #lakdata14 have been:
- Analysis & assessment of the emerging LAK community in terms of topics, people, citations or connections with other fields
- Innovative applications to explore, navigate and visualize the dataset (and/or its correlation with other datasets)
- Usage of the dataset as part of recommender systems
- Analysis of the evolution of LAK discipline
- Improvement or enrichment of the LAK Dataset
This time we had four high quality submissions that provided new insights into the LAK & EDM dataset.
Introduction slides to the LAK14 data challenge by providing a retrospective of the LAK13 data challenge papers.
Dietze, S., Herder, E., d’Aquin, M., Taibi D., & Drachsler H. (2014). The LAK data challenge, Learning Analytic and Knowledge (LAK14) Indianapolis, Indiana, USA.
The winners were:
FIRST PRIZE: Deconstruct and Reconstruct, Mike Sharkey & Mohammed Ansari Deconstruct and Reconstruct provided some nice insights into the LAK 2014 dataset such as evidence of the merging of the LAK and EDM community, core research topics and their changes over years. The submission hit the core objective of the LAk14 challenge: What do analytics on learning analytics tell us? The various visualizations are meaningful and informative and extend knowledge we gained from the previous LAK data challenge: http://lak14.bluecanarydata.com/
SECOND PRIZE: A linked-data-driven web portal, Yingjie Hu et al.
The linked-data-driven web portal is really very powerful, provides nice visualizations on various objects such as authors, co-authors networks etc., and connects a large amount of datasets. Unfortunately, the level of reported insights by this powerful tool in the paper have been limited: http://stko-exp.geog.ucsb.edu/lak/
Demo:
THIRD PRIZE: Spiral me to the core, Maren Scheffel et al.
A nice visualization, the focus on core concepts make sense and help to explore the LAK key concept in a meaning full manner: http://mitarbeiter.fit.fraunhofer.de/~scheffel/LAKchallenge2014/
FOURTH PRIZE: RecLAK, Giseli Lopes et al.
RecLAK shows analysis of the metadata and recommendations of related datasets. The app demonstrates nicely how the LAK dataset can be extended and connected to other LD sources. A thorough investigation on which data sets can best be used for interlinking with LAK.
The data challenge has been very well appreciated their are plans to extend he current workshop challenge also with a twitter feed analysis of the LAK2011, 2012, 2013 and 2015. A couple of new people indicated their interest to participate in the #lakdata15 next year. The driving idea is to invite all previous submission on an early stage and ask them to present their insights accruing to some Focus Tasks.
Linked Education 