[on behalf of Collin F. Lynch] The Second International Workshop on: Graph-Based Educational Data Mining (GEDM 2015) https://sites.google.com/a/ncsu.edu/gedm2015/ Held in Conjunction with the 8th International Conference on Educational Data Mining June 26 - June 29, 2015 UNED, Madrid, Spain *** Submission Deadline is April 5th *** Graph data has become increasingly prevalent in data-mining and data analysis. Many types of data can be represented naturally as graphs including social network data, log traversal, and online discussions. Such data has grown exponentially in volume as courses have moved online and educational technology has been incorporated into the traditional classroom. Recent work on tutorial interactions online resource use, and argumentation has highlighted educationally relevant data that lends itself to graphical analysis including: graphical solution representations such as argument diagrams; interaction logs; social networks in learner communities, and online discussion forums. While data of this type has grown increasingly common it has only recently been approached by analysts, and no strong community of researchers focused on graph-based data exists. Such a community is important to foster useful interactions, share tools and techniques, and to explore common problems. This workshop will provide a forum for interested researchers to discuss ongoing work, share lessons learned, and to identify common challenges. Researchers are encouraged to discuss prior analyses of graph data and to demonstrate novel mining techniques. We are also welcome discussions of in-progress work from researchers seeking to identify suitable sources of data or appropriate analytical tools. Our goal in the present workshop is to continue that collaboration and to expand the community of interested researchers to include members of the EDM community. We believe that the problems and techniques discussed previously are relevant to the EDM community. We also believe that the EDM 2015 focus on large-scale data presents an opportunity to address novel problems with the massive datasets under discussion. The advent of large-scale online instruction, the use of online instructional materials and tutoring technologies, and the rise of social media has produced an explosion of graph-based educational data. Analyzing such data can help to answer a range of important questions such as: * What path(s) do high-performing students take through online educational materials? * What social networks can foster or depress learning? * Do users of online learning tools behave as we expect them to do so? * What substructures are commonly found in student-produced diagrams? * Can we use prior student data to identify students' solution plan, if any? * Can we use prior student data to provide meaningful hints in complex domains? * Can we identify students who are particularly helpful in a course? These questions are important to educators and researchers in a variety of domains. All of them can be addressed applying general graph analysis methods to appropriate datasets. And many of these analyses can draw on common graph techniques such as community detection and graph grammars. Our goal in this workshop is to help foster a community of interested researchers who can identify and deploy shared analytical tools and common research questions. We held the first international workshop on Graph-Based Educational Data-Mining at EDM2014 in London. The workshop was a success with over 30 attendees and 12 publications. This workshop will build upon the prior event by providing a forum to present mature work in this area, incorporating group discussions to cover shared issues, and presenting a venue for individual networking and collaboration. Paper Formats ----------------------------------------------------------------- We particularly welcome submission of in-progress work both from students and researchers with problems who are seeking appropriate tools, and developers of graph analysis tools who are seeking new challenges. We will accept long papers, short papers, and poster/demo submissions. All submissions should be novel and not previously published work. Long papers should be from describe mature work and be from 7-8 pages long. Short papers should be 5 pages long and describe planned research; existing datasets that would be amenable to graphical analysis; or data mining tools that are available for use. Poster and demo submissions should be 3 pages and should present an overview of the planned content. Posters and demos should be focused on available datasets and tools and be designed to foster discussion. Papers should be submitted in the EDM 2015 latex and word formats: http://educationaldatamining.org/EDM2015/index.php?page=submission Submission ------------------------------------------------------------------- Papers should be submitted via EasyChair https://easychair.org/conferences/?conf=gedm2015 Organization ------------------------------------------------------------------- The workshop will be organized as a mini-conference with time set aside for short presentations, collaborative discussion, and demos. More information on the presentation formats will be made available once the final submissions are selected. Important Dates -------------------------------------------------------------- 5 April 2015 - Submissions Due. 19 April 2015 - Acceptance notification. 26 April 2015 - Final Paper Due. Sincerely: Dr. Collin F. Lynch, Dr. Tiffany Barnes, Dr. Jennifer Albert, & Michael Eagle.