Update: Data Challenge Now Live!

This year, we are introducing a new activity which attempts to discuss some challenges when doing Data Mining in Computer Science Education. This year's challenge focuses on student modelling of programming data for predicting success. The full description, along with submission requirements can be found here. The winner of the challenge will receive free registration to the workshop (sponsored by CS-SPLICE)!

About the Workshop

Computer Science (CS) has become ubiquitous and is part of everything we do. Studying CS enables us to solve complex, real and challenging problems and make a positive impact in the world we live in.

Yet, the field of CS education is still facing a range of problems from inefficient teaching approaches to the lack of minority students in CS classes and the absence of skilled CS teachers. One of the solutions to these problems lies with effective technology-enhanced learning and teaching approaches, and especially those enhanced with AI-based functionality.

Providing education in Computer Science requires not only specific teaching techniques but also appropriate supporting tools. The number of AI-supported tools for primary, secondary and higher CS education is small and evidence about the integration of AI-supported tools in teaching and learning at various education levels is still rare.

In order to improve our current learning environments and address new challenges we ought to implement new AI techniques, collaborate and share student data footprints in CS. Data is the driving force for innovation at this time and new approaches have been implemented in other fields of innovation and research like Computer Vision and Image Classification. New data-driven learning algorithms and machines to process them are now widely accessible such as Deep Neural Networks and Graphical Processing Units (GPUs).

We want to keep the momentum and support the Computer Science Education community by organizing a workshop focusing on how to mine the rich student digital footprint composed by behavioral logs, backgrounds, assessments and all sort of learning analytics. We aim to create a forum to bring together CS education researchers from adjacent fields (EDM, AIED, CSE) to identify the LAK challenges and issues in the domain-specific field, Computer Science Education.

This workshop will follow on Educational Data Mining in Computer Science Education (CSEDM 2018) and AI-supported Education for Computer Science (AIEDCS) 2013 and 2014 which had an increasing number of participants, submissions and presentations. These workshops and the conferences on this field such as the ACM Technical Symposium on Computer Science Education (SIGCSE) demonstrate the strength of a community that leverages AI techniques to build its innovations.

The workshop encourages contributions from the following topics of interest:

• Predictive student modelling for Computer Science courses and learning
• Adaptation and personalization within Computer Science learning environments
• Intelligent support for collaborative Computer Science problem solving
• Deep learning approaches to massive Computer Science datasets and courses
• Online learning environments for Computer Science: implementation, design and best practices
• Multimodal learning analytics and combination of student data sources in Computer Science Education
• Affective, emotional and motivational aspects related to Computer Science learning
• Explanatory predictive models in Computer Science Education
• Adaptive feedback, adaptive testing for Computer Science learning
• Discourse and dialogue research related to classroom, online, collaborative, or one-on-one learning of Computer Science
• Peer-review, peer-grading and peer-feedback in Computer Science
• Teaching approaches using AI tools
• Visual Learning Analytics and Dashboards for Computer Science
• Learning approaches using AI tools
• Network Analysis for programming learning environments
• Self-Regulated learning for Computer Science environments
• Writing and syntax analysis for programming design learning
• Natural Language Processing for Computer Science forums and discussions
• Analysis of programming design and trajectory paths
• Linked Data for Computer Science knowledge mapping
• Recommender systems and in-course recommendations for Computer Science learning

Submission Guidelines

We invite you to submit your original work for presentation and discussion. There will be three types of submissions, each having their own deadlines:

• 2-4 page* Research Papers (Extended to Dec 13, 2018) addressing any of the topics above. Accepted papers will be published in the LAK Companion Proceedings.
• 2 page* Presentation Abstracts (due Jan 15, 2019). Researchers will present their work at CSEDM in a conversational format. However, these submissions will not be published in the LAK Companion Proceedings. Presentation might include:
  • Descriptions of shareable Computer Science (CS) datasets
  • Descriptions of data mining / analytics approaches applied to specifically Computer Science datasets
  • Descriptions of tools or programming environments that use/produce data
  • Case studies of collaboration where reproducible practices were used to integrate or compose two or more data analysis tools from different teams
  • Descriptions of infrastructures that could collect and integrate data from multiple learning tools (e.g. forum posts, LMS activity and programming data)
  • Calls for Conversation (i.e. Birds of a Feather)
• Dataset Challenge Entries (abstracts due Feb 12, 2019). This year, we are introducing a new activity which attempts to discuss some challenges when doing Data Mining in Computer Science Education. This year's challenge focuses on student modelling of programming data for predicting success. The full description, along with submission requirements can be found here.

*Note: references do not count towards the page limit.

All submissions must be formatted using the Learning Analytics & Knowledge (LAK)'s Companion Proceedings Template.

Submissions are handled via EasyChair.

Important Dates

29 Oct 2018 Open Call for Submissions

13 Dec 2018 Extended: Deadline for Research Paper Submissions

30 Dec 2018 Dataset Challenge Released

04 Jan 2019 Notification of Research Paper Acceptance

15 Jan 2019 Deadline for Presentation Abstracts Submissions

30 Jan 2019 Notification of Presentation Abstracts Acceptance

12 Feb 2019 Abstract Deadline for Dataset Challenge

17 Feb 2019 Paper/Code Deadline for Dataset Challenge

05 Mar 2019 2nd CSEDM Workshop