This Week in Learning Analytics (November 22 – 28, 2014)

We're Always Watching Pictured left to right: Ty Ty, Poohie, and Pocket

“We’re Watching You”
Pictured left to right: Ty Ty, Poohie, and Pocket


Student Privacy and Ethics

November 25, 2014
Seattle Public Schools waited days to tell parents of huge student information leak.
While pursuing an administrative claim agains the Seattle School Board, a man accidentally received two large pdf files containing personal information about nearly all of of the district’s special education students. LESSON: Do not send sensitive student information over email.

November 20, 2014
ClassDojo to Offer Fix for Student Data Privacy Issues.
ClassDojo * a student conduct tracking app) has announced that it will only keep children’s behavioral statistics for one school year. The announcement comes amidst criticism sparked as a result of a recent New York Times Article

Industry Updates

November 28, 2014
Find Your Match: Data Companies Transform College Applications.
Parchment, LinkedIn, and Admittedly offer students college matching tools that predict student interest on the basis of GPA, SAT scores, state, race, and other information. Some worry that such tools will oversimplify college decisions, while others point out that these kinds of recommender systems have the ability to connect students with institutions that would not otherwise be on their radar.

Awards and Accolades

November 24, 2014
Tom Enders Nationally Recognized for Visionary Leadership in Student Success.
Thomas Enders, associate vice president of Enrollment Services at Cal State Long Beach (CSULB), has been presented with the Visionary Leadership Award from the Education Advisory Board (EAB), for the work he has done to increase his institution’s first-time freshman six-year graduation rate. Enders results were a consequence of a combination of predictive analytics and the implementation of an ambitious eAdvising initiative.


How to prepare a new kind of classroom teacher by Jill Harvieux Pitner
Increased emphasis is being placed upon incorporating data literacy into American teacher training. Existing approaches to fostering data literacy involve training in data literacy as a decontextualized skill. The Urban Teacher Residency United (UTRU) Assessment and Data Literacy Scope and Sequence seeks to embed training in the use of educational data into all pre-service coursework modules, and in a way that is closely aligned with training in content areas and pedagogy.

Principal uncovers flawed data in her state’s official education reports by Carol Burris
Award-winning Principal Carol Burris of South Side High School in New York comments on problems associated with making significant ‘data-driven’ policy decisions on the basis on poor-quality and incomplete data. ‘Bigger data’ can lead decision-makers into a false sense of certainty that obscures significant gaps. Where decisions have a real impact on the lives and behaviors of people, it is incumbent upon ‘data-driven’ decision-makers to get their priorities straight, and focus on data quality ahead of quantity. It’s time that ‘Big Data’ became ‘Better Data.’

Five Reasons You Shouldn’t Use Technology In The Classroom by Andrew Campbell
The author cites privacy and security concerns as the number one reason why teachers should think twice about incorporating edtech into their classrooms: “My intent is not to prevent or dissuade educators from using EdTech, but rather to ensure more do so. “Non-techy” teachers are smarter than EdTech advocates give them credit for. They know that if something sounds too good to be true, it probably is.”

SOPIPA: A first step towards national standards for student data protection
The author makes a case for federal student privacy standards, along the lines of California’s Student online Personal Information Protection Act (SOPIPA). He identifies several gaps in SOPIPA, but nevertheless upholds the act as an admirable first step, on the road to establishing more universal legislation.



Participation-Based Student Final Performance Prediction Model through Interpretable Genetic Programming: Integrating Learning Analytics, Educational Data Mining and Theory
Wanli Xing, Rui Guo, Eva Petakovic, & Sean Goggins

Building a student performance prediction model that is both practical and understandable for users is a challenging task fraught with confounding factors to collect and measure. Most current prediction models are difficult for teachers to interpret. This poses significant problems for model use (e.g. personalizing education and intervention) as well as model evaluation. In this paper, we synthesize learning analytics approaches, educational data mining (EDM) and HCI theory to explore the development of more usable prediction models and prediction model representations using data from a collaborative geometry problem solving environment: Virtual Math Teams with Geogebra (VMTwG). First, based on theory proposed by Hrastinski (2009) establishing online learning as online participation, we operationalized activity theory to holistically quantify students’ participation in the CSCL (Computer-supported Collaborative Learning) course. As a result, 6 variables, Subject, Rules, Tools, Division of Labor, Community, and Object, are constructed. This analysis of variables prior to the application of a model distinguishes our approach from prior approaches (feature selection, Ad-hoc guesswork etc.). The approach described diminishes data dimensionality and systematically contextualizes data in a semantic background. Secondly, an advanced modeling technique, Genetic Programming (GP), underlies the developed prediction model. We demonstrate how connecting the structure of VMTwG trace data to a theoretical framework and processing that data using the GP algorithmic approach outperforms traditional models in prediction rate and interpretability. Theoretical and practical implications are then discussed.


Learning Analytics: Theoretical Background, Methodology and Expected Results
European Multiple MOOC Aggregator

“Learning analytics in EMMA project will focus on: a) real-time analytics through learning analytics dashboards for instructors and students; b) retrospective analysis of the digital traces in EMMA platform. First approach aims to support participants’ learning activities whereas the second approach is intended for more in-depth analysis of the MOOCs and overall EMMA evaluation. As EMMA is a MOOC platform then calculating the dropout and clustering the participants will be one of the research aims. Additionally uptake of the knowledge, students’ progress and social structures emerging from MOOCs will be analyzed in the pilot phase.

Videos, Presentations, and Webinars

Three Paths for Learning Analytics and Beyond: Moving from Rhetoric to Reality
Colin Beerm Rolley Tickner, & David Jones

Applying Learning Analytics in Serious Games
Baltasar Fernandez-Manjon

Learning Analytics for Holistic Improvement
Ruth Deakin Crick

Calls for Papers / Participation


NEW! Workshop: It’s About Time: 4th International Workshop on Temporal Analyses of Learning Data @LAK15 Poughkeepsie, NY | 16 – 20 March, 2015 (SUBMISSION DEADLINE: 11 January 2015)

EDM 2015: 8th International Conference on Education Data Mining Madrid, Spain | 26 – 29 June, 2015 (SUBMISSION DEADLINE: 12 January 2015)

NEW! Workshop: Ethics and Privacy in Learning Analytics (#EP4LA) @LAK15 Poughkeepsie, NY | 16 – 20 March, 2015 (SUBMISSION DEADLINE: 15 January 2015)

NEW! Workshop: LAK Data Challenge 2015 Poughkeepsie, NY | 16 – 20 March, 2015 (SUBMISSION DEADLINE: 31 January 2015)

EDEN Annual Conference Barcelona, Spain | 9 – 12 June, 2015 (SUBMISSION DEADLINE: 31 January 2015)

NEW! The Fourth International Conference on Data Analytics Poughkeepsie, NY | 19 – 24 July, 2015 (SUBMISSION DEADLINE: 27 February 2015)

Journals / Book Chapters

Universities and Knowledge Society Journal (RUSC): Special Section on Learning Analytics (SUBMISSION DEADLINE: 20 January 2015)

Journal of Learning Analytics: Special Section on Multimodal Learning Analytics (SUBMISSION DEADLINE: 1 March 2015)

Employment Opportunities

Data & Society Research Institute (New York, NY)
Researcher, Enabling Connected Learning – seeking either a full-time or part-time researcher to help drive the research components of this project. Start date is negotiable and the appointment is for two years (with renewal possibilities). Applicants should have a PhD in a social science or related field or significant experience doing similar types of research. Applicants may be postdocs or more advanced researchers. This is a fully funded position with benefits and vacation; salary is dependent on experience. The appointment requires residency in New York. Travel may be necessary, both for conducting the research and for disseminating findings. DEADLINE FOR APPLICATION: Posted Until Filled

Simon Fraser University (Victoria, BC, Canada)
Tenure Track Position In Educational Technology And Learning Design – The Faculty of Education, Simon Fraser University ( seeks applications for a tenure-track position in Educational Technology and Learning Design at the Assistant Professor rank beginning September 1, 2015, or earlier. The successful candidate will join an existing complement of faculty engaged in Educational Technology and Learning Design, and will contribute to teaching and graduate student supervision in our vibrant Masters program at our Surrey campus and PhD program at our Burnaby campus. DEADLINE FOR APPLICATION: December 1, 2014

University at Buffalo (Buffalo, NY, USA)
Associate for Institutional Research/Research Scientist: Online Learning Analytics – The University at Buffalo (UB), State University of New York seeks a scholar in online learning analytics to join its newly formed Center for Educational Innovation. Reporting to the Senior Vice-Provost for Academic Affairs, the Center for Educational Innovation has a mission to support and guide the campus on issues related to teaching, learning and assessment, and at the same time serves as a nexus for campus-wide efforts to further elevate the scholarship of and research support for pedagogical advancement and improved learning. The Research Scientist in online learning analytics will work in the area of Online Learning within the department and join a campus-wide network of faculty and researchers working on “big data”. DEADLINE FOR APPLICATION: December 6, 2014

University of Boulder Colorado (Boulder, Colorado, USA)
Multiple Tenure Track Positions in Computer Science – The openings are targeted at the level of Assistant Professor, although exceptional candidates at higher ranks may be considered. Research areas of particular interest include secure and reliable software systems, numerical optimization and high-performance scientific computing, and network science and machine learning. DEADLINE FOR APPLICATION: Posted Until Filled

University of Technology, Sydney (Sydney, AUS)
Postdoctoral Research Fellow: Academic Writing Analytics – Postdoctoral research position specialising in the use of language technologies to provide learning analytics on the quality of student writing, across diverse levels, genres and domains DEADLINE FOR APPLICATION: Posted Until Filled

University of Michigan (Ann Arbor, MI)
Senior Digital Media Specialist – The University of Michigan is seeking a qualified Senior Digital Media Specialist to create digital content in support of online and residential educational experiences for the Office of Digital Education & Innovation (DEI). DEADLINE FOR APPLICATION: Posted Until Filled

NYU Steinhardt School of Culture, Education,and Human Developments Center for Research on Higher Education Outcomes (USA)
12-month postdoctoral position – available for a qualified and creative individual with interests in postsecondary assessment, learning analytics, data management, and institutional research.The Postdoctoral Fellow will be responsible for promoting the use of institutional data sources and data systems for the purpose of developing institutional assessment tools that can inform decision making and contribute to institutional improvement across New York University (NYU). DEADLINE FOR APPLICATION: Open Until Filled