Available Workshops

1

Predictive Models to Identify "At-Risk" Students

Mar 22, 2016
  • Chris Brooks (University of Michigan) & Craig Thompson (University of Saskatchewan)

The goal of this workshop is to share data mining tools and techniques used by computer scientists with educational social scientists who seek to expand their knowledge of data-driven tools and techniques. Specifically, attendees will learn how to describe the differences between supervised and unsupervised classification, better understand how to choose a classification method for a particular research question, frame different kinds of educational datasets in a way that is appropriate for data mining, Contextualize the results of a J48 decision tree and k-means clustering and apply knowledge of the Weka toolkit to create decision trees or clusters of new educational datasets. Participants will be expected to bring a laptop and may have to preinstall some software. No experience with data mining is expected.

2

Topic Modeling

Mar 22, 2016
  • Dragan Gašević, Srecko Joksimović, & Vitomir Kovanović (University of Edinburgh)

With the rising amount of data about learning processes, there is a growing need for automated analysis of the large corpora of text that is produced by learners. Among different methods, topic modeling represents a promising approach which is gaining popularity in social science research. Topic modeling enables for the discovery of the hidden themes in the collection of documents revealing important underlying relationships within the document collection. The goal of this workshop is to introduce the area of topic modeling and different algorithms used for topic modeling to a broad community of learning analytics researchers.

3

Data Visualization

Mar 22, 2016
  • Matt Steinwachs (University of California - Davis)

This workshop will be a guided tour of approaches to creating and sharing rich visualizations of learning data. You will learn how to leverage freely available, web-based tools to clean and prepare data, create the best visual representation for the questions you are exploring, and get your visualization to the people who can benefit from it.

4

LearnSphere: Enabling Data Fusion across Diverse Data Sources

Mar 22, 2016
  • Carolyn Rose, John Stamper, & Oliver Ferschke (Carnegie Mellon)

This workshop will introduce learning researchers with diverse data in the form of discourse from discussions or open ended response items, transaction level data from tutoring systems, and/or logfile data from MOOCs to create analytic workflows that fuse these diverse data sources and provide a means to transform, model, and visualize the integrated data. LearnSphere is both a repository and infrastructure designed to enable educators, learning scientists, and researchers to easily collaborate over shared data using the latest tools and technologies. The capabilities of LearnSphere will be illustrated using an exemplar MOOC involving all three types of data sources. Tutorials will alternate with hands-on practice using a combination of web-accessible resources and fully opensource tools.

5

Multimodal Learning Analytics

Mar 22, 2016
  • Xavier Ochoa (Escuela Superior Politécnica del Litoral, Ecuador)

Learning does not only occur over Learning Management Systems or digital tools. It tends to happen in several face-to-face, hands-on, unbounded and analog learning settings such as classrooms and labs. Multimodal Learning Analytics (MLA) emphasizes the analysis of natural rich modalities of communication during situated learning activities. This includes students’ speech, writing, and nonverbal interaction (e.g., movements, gestures, facial expressions, gaze, biometrics, etc.). A primary objective of multimodal learning analytics is to analyze coherent signal, activity, and lexical patterns to understand the learning process and provide feedback to its participants in order to improve the learning experience. This workshop is posed as a gentle introduction to this new approach to Learning Analytics: its promises, its challenges, its tools and methodologies. To follow the same spirit of MLA, this workshop will include a hands-on learning experience analyzing different types of signals captured from real environments.

6

Feature Engineering

Mar 22, 2016
  • Andrew Krumm (SRI) & Joseph Waddington (University of Kentucky)

How can we use system log data to better understand learning and drive more timely and targeted interventions? In this workshop, we will explore how to leverage theory in the development and testing of features, or composite variables, used in statistical or machine learning models. Topics will include data manipulation and blending using R (e.g., dplyr), hierarchical linear modeling, and methods for visualizing features to support end-users (e.g., run charts).

7

Log Analysis

Mar 22, 2016
  • Abelardo Pardo & Kathryn Bartimote-Aufflick (University of Sydney)

The activities in the workshop are oriented to expose you to the typical data processing steps required to go from server logs to data suitable to be manipulated and used for analysis tasks. The objective is to establish a connection between the clickstream and actionable items derived from the data. The target audience are students and instructors that are curious to work with server logs and similar data sources that need processing, cleaning, uploading in a data manipulation platform, and then translated into basic actionable items. We will explore basic cases of visualization and detecting relationships among variables provided by these logs. We will follow a collective intelligence approach in which you get to choose which aspects you want to explore in more depth and then share your insight with the rest of the group.

8

Pathways/ Temporal analysis

Mar 22, 2016
  • Britte Cheng (SRI) & Leah MacFadyen (University of British Columbia)

Interest in temporal analytics - analytics that probe temporal aspects of learning so as to gain insights into the processes through which learning occurs - continues to grow. The study of different temporal patterns (e.g., changes in how students access web resources over time, interact with peers) and their relationship to learning outcomes is a central area of interest. This workshop will present a set of approaches and tools to conduct temporal analytics, including hands-on sessions to apply those approaches with a common data set. Using multiple lenses to analyze a common data set will ground workshop discussions of theoretical and practical issues of various temporal approaches, constructs and patterns that are visible via these approaches, and issues of interpretation and visualization of results that are critical all learning analytics but are particularly challenging for temporal analytics due to their complex and dynamic character.

9

Social network analysis

Mar 22, 2016
  • Sean Goggins (University of Missouri)

Technology mediated learning environments make records of each interaction between students. Course management systems, games for learning, synchronous collaboration systems and other technologies each have different electronic trace data technical characteristics. Understanding how these electronic traces reflect student relationships is more complex than loading them into a social network analysis tool. This workshop will emphasize researcher decision making for using electronic trace data to characterize social structure in technology mediated learning environments; relating that social structure to characteristics of performance; and developing systems that make online social structure visible to students and teachers in useful ways. The SNA approach to electronic trace data will focus on the Group Informatics Model and its related, two-phase methodological approach in detail. Phase one of the methodological approach centers on a set of guiding research questions aimed at directing the application of Group Informatics to new corpora of integrated electronic trace data and qualitative research data. Phase two of the methodological approach is a systematic set of steps for transforming electronic trace data into weighted social networks. We show that the Group Informatics methodological approach is the starting point for important discussions aimed at advancing empirically and theoretically informed analysis of electronic trace data focused on small groups. Group Informatics can also be used as a foundation for pursuing research questions in a range of technology mediated environments where formal and informal learning take place. Participants will learn how to perform SNA technologically; but the frame of that technology use for research is much broader.

10

Wearable & Affective Computing

Mar 22, 2016
  • George Siemens & Catherine Spann (University of Texas - Arlington)

The goal of this workshop is to move data collection activities in learning analytics to broader and more sophisticated approaches. Whereas much of the early LA research used log and clickstream data, wearable technologies such as FitBits, E4s, Apple Watches, and Spires, enable greatly expanded data collection. Heart rate, skin temperature, GSR, movement, heart rate variability, EEG and other approaches offer the creation of new analytics models based on physiological attributes of learners. When combined with discourse, SNA, and other LA techniques, greatly expanded insight into learner affect may be attained. This workshop will provide hands on exploration of wearable technologies as well as review the process of setting up a wearable study, collected and extracting data, and performing analysis on those data.