Learning Analytics Workflow
The Learning Analytics Workflow modules are designed to equip STEM education researchers with the skills to apply these analytical methods to better understand and enhance student learning and educational environments. The modules offer a comprehensive overview of the learning analytics process, starting with the characteristics of educational data and progressing through data visualization, analytical methods, and communication of findings. The presentations, readings, and case studies for each module draw from leading texts, such as Learning Analytics Goes to School (Krumm, Means, and Bienkowski 2018), as well as current research in the field, providing participants with both theoretical knowledge and practical experience. Scholars will engage in hands-on coding exercises using R and Python, tailored to their respective programming preferences, ensuring they gain practical skills in data preparation, visualization, modeling, and communication.
 |
Github |
Repository for Instructors |
 |
Posit Cloud | Workspace for Learners |
Module 1: Characteristics of Data
In Module 1, scholars will learn about different types of learning environments and the characteristics of data commonly used in educational research. The module offers an introduction to the fundamental concepts of learning analytics, tailored for those new to the field or seeking to enhance their basic R or Python programming skills, particularly within STEM education contexts. Scholars will examine various data types, including interaction between instructors and students, administrative and demographic data, and student affectivity, each crucial for developing educational strategies. The hands-on component involves navigating the initial steps of the Learning Analytics workflow, such as preparing data, installing necessary packages, loading data sets, and inspecting data structures. By the end of the module, participants will have a practical understanding of how to apply these concepts through coding exercises, setting the stage for advanced analytical tasks in future modules. The Data Prep badge provides an opportunity to show your skills using the case study data or a choice of data to wrangle using the skills you learned in this module.
 |
Conceptual Overview |
Characteristics of Data in Learning Analytics |
 |
Code Along | Preparing for Research and Wrangling Data in R | Python |
 |
Readings & Reflection |
Chapter 2: Data Used in Educational Data-Intensive Research |
 |
Case Study | The Data-Intensive Research Workflow | R Key | Python Key |
 |
Badge | Foundations of Learning Analytics with R | Python |
 |
Module Survey | Feedback Form After Finishing Module |
Module 2: The Power of Data Viz
In Module 2, scholars explore the vital role of data visualization in learning analytics. This module underscores how visual representations of data can significantly simplify the complexity of educational data, making it more comprehensible and accessible for analysis. Scholars learn to appreciate the benefits of visualization in enhancing understanding, promoting engagement, aiding decision-making, and improving communication. The module covers various types of data visualizations, such as bar charts, line graphs, scatter plots, heatmaps, and network diagrams, each chosen for their effectiveness in illustrating specific data relationships and patterns. Real-world examples are provided to showcase practical applications and the impact of effective data visualization in educational contexts. Best practices are also discussed, emphasizing the importance of knowing the audience, opting for simple designs, choosing the correct types of visualizations, providing contextual clarity, using colors strategically, and iterating based on feedback to refine the visual outputs. The Exploratory LA badge provides an opportunity to show your skills using case study data or your choice of data to visualize using the skills you learned in this module.
 |
Conceptual Overview |
The Power of Data Visualization |
|
Code Along | Exploratory Data Analysis Basics with R | Python |
|
Readings & Reflection |
Chapter 4: Legal and Ethical Issues in Learning Analytics |
|
Case Study | Intro to Exploratory Data Analysis | R Key | Python Key |
 |
Badge | Data Visualization Basics with R | Python |
|
Module Survey | Feedback Form After Finishing Module |
Module 3: Learning Analytics Methods
In Module 3, scholars explore a variety of methods used in learning analytics. The session begins by revisiting basic concepts about the types and characteristics of data in LA. It covers five main analytical methods: predictive analytics, social network analysis, discourse analysis, text analysis, and multimodal analysis. Predictive analytics aims to forecast student performance and enhance intervention strategies. Social network analysis examines social interactions to identify key influencers and optimize collaborative learning. Discourse analysis investigates communication within educational settings to understand student engagement in critical thinking. Text analysis applies natural language processing to assess and provide feedback on text-based assignments. Lastly, multimodal analysis integrates various data sources to provide a comprehensive view of the learning process, supporting personalized educational experiences. This overview equips scholars with the knowledge to apply these methods effectively in educational research and practice. The Modeling badge provides an opportunity to show your skills using case study data or your choice of data to model using the skills you learned in this module.
|
Conceptual Overview |
Methods Used in Learning Analytics |
|
Code Along | Modeling Basics with R | Python |
|
Readings & Discussion |
Chapter 3: Methods Used in Learning Analytics |
|
Case Study | Introduction to Modeling | R Key | Python Key |
 |
Badge | Data Sources in Learning Analytics with R | Python |
|
Module Survey | Feedback Form After Finishing Module |
Module 4: Data Products
In Module 4, scholars will learn to communicate their analytical findings effectively, focusing on creating publication-ready products and considering ethical aspects of data presentation. They will be introduced to strategies for engaging education stakeholders through compelling data storytelling, ensuring the message is clear and accessible. The course also delves into the preparation of various communication mediums using tools like R Markdown and Flexdashboard to model and communicate insights. Additionally, this module emphasizes the importance of addressing ethical considerations such as data privacy, bias, and inclusive practices to ensure responsible use of data in educational settings. This framework prepares scholars to craft their messages thoughtfully, considering both their audience and the ethical dimensions of data use. The Communication badge provides an opportunity to show your skills using case study data or your choice of data to develop a dashboard using the skills you learned in this module.
|
Conceptual Overview |
Communicating with Stakeholder |
|
Code Along | Data Products with R | Python |
|
Readings & Discussion |
Chapter 7: Five Phases of Data-Intensive Improvement |
|
Case Study | Building a Basic Data Dashboard | R Key | Python Key |
 |
Badge | Data Products |
|
Module Survey | Feedback Form After Finishing Module |
Microcredential
The culminating activity for the LAW Modules is designed to provide you some space for independent analysis of a self-identified data source. To earn your LAW Microcredential, you are required to demonstrate your ability to formulate a basic research question appropriate to a social network context, wrangle and analyze relational data, and communicate key findings. Your primary goal for this analysis is to create a simple data product that illustrates key findings by applying the knowledge and skills acquired from the essential readings and case studies.
|
Microcredential | The Learning Analytics Workflow |