2024 applications will open in early 2024
Deadline: May 1, 2024
Held in person in Pittsburgh
- When: Monday, July 29, 2024 – Friday, August 2, 2024
- In person: 9 AM to 5 PM EDT in person
- Where: Carnegie Mellon University
- Cost: $950 Professional Fee / $500 for Graduate Students
- Some graduate student scholarships available for full-time graduate students as well as participants focused on computer science education (see application).
- Apply: Will open in early 2024
- Contact: LearnLab Help – email
- New track as of 2023: Computer Science Education Research
- Background Readings can be found here
- Important Dates:
- The deadline for applications is noon (12 PM) EST May 1, 2023.
- Admission decisions will be made by June 12, 2023.
The LearnLab Summer School is an intensive 1-week course focused on creating technology-enhanced learning experiments and building intelligent tutoring systems. The summer school will provide you with a conceptual background and considerable hands-on experience in designing, setting up, and running technology-enhanced learning experiments, as well as analyzing the data from those experiments in a technology-supported manner. Programming experience is not a pre-requisite for attending.
The summer school lasts five days evenly split between lectures and hands-on activities. Each day includes lectures, discussion sessions, and laboratory sessions where the participants work on developing a small prototype experiment in an area of math, science, or language learning. The participants use state-of-the-art tools including but not limited to the Open Learning Initiative (OLI) development environment, Cognitive Tutor Authoring Tools and other tools for course development, tools for authoring natural language dialog, TagHelper tools for semi-automated coding of verbal data, and DataShop for storage of student interaction data and analysis of student knowledge and performance.
On the last day, student teams present their accomplishments to the rest of the participants, Participants are expected to do some preparation before the summer school’s starts.
The summer school is organized into five parallel tracks: Building online courses with OLI (BOLI), Intelligent Tutor Systems development (ITS), Educational Data Mining (EDM), Computational Models of Learning (CML) and (new this year!) Computer Science Education Research (CER). We are particularly encouraging participants that are addressing inequities in education and participants interested in computer science education.
The tracks will overlap somewhat but will differ significantly with respect to the hands-on activities, which make up about half the summer school. Although as a participant you will be assigned to one of the tracks, based on your preferences stated in the application, it will be possible to “shop around” – that is, participate in activities of tracks other than the one to which you have been “officially” assigned. Our primary concern is that the summer school will be a good learning experience for you.
The summer school involves intensive mentoring by LearnLab researchers, which starts by e-mail before the summer school (in order to select a subject domain and task for the project, where appropriate) and continues during the summer school with a good amount of one-on-one time during the hands-on sessions. The mentors are assigned based on your interests as stated in the application. (All participants will have the opportunity to interact with all course instructors, but will interact more frequently with their designated mentor.)
The following researchers are expected to function as mentors and instructors:
The Five Tracks
Computer Science Education Research (CER): In this track, you will learn how to create, improve and evaluate interactive learning content, instructional materials, learning technologies, and analytics for computer science education. You will learn how this design process is informed by existing CER research, and to use your results to further understand how people learn computer science, as well as how to improve their learning. CER is an interdisciplinary field that draws on education research, computer science, psychology, and other related fields to investigate questions related to computer science learning and teaching. For more on CER, see Dr. Amy Ko’s CER FAQ.
We will explore how students learn computer science concepts and skills; explain the impact of different pedagogical approaches on students’ learning and engagement; demonstrate how instrumenting a CS course or module for data driven analysis enables educational data mining to be used as a tool to improve learning; as well as cover methods to reduce barriers to participation and increase diversity.
You might engage in the following:
- Design a novel system or intervention, grounded in educational theory, to improve learning in a CS classroom or informal learning environment.
- Create and evaluate a data-driven algorithm to automate some part of CS instruction (e.g., feedback, or problem selection).
- Design a study to rigorously evaluate an intervention in a CS classroom, using data to better understand how students used and benefited from the intervention.
- Instrument an existing CS learning environment and design analytics to better understand student learning in that environment.
- Apply learning analytic approaches to existing datasets from CS classrooms to answer a research question about how students learn.
Building online courses with OLI – OLI Track: In the OLI (Open Learning Initiative) track, you will focus on elements of effective course design including the connection between learning objectives and learning outcomes. Participants will identify a course module that they would like to create and the expected learning outcomes. Over the course of the week, you will 1) refine your learning outcomes toward making them precise and measurable and 2) develop content, activities, and assessments to support these outcomes. If time permits, you may also develop a plan for completing additional course modules. The modules you create can be used in live classrooms via the OLI platform and improved using data from learner interactions over time. Participants will create OLI courseware and be able to continue to use OLI tools and techniques after the summer session concludes.
This track will offer a two-tiered approach, introducing you to both the underlying pedagogical approach and design philosophy that supports OLI learning experiences and guiding you in the use of the tools and technologies that constitute the OLI platform. Carnegie Mellon’s Open Learning Initiative (OLI) develops online learning environments that integrate research and practice to deliver effective learning experiences while advancing our understanding of how humans learn. OLI technologies combine a standard set of learning activities with the ability to integrate additional education technologies; an OLI course could integrate technologies and approaches from the other Summer School tracks (i.e. incorporating a tutor or collaborative learning experience into a larger learning environment, or using EDM techniques to analyze data from your OLI course).
Computational Models of Learning Track: A key theme of this track will be to explore the relationship between human and machine learning and how each can inform the other. We will provide an overview of techniques for modeling human learning and simulating the behavior of those models to inform theory and instructional design. Attendees will increase their awareness of approaches for building simulated learners and the use cases for these models. This modeling approach provides a new robust way to conceptualize how learning takes place and can guide theory revision based on the fit of models to data. Simulated learners combine work from psychology, cognitive science, and computer science to implement detailed, theory-based learning architectures that can make testable predictions about human behavior. The emphasis will be on prescriptive, generative models of human learning that do not require a priori data. You will build your own generative models of learning to predict and explain human learning and behavior.
EDM (Educational Datamining) Track: If you are in the educational data mining track, your goal will be to analyze an educational dataset using data mining tools and methods. The data set could be one of the data sets currently in LearnLab’s DataShop or you could bring your own. (Best to work this out beforehand with your mentor – see below.) A typical data set would be a detailed record of the interactions that students had with a computer tutor over a (possibly extended) period of time, but other data sets are welcome/interesting too. You will identify a driving question that guides your analysis (quite possibly, one that you were interested in already), such as to understand how students’ strategy use evolves over time, or what aspects of students’ meta-cognitive abilities are related to learning. You will need to familiarize with the data, for example, by playing as a student working through the activities that the data pertain to, operationalize your hypothesis into more detailed analysis questions, run the analysis with various tools (e.g., DataShop, TagHelper, R, SPSS, Weka, RapidMiner, or other relevant packages) and algorithms (e.g., Logistic Regression, exponential-family Principle Component Analysis), interpret the results, and prepare a summary poster presentation.
ITS (Intelligent Tutoring System) Track: In the intelligent tutor system development track, your goal will be to implement a prototype computer-based tutor, using authoring tools developed by LearnLab researchers, such as CTAT (the Cognitive Tutor Authoring Tools) which supports the creation of intelligent tutoring systems. CTAT has been designed for non-programmers. You will be able to use these tools even if you have no programming experience. Depending on your interest, your tutor might be related to a planned or possible experiment (perhaps an in vivo experiment), or it might be related to a tutor development project that you are involved in or are planning to start-up or a course that you are teaching. CTAT-built tutors typically focus on multi-step problem solving as is often found in math, physics, or chemistry, but they are also being applied with increasing success and frequency to language learning, where the exercises presented to students often have smaller granularity. During the week, you will start out by doing some cognitive task analysis to understand the nature of the problems for which your tutor will provide tutoring. Then, depending on your interest, you will use one or more of the tools described above to implement a computer-based tutor. By the end of the week, you will have a prototype running. In fact, if you decide to focus on intelligent tutoring systems development, you will already have implemented some intelligent tutor behavior by the end of day 2 (an Example-Tracing Tutor).