News
Currently, no news are available
Intelligent Systems and Human Learning (
new advanced lecture
)
Description:
This new advanced lecture introduces various kinds of advanced technologies used to support human learning (e.g., in school classrooms). We will review and critically analyze different techniques, learning science theories and principles, “learning engineering” efforts, and technological features that are embedded in such systems. We will work on a group-based project in which students will conduct an end-to-end cycle of designing, implementing, and testing (via a small experiment or user study) a learning technology for a target goal/domain, guided by the instructor and teaching team. The goal of this lecture is to help you understand core technologies and approaches used in the design/development of learning technologies (that are used in practice) and to equip you with the skills of designing/developing a piece of learning technology and evaluation its effectiveness on learning, engagement, and on related constructs. The course welcomes students with any background (in terms of cultural, racial, disciplinary, and technological) -- we are looking forward to building a community of learners with diverse perspective to engage in deep discussions and hands-on activities.
Lecturer: Prof. Dr. Tomohiro Nagashima (https://tomonag.org/)
Teaching Assistant: Dr. Man "Echo" Su (https://www.mansu.net/)
Tutors: Marjo Toska & Ida Amoli
Location and Time: Tue 12-14 HS002 for the lecture; Thu 12-14 HS003 for the tutorial.
Credit points: 6CP
Learning objectives:
In this course, students will be able to
- 1) critically analyze learning technologies using learning sciences principles
- 2) learn how to conduct a user-centered design of learning technologies, and
- 3) learn how to empirically test the effectiveness of learning technologies through multiple methods.
Prerequisite:
Students will be designing and developing a learning technology (as a group). Therefore students are required to have web-based programming skills and experience. Students will also be testing a learning technology with stakeholders in the form of an experiment or user study -- some basic knowledge of HCI, user studies, experimental design is a plus, but not required. The course is open to any students from any department/faculty/degree programs.
Course structure and schedule:
For most of the weeks during the semester, we will follow the structure below, where we'll begin with reading 2-3 assigned papers, attend the lecture, then tutorial, and submit the assignment by the end of week (there are several weeks without assignments).
Monday | Tuesday | Wednesday | Thursday | Friday | Saturday | Sunday |
Readings due | Lecture | Tutorial | Assignment due |
Detailed, week-by-week course topics and readings will be updated here later, but here are the main topics that will (most likely) be covered in the lecture:
- Cognitive task analysis
- Established instructional strategies that are used in adaptive learning software
- Intelligent tutoring systems
- Cognitive and student modeling, knowledge tracing
- Teachable agents and pedagogical agents
- Data-informed system improvement
- Emotion and learning technology
- Generative AI for teaching and learning
- Multimodal learning technologies
- Participatory design
- User studies (UX methods) and experiments
Grading:
10%: Weekly reflection posts
20%: Mid-term exam/quiz
30%: Weekly individual and group-based assignments
20%: Final project report (individual)
20%: Final presentation (group)
5% bonus: Contributions to discussion during the class
*No final exams are planned
Core activities:
- Attending and engaging in lectures: students are expected to attend the in-person lecture every Tuesday. Lectures (led by Tomo, occasionally Echo) introduce important key concepts, examples, and core knowledge and skills needed to understand the topic. Typically, lecture sessions would start with a 40-50 lecture, followed by hands-on activities to contextualize lecture concepts through tangible learning experiences.
- Attending and engaging in tutorials: students are expected to attend the tutorial sessions every Thursday. Tutorials, led by our teaching assistant and tutors (Echo, Ida, and Marjo) help students better understand key concepts covered in the lecture during the same week, with examples and activities, as well as some extra resources. Tutorials also provide important opportunities where students can spend time working on assignments and individual/group projects and receive help from the teaching team.
- Weekly reflection posts: For every week (except for the first week), students are asked to read 2-3 research papers (not very long) and share a paragraph or two on their thoughts on the papers -- these thoughts can be deep questions, comments relating what they read with their own experience, and/or critiques. Weekly reflection posts help you deeply engage with the readings (which give basic knowledge of the topic covered in the week), which will help you better understand the lecture and tutorial sessions.
- Mid-term exam: In around Week 7 or 8, we will be conducting an open-book mid-term exam, where you will be applying concepts learned in the first half of the lecture to answer some deep questions about intelligent learning systems. More details to come!
- Individual project: In the first half of the lecture, to scaffold students' contextualized understanding of key concepts and to help students practice skills, we will assign a small assignment on designing/developing a piece of learning software. More details to come!
- Group project: After getting familiar with key concepts, skills, and knowledge, which students practice through several small assignments in the first week, during the second half, students will work on a group project in which they will design, develop, and test a learning technology.
- Final presentation/demo: At the end of the lecture, we would have a "demo day" where all the groups will showcase what they have done for the group project.
- Final report: Students will individually reflect on what they have learned in the course and what are some things that they would have done differently.
Readings:
TBD: All readings will be provided .
Notes on respecting teaching team's (and each other's) time:
Every one of you have a busy schedule - balancing coursework, research jobs, tutor jobs, and other responsibilities - and that's same for us. While we try to answer all the questions within 24 hours, we kindly ask you to understand that our response to your questions may sometimes be delayed, especially on weekends.
Accommodations for learning needs and the importance of inclusion:
If you have any needs that require some adjustments for you to succeed in this lecture, please discuss with Tomo in advance, and/or contact the Equal Opportunities and Diversity Unit at UdS: https://www.uni-saarland.de/en/administration/diversity.html Also, it is important that all members of the class feel respected, safe, and valued. I recognize that my ideas and thoughts might be biased based on my training and cultural experiences. Therefore, please let me know if at any time you feel uncomfortable in the class (this also applies to course materials and discussions we will have in the class).