Improving Argumentation Skill Learning Through Artificial Intelligence

This event will be held in hybrid format. Attenance in-person will be in 3725 Beyster Building. To attend virtually, use:
https://umich.zoom.us/j/97446195922
Meeting ID: 974 4619 5922
Passcode: 888683

Abstract: Argumentation is an omnipresent rudiment of daily communication and thinking. The ability to form convincing arguments is not only fundamental to persuading an audience of novel ideas but also plays a major role in strategic decision-making, negotiation, and constructive civil discourse. However, humans often struggle to develop argumentation skills owing to a lack of individual and instant feedback in their learning process, since providing feedback on the individual argumentation skills of learners is time-consuming and not scalable if conducted manually by educators. Building on self-regulated learning theory, I follow a design oriented research approach to investigate a set of theory-based design principles for a novel class of AI-based argumentation tutoring systems (ATS). The proposed systems provide learners with adaptive self-evaluation opportunities based on logical argumentation errors irrespective of instructor, time, and location. To evaluate the principles’ feasibility, I instantiate, develop, demonstrate, and evaluate three AI-based ATS. I evaluated the novel artifact class in comparison to traditional argumentation learning systems across three empirical studies. As these technologies advance further, I hope my work will support researchers in Natural Language Processing, Human-Computer Interaction and Educational Technology when designing new AI-based skill learning systems to leverage these systems’ full potential for a metacognition skill-based future (continuous) education.

Short biography: Thiemo Wambsganss is a research associate at the Institute of Information Systems at the University of St. Gallen (Switzerland), advised by Prof. Dr. Jan Marco Leimeister. Moreover, since April 2021 Thiemo is a Swiss National Science Foundation (SNSF) fellow and a research collaborator at the Human-Computer Interaction Institute at Carnegie Mellon University, where he is collaborating with Ken Koedinger on adaptive argumentation skill learning. His research interests lie at the intersection of Natural Language Processing (NLP), Human-Computer Interaction (HCI), and Educational Technology. Here, he is primarily driven by the vast opportunities to enhance and improve pedagogical scenarios based on recent advantages in NLP and Machine Learning to enable students to learn when, where, and how they want independent of an educator or their background. To do so, he uses techniques from Artificial Intelligence such as Transfer and Deep Learning to build AI-powered education tools such as Intelligent-Tutoring-Systems, Conversational Agents, and intelligent writing support systems. His publications in the area of Argumentation Writing Support, Empathy Detection, and Pedagogical Conversational Agents are mainly in the areas of HCI (e.g., CHI20, CHI21), NLP (ACL21, COLING20), and Information System (ICIS19, ICS20, ICIS21) and have received several awards, such as the Delina Learntec Award 2021, the Best Theory Paper First Runner-Up Award at ICIS20 or two ACM CHI Honorable Mention Awards. Thiemo completed his bachelor’s and master’s degrees in industrial engineering at the Karlsruhe Institute of Technology (KIT) in Germany, where he immersed himself in applied computer science and data science at an early stage. More information about end-to-end developed educational prototypes and annotated data sets can be found at his website: https://thiemowa.github.io/.