BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Designing Adaptive Argumentation Feedback Systems based on Machine
  Learning
DTSTART:20221130T120000
DTEND:20221130T130000
DTSTAMP:20260501T075614Z
UID:c4c7bc906f46a2026144c92a8388e8e0482dcca18a13f877ddcef2f6
CATEGORIES:Conferences - Seminars
DESCRIPTION:Thiemo Wambsganss\nThe EDIC program is happy to invite you to 
 a public talk by our post-doctoral student Thiemo Wambsganss at the Machin
 e Learning for Education Lab at EPFL.\nThe aim of the talk is to present h
 is achievements to a broad audience to prepare for hiring interviews comin
 g up soon.You are warml welcome to listen to the talk and participate in t
 he Q&A session at the end of the presentation.\n\nAbstract\nArgumentation 
 is an omnipresent rudiment of daily communication and thinking. The abilit
 y to form convincing arguments is not only fundamental to persuading an au
 dience of novel ideas but also plays a major role in strategic decision-ma
 king\, negotiation\, and constructive\, civil discourse. However\, humans 
 often struggle to develop argumentation skills owing to a lack of individu
 al and instant feedback in their learning process\, since providing feedba
 ck on the individual argumentation skills of learners is time-consuming an
 d not scalable if conducted manually by educators. To investigate if dynam
 ic technology-mediated argumentation feedback improves persuasive writing\
 , we built a novel dynamic argumentation feedback system based on machine 
 learning (ML). The novel system provides learners with dynamic writing fee
 dback opportunities based on logical argumentation errors irrespective of 
 instructor\, time\, and location. We evaluate our system in two studies to
  test if dynamic argumentation feedback improves persuasive writing perfor
 mance more so than traditional upfront argumentation instruction (H1) and 
 if dynamic feedback on repeated argumentation tasks (over three months) le
 ads to better learning in comparison to static feedback (H2). Our results 
 show that dynamic feedback helps learners to increase their metacognitive 
 argumentation skills across domains compared to the benchmark of upfront i
 nstructions and static feedback. Our research\, thus\, investigates the po
 tential of dynamic feedback tools in a field study to support students to 
 train their skills in large-scale or distance-learning scenarios. This wor
 k can support researchers in designing new skill learning systems based on
  ML to leverage these systems’ full potential not only for information s
 ystems but also for metacognition skill-based future (continuous) educatio
 n.\n\nBio\nThiemo Wambsganss is a PostDoc at the Machine Learning for Educ
 ation Lab at EPFL\, advised by Prof. Dr. Tanja Käser. His research intere
 sts lie at the intersection of Natural Language Processing (NLP)\, Human-C
 omputer Interaction (HCI)\, and Educational Technology. Here\, he is prima
 rily driven by the vast opportunities to enhance and improve pedagogical s
 cenarios based on recent advantages in NLP and\nMachine Learning to enable
  students to learn when\, where\, and how they want independent of an educ
 ator or their background. To do so\, he uses techniques from Artificial In
 telligence such as Transfer and Deep Learning to build AI-powered educatio
 n tools such as Intelligent-Tutoring-Systems\, Conversational Agents\, and
  intelligent writing support systems. His publications in the area of Argu
 mentation Writing Support\, Empathy Detection\, and Pedagogical Conversati
 onal Agents are mainly in the areas of HCI (e.g.\, CHI20\, CHI21\, CHI22)\
 , NLP (ACL21\, ACL22\, COLING22)\, and Information System (ICS20\, ICIS21\
 , ICIS22) and have received several awards\, such as the Delina Learntec A
 ward 2021\, the Best Theory Paper First Runner-Up Award at ICIS20 or two A
 CM CHI Honorable Mention Awards. Thiemo completed his PhD at the Institute
  of Information System at the University of St.Gallen.
LOCATION:BC 410 https://plan.epfl.ch/?room==BC%20410
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR