165 citations · 181 across the 6 of their papers we have counts for
5 papers · 1 filter
Sensing What Surveys Miss: Understanding and Personalizing Proactive LLM Support by User Modeling
Ailin Liu, Yesmine Karoui, Fiona Draxler +2
Difficulty spillover and suboptimal help-seeking challenge the sequential, knowledge-intensive nature of digital tasks. In online surveys, tough questions can drain mental energy a…
Physiological and Behavioral Modeling of Stress and Cognitive Load in Web-Based Question Answering
Ailin Liu, Francesco Chiossi, Felix Henninger +5
Time pressure and question difficulty can trigger stress and cognitive overload in web-based surveys, compromising data quality and user experience. Most stress detection methods a…
"If the Machine Is As Good As Me, Then What Use Am I?" -- How the Use of ChatGPT Changes Young Professionals' Perception of Productivity and Accomplishment
Charlotte Kobiella, Yarhy Said Flores López, Fiona Draxler +1
Large language models (LLMs) like ChatGPT have been widely adopted in work contexts. We explore the impact of ChatGPT on young professionals' perception of productivity and sense o…
Useful but Distracting: Keyword Highlights and Time-Synchronization in Captions for Language Learning
Fiona Draxler, Henrike Weingärtner, Maximiliane Windl +2
Captions provide language learners with a scaffold for comprehension and vocabulary acquisition. Past work has proposed several enhancements such as keyword highlights for increase…
The AI Ghostwriter Effect: When Users Do Not Perceive Ownership of AI-Generated Text But Self-Declare as Authors
Fiona Draxler, Anna Werner, Florian Lehmann +4
Human-AI interaction in text production increases complexity in authorship. In two empirical studies (n1 = 30 & n2 = 96), we investigate authorship and ownership in human-AI collab…