arXiv subjects

Fiona Draxler

Publications and source records attributed to Fiona Draxler.

6 recordsLinked to original sources

arXiv2026

Sensing What Surveys Miss: Understanding and Personalizing Proactive LLM Support by User Modeling

Difficulty spillover and suboptimal help-seeking challenge the sequential, knowledge-intensive nature of digital tasks. In online surveys, tough questions can drain mental energy and hurt performance on later questions, while users often fail to recognize when they need assistance or may satisfy, lacking motivation to seek help. We developed a proactive, adaptive system using electrodermal activity and mouse movement to predict when respondents need support. Personalized classifiers with a rule-based threshold adaptation trigger timely LLM-based clarifications and explanations. In a within-subjects study (N=32), aligned-adaptive timing was compared to misaligned-adaptive and random-adaptive controls. Aligned-adaptive assistance improved response accuracy by 21%, reduced false negative rates from 50.9% to 22.9%, and improved perceived efficiency, dependability, and benevolence. Properly timed interventions prevent cascades of degraded responses, showing that aligning support with cognitive states improves both the outcomes and the user experience. This enables more effective, personalized LLM-assisted support in survey-based research.

cs.HC↗

arXiv2026

Physiological and Behavioral Modeling of Stress and Cognitive Load in Web-Based Question Answering

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 are based on low-resolution self-reports, which are poorly suited for capturing fast, moment-to-moment changes during short online tasks. Addressing this gap, we conducted a 2x2 within-subjects study (N = 29), manipulating question difficulty and time pressure in a web-based multiple-choice task. Participants completed general knowledge and cognitive questions while we collected multimodal data: mouse dynamics, eye tracking, electrocardiogram, and electrodermal activity. Using condition-based and self-reported labels, we used statistical and machine learning models to model stress and question difficulty. Our results show distinct physiological and behavioral patterns within very short timeframes. This work demonstrates the feasibility of rapidly detecting cognitive-affective states in digital environments, paving the way for more adaptive, ethical, and user-aware survey interfaces.

cs.HC↗

arXiv2024

"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

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 of accomplishment. We collected LLMs' main use cases in knowledge work through a preliminary study, which served as the basis for a two-week diary study with 21 young professionals reflecting on their ChatGPT use. Findings indicate that ChatGPT enhanced some participants' perceptions of productivity and accomplishment by enabling greater creative output and satisfaction from efficient tool utilization. Others experienced decreased perceived productivity and accomplishment, driven by a diminished sense of ownership, perceived lack of challenge, and mediocre results. We found that the suitability of task delegation to ChatGPT varies strongly depending on the task nature. It's especially suitable for comprehending broad subject domains, generating creative solutions, and uncovering new information. It's less suitable for research tasks due to hallucinations, which necessitate extensive validation.

cs.HC↗

arXiv2023

The AI Ghostwriter Effect: When Users Do Not Perceive Ownership of AI-Generated Text But Self-Declare as Authors

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 collaboration for personalized language generation. We show an AI Ghostwriter Effect: Users do not consider themselves the owners and authors of AI-generated text but refrain from publicly declaring AI authorship. Personalization of AI-generated texts did not impact the AI Ghostwriter Effect, and higher levels of participants' influence on texts increased their sense of ownership. Participants were more likely to attribute ownership to supposedly human ghostwriters than AI ghostwriters, resulting in a higher ownership-authorship discrepancy for human ghostwriters. Rationalizations for authorship in AI ghostwriters and human ghostwriters were similar. We discuss how our findings relate to psychological ownership and human-AI interaction to lay the foundations for adapting authorship frameworks and user interfaces in AI in text-generation tasks.

cs.HC↗

arXiv2023

Gender, Age, and Technology Education Influence the Adoption and Appropriation of LLMs

Large Language Models (LLMs) such as ChatGPT have become increasingly integrated into critical activities of daily life, raising concerns about equitable access and utilization across diverse demographics. This study investigates the usage of LLMs among 1,500 representative US citizens. Remarkably, 42% of participants reported utilizing an LLM. Our findings reveal a gender gap in LLM technology adoption (more male users than female users) with complex interaction patterns regarding age. Technology-related education eliminates the gender gap in our sample. Moreover, expert users are more likely than novices to list professional tasks as typical application scenarios, suggesting discrepancies in effective usage at the workplace. These results underscore the importance of providing education in artificial intelligence in our technology-driven society to promote equitable access to and benefits from LLMs. We urge for both international replication beyond the US and longitudinal observation of adoption.

cs.CY↗

arXiv2023

Useful but Distracting: Keyword Highlights and Time-Synchronization in Captions for Language Learning

Captions provide language learners with a scaffold for comprehension and vocabulary acquisition. Past work has proposed several enhancements such as keyword highlights for increased learning gains. However, little is known about learners' experience with enhanced captions, although this is critical for adoption in everyday life. We conducted a survey and focus group to elicit learner preferences and requirements and implemented a processing pipeline for enhanced captions with keyword highlights, time-synchronized keyword highlights, and keyword captions. A subsequent online study (n = 49) showed that time-synchronized keyword highlights were the preferred design for learning but were perceived as too distracting to replace standard captions in everyday viewing scenarios. We conclude that keyword highlights and time-synchronization are suitable for integrating learning into an entertaining everyday-life activity, but the design should be optimized to provide a more seamless experience.

cs.HC↗