arXiv subjects

Thomas Fritz

Publications and source records attributed to Thomas Fritz.

4 recordsLinked to original sources

arXiv2026

Exploring a Real-time Feedback Display of Non-Verbal Cues in Online Work Meetings to Support Self-Presentation

Expressing oneself appropriately in online meetings through non-verbal cues can be challenging for knowledge workers. Automatic non-verbal cue detection technologies have the potential to support workers' self-presentation efforts through real-time feedback, but little is known about workers' reactions to and the implications of doing so. We designed and implemented Novecs as a technology probe of a real-time feedback display that automatically detects and signals users' own non-verbal cues -- smiling, nodding, gaze, and posture. Novecs was deployed in an exploratory field study (n=18) to support knowledge workers' self-presentation in their everyday meetings. Post-study interviews reveal how Novecs' real-time feedback helped increase in-the-moment self-awareness, and how neutrally-framed feedback may help navigate tensions between authentic and in-authentic self-presentation. Participants also emphasized the need for natural timing when adjusting non-verbal cues in-meeting. We discuss design opportunities and challenges of real-time, non-verbal cue feedback systems, such as personalizing feedback based on different meeting types.

cs.HC↗

arXiv2026

ChatGPT: Friend or Foe When Comprehending and Changing Unfamiliar Code

A rapidly growing body of research is examining how LLMs influence developers when they code. To date, this research has tended to focus on productivity and code quality outcomes, rather than the underlying cognitive processes involved in programming. To address this gap, we report on the results of an exploratory laboratory study of ten advanced student developers (five with support from AI and five without) who had to make a non-trivial extension to a sizable software system. Leveraging Polya's four problem-solving phases and 25 inductively-generated codes detailing distinct problem-solving behaviors as the primary lenses, we examined: (1) how AI impacted the problem-solving approach the developers used to solve the programming task, and (2) how AI impacted their progress when they became stuck. For the analysis, we triangulated data across multiple sources (e.g., think-aloud, code changes, web searches, and LLM prompts). Unexpectedly, while developers in the AI group repeatedly turned to the AI tool to offload certain aspects of the process, all detailed problem-solving behaviors appeared in both groups. We also found that nine out of ten participants found themselves stuck in their work, but with key differences in how they became stuck and unstuck. We highlight seven distinct causes for being stuck and highlight how AI in some cases helped and in other cases hindered becoming unstuck.

cs.SE↗

arXiv2015

The Making of Cloud Applications An Empirical Study on Software Development for the Cloud

Cloud computing is gaining more and more traction as a deployment and provisioning model for software. While a large body of research already covers how to optimally operate a cloud system, we still lack insights into how professional software engineers actually use clouds, and how the cloud impacts development practices. This paper reports on the first systematic study on how software developers build applications in the cloud. We conducted a mixed-method study, consisting of qualitative interviews of 25 professional developers and a quantitative survey with 294 responses. Our results show that adopting the cloud has a profound impact throughout the software development process, as well as on how developers utilize tools and data in their daily work. Among other things, we found that (1) developers need better means to anticipate runtime problems and rigorously define metrics for improved fault localization and (2) the cloud offers an abundance of operational data, however, developers still often rely on their experience and intuition rather than utilizing metrics. From our findings, we extracted a set of guidelines for cloud development and identified challenges for researchers and tool vendors.

cs.SE↗

arXiv2000

Molecular gas in blue compact dwarf galaxies

Blue compact dwarf galaxies (BCDGs) are currently undergoing strong bursts of star formation. Nevertheless, only a few of them have been clearly detected in CO, which is thought to trace the "fuel" of star formation: H_2. In this paper, we present a deep search for CO J=1-->0 and J=2-->1 emission lines in a sample of 8 BCDGs and two companions. Only 2 of them (Haro 2 and UM 465) are detected. For the other galaxies we have obtained more stringent upper limits on the CO luminosity than published values. We could not confirm the previously reported ``detection'' of CO for the galaxies UM 456 and UM 462. We analyze a possible relation between metallicity, CO luminosity, and absolute blue magnitude of the galaxies. We use previously determined relations between X = N(H_2)/I_CO and the metallicity to derive molecular cloud masses or upper limits for them. With these ``global'' X_CO values we find that for those galaxies which we detect in CO, the molecular gas mass is similar to the HI mass, whereas for the non-detections, the upper limits on the molecular gas masses are significantly lower than the HI mass. Using an LVG (Large Velocity Gradient) model we show that X_CO depends not only on metallicity, but also on other physical parameters such as volume density and kinetic temperature, which rises the question on the validity of ``global'' X_CO factors.

astro-ph↗