Daniel Vogel

Daniel Vogel

Auto-generated profile, based on publicly available information

Daniel Vogel

Cheriton School of Computer Science, University of Waterloo, Waterloo, Ontario, Canada

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 May 2024
Verified
Conference Paper
Open access
DMDamien Masson
Damien Masson
SMSylvain Malacria
Sylvain Malacria
GCGéry Casiez
Géry Casiez
DVDaniel Vogel
Daniel Vogel
We characterize and demonstrate how the principles of direct manipulation can improve interaction with large language models. This includes: continuous representation of generated objects of interest; reuse of prompt syntax in a toolbar of commands; manipulable outputs to compose or control the effect of prompts; and undo mechanisms. This idea is exemplified in DirectGPT, a user interface layer on top of ChatGPT that works by transforming direct manipulation actions to engineered prompts. A study shows participants were 50% faster and relied on 50% fewer and 72% shorter prompts to edit text, code, and vector images compared to baseline ChatGPT. Our work contributes a validated approach to integrate LLMs into traditional software using direct manipulation. Data, code, and demo available at https://osf.io/3wt6s.

1 July 2019 in ACM Transactions on Computer-Human Interaction
Verified
Journal Article
Open access
KHKasper Hornbæk
Kasper Hornbæk
AMAske Mottelson
Aske Mottelson
JKJarrod Knibbe
Jarrod Knibbe
DVDaniel Vogel
Daniel Vogel
The notion of interaction is essential to human-computer interaction, yet rarely studied. We use quantitative and qualitative methods to investigate how this notion has been used across 35 years of proceedings from the ACM Conference on Human Factors in Computing (CHI). Using natural language processing, we extract 53,568 occurrences of the word “interaction” across 4,604 papers. In these occurrences, we categorize 2,668 unique words that modify how “interaction” is used in a sentence. We show that the use of “interaction” is both increasing and diversifying, suggesting the importance of the notion, but also the difficulty in developing theory about interaction. Our findings show that styles of interaction are closely associated with changes in technology and that modalities and characteristics of interaction are becoming more of a topic than specific devices or widgets. Interaction qualities, relating to structure, feel, effectiveness, and efficiency, are consistently prominent, and the quality of novelty is increasingly frequent. From this analysis, we identify open questions about interaction, including how to build knowledge across changing technologies, how to work toward a model of quality for interaction, and what the core of a science of interaction could be.

19 April 2023
Verified
Conference Paper
Open access
DMDamien Masson
Damien Masson
SMSylvain Malacria
Sylvain Malacria
GCGéry Casiez
Géry Casiez
DVDaniel Vogel
Daniel Vogel
Documents often have paragraphs packed with numbers that are difficult to extract, compare, and interpret. To help readers make sense of data in text, we introduce the concept of Charagraphs: dynamically generated interactive charts and annotations for in-situ visualization, comparison, and manipulation of numeric data included within text. Three Charagraph characteristics are defined: leveraging related textual information about data; integrating textual and graphical representations; and interacting at different contexts. We contribute a document viewer to select in-text data; generate and customize Charagraphs; merge and refine a Charagraph using other in-text data; and identify, filter, compare, and sort data synchronized between text and visualization. Results of a study show participants can easily create Charagraphs for diverse examples of data-rich text, and when answering questions about data in text, participants were more correct compared to only reading text.


17 April 2023 in European Neuropsychopharmacology
Verified
Journal Article
Open access
SGSophie Gimbach
Sophie Gimbach
DVDaniel Vogel
Daniel Vogel
RFRoland Fried
Roland Fried
SFStephen V. Faraone
Stephen V. Faraone
TBTobias Banaschewski
Tobias Banaschewski
RARichard Ammer
Richard Ammer
The objective of this study is to quantify the impact of the COVID-19 pandemic on attention deficit hyperactivity disorder (ADHD) medication consumption globally and nationally using pharmaceutical sales data from 2014 to 2021 across 47 countries and regions. A seasonal autoregressive integrated moving average model (SARIMA) was applied to the time series until the end of 2019 at country level and used for the prediction of the ADHD medication consumption in 2020 and 2021. The deviations from the actual to the forecasted sales, which simulate the development without the emergence of COVID-19, yield estimates for the pandemic's impact. In 36 of the 47 countries and regions, the actual sales in 2020 were lower than predicted, with an average relative drop of 6.2% in defined daily doses (DDD) per 1000 inhabitants per day at country-level. In 2021, most countries recorded actually higher ADHD medication use than predicted at the end of 2019. On average, the consumption increased per country by 1.60%. The deviations strongly correlate with the stringency of anti-pandemic government policies. The findings suggest that the pandemic led to a substantially lower consumption of ADHD medication in 2020. However, in 2021 the pandemic had an accelerating effect as the increasing consumption trends are more pronounced than before the pandemic.

19 April 2023
Verified
Conference Paper
Open access
DMDamien Masson
Damien Masson
SMSylvain Malacria
Sylvain Malacria
DVDaniel Vogel
Daniel Vogel
ELEdward Lank
Edward Lank
GCGéry Casiez
Géry Casiez
Extracting underlying data from rasterized charts is tedious and inaccurate; values might be partially occluded or hard to distinguish, and the quality of the image limits the precision of the data being recovered. To address these issues, we introduce a semi-automatic system leveraging vector charts to extract the underlying data easily and accurately. The system is designed to make the most of vector information by relying on a drag-and-drop interface combined with selection, filtering, and previsualization features. A user study showed that participants spent less than 4 minutes to accurately recover data from charts published at CHI with diverse styles, thousands of data points, a combination of different encodings, and elements partially or completely occluded. Compared to other approaches relying on raster images, our tool successfully recovered all data, even when hidden, with a 78% lower relative error.