SearcharxivSearch

arXiv subjects

Jinhan Choi

Publications and source records attributed to Jinhan Choi.

2 recordsLinked to original sources

Understanding the Research-Practice Gap in Visualization Design Guidelines

Although empirical research often underpins practical visualization guidelines, it remains unclear how well these research-driven insights are reflected in the guidelines practitioners actually use. In this paper, we investigate the research-practice gap in visualization design guidelines through a mixed-methods approach. We collected 390 design guidelines from practitioner-facing sources and 235 empirical studies to quantitatively assess their alignment. To complement this analysis, we conducted surveys with 69 participants (33 practitioners, 36 researchers) and in-depth interviews with 20 experts to examine their experiences, perceptions, and challenges. Our findings reveal discrepancies: empirical evidence often contradicts or only partially supports widely used guidelines, and the two communities prioritize different attributes of design. Based on these insights, we derive a holistic guideline template (integrating Context, Approach, Problem, and Purpose) and discuss actionable strategies, such as a triadic knowledge model.

cs.HC

The Eyes Have It!: Using Human-Selected Features for Predicting Athletes' Performance

Predicting athletes' performance has relied mostly on statistical data. Besides the traditional data, various types of data, including video, have become available. However, it is challenging to use them for deep learning, especially when the size of the athletes' dataset is small. This research proposes a feature-selection strategy based on the criteria used by insightful people, which could improve ML performance. Our ML model employs features selected by people who correctly evaluated the athletes' future performance. We tested out a strategy to predict the LPGA players' next day performance using their interview video. We asked study participants to predict the players' next day score after watching the interviews and asked why. Using combined features of the facial landmarks' movements, derived from the participants, and meta-data showed a better F1-score than using each feature separately. This study suggests that the human-in-the-loop model could improve algorithms' performance with small-dataset.

cs.HC