Evaluation of the Effectiveness of Sonification for Time-series Data Exploration

Abstract

Astronomy is a discipline primarily reliant on visual data. However, alternative data representation techniques are being explored, in particular “sonification,” namely, the representation of data into sound. While there is increasing interest in the astronomical community in using sonification in research and educational contexts, its full potential is still to be explored. This study measured the performance of astronomers and nonastronomers to detect a transit-like feature in time-series data (i.e., light curves), which were represented visually or auditorily, adopting different data-to-sound mappings. We also assessed the bias that participants exhibited in the different conditions. We simulated the data of 160 light curves with different signal-to-noise ratios. We represented them as visual plots or auditory streams with different sound parameters to represent brightness: pitch, duration, or the redundant duration and pitch. We asked the participants to identify the presence of transit-like features in these four conditions in a session that included an equal number of stimuli with and without transit-like features. With auditory stimuli, participants detected transits with performances above the chance level. However, visual stimuli led to overall better performances compared to auditory stimuli and astronomers outperformed nonastronomers. Visualisations led to a conservative response bias (reluctance to answer “yes, there is a transit”), whereas sonifications led to more liberal responses (proneness to respond “yes, there is a transit”). Overall, this study contributes to understanding how different representations (visual or auditory) and sound mappings (pitch, duration, and duration and pitch) of time-series data affect detection accuracy and biases.