You can view the full text of this article for free using the link below.

Title: Supporting user-centred ontology visualisation: predictive analytics using eye gaze to enhance human-ontology interaction

Authors: Bo Fu; Ben Steichen

Addresses: Computer Engineering and Computer Science, California State University Long Beach, 1250 Bellflower Blvd, Long Beach, CA 90840, USA ' Computer Science, California State Polytechnic University Pomona, 3801 W Temple Ave, Pomona, CA 91768, USA

Abstract: Visualisation is an important aspect to support human-ontology interaction, as visual cues amplify cognition and offload cognitive efforts to the human perceptual system. While significant research efforts have focused on visualisation layouts, adapting to the individual user has been largely overlooked in typical ontology visualisation systems. This provides an opportunity to potentially seek more personalised support in ontology visualisation. As such, this paper utilises a tumbling window analytical technique and demonstrates accurate predictions of a user's likelihood to succeed in a given task based on this person's latest gaze data during an interactive session. We show several trial scenarios where statistically significant accuracies are achieved for two commonly used ontology visualisations in the presence of mixed user backgrounds and task domains. In addition, depending on the gaze features that emphasise a user's search or processing activities, or cognitive workload, trial results show earlier predictions as well as higher accuracies can be achieved in some cases. Furthermore, an investigation of influential gaze features reveals a combination of gaze traits is often associated with higher user success. These findings motivate and highlight potentially ample opportunities to adapt to the individual user throughout various interactive stages in the realisation of adaptive ontology visualisation.

Keywords: semantic web; semantic data interaction; predictive analytics; adaptive ontology visualisation; eye tracking; applied machine learning.

DOI: 10.1504/IJIIDS.2022.120143

International Journal of Intelligent Information and Database Systems, 2022 Vol.15 No.1, pp.28 - 56

Received: 10 Nov 2020
Accepted: 15 Jun 2021

Published online: 07 Jan 2022 *

Full-text access for editors Full-text access for subscribers Free access Comment on this article