Evaluating Replay Techniques for Asynchronous Task Handover in Immersive Analytics

TL;DR

The results show that the immersive VR replay led to significantly better task comprehension and workflow reconstruction accuracy, demonstrating the critical role of embodied agency in understanding complex analytical processes.

Abstract

Immersive analytics enables collaborative data analysis in shared virtual spaces. While synchronous collaboration in such environments is well-established, real-world analysis often requires an effective task handover - the transfer of knowledge and analytical context between analysts working asynchronously. Traditional handover methods often rely on static annotations that fail to capture the dynamic problem-solving process and spatial context inherent in immersive workflows. To address this handover challenge, we explore session replay as a comprehensive approach for analysts to re-experience a predecessor's work, facilitating a deeper understanding of both the visual details and the insight formation process. Two phases of studies were conducted to establish design guidelines for such replay systems by investigating the impact of viewing platform (PC vs. VR), perspective (first-person vs. third-person), and navigation control (active vs. passive). Phase 1 identified the optimal replay configurations within each viewing platform, revealing a platform-dependent divergence: PC users favored a guided, first-person perspective for its focused detail, while VR users benefited significantly from the agency afforded by a third-person perspective with active navigation. After refining each condition based on user feedback, including developing a novel hybrid 1PP+3PP format for PC, Phase 2 compared the two optimized systems (PC vs. VR). Our results show that the immersive VR replay led to significantly better task comprehension and workflow reconstruction accuracy, demonstrating the critical role of embodied agency in understanding complex analytical processes.

Figures (7)

• Figure 1: Project Procedure Overview. In Phase 1, we identified the best configuration separately from PC and VR. In Phase 2, we first enhanced the conditions by introducing most frequently mentioned features, and then compared the optimized VR and PC conditions.
• Figure 2: The three PC conditions evaluated in Phase 1. 1PP-Passive: A first-person view from the original analyst's perspective with no user interaction. 3PP-Passive: A third-person view that follows the analyst's avatar along a pre-defined spatial trajectory. 3PP-Active: A third-person view that permits viewer-initiated navigation through mouse and keyboard, like some video games.
• Figure 3: The three VR conditions evaluated in Phase 1. 1PP-Passive: A first-person view from the original analyst's perspective with no user interaction. 3PP-Passive: A third-person view that follows the analyst's avatar along a pre-defined spatial trajectory. 3PP-Active: A third-person view that permits viewer-initiated navigation through body movements.
• Figure 4: Average Comprehension and Reconstruction Scores in PC and VR Conditions. * indicates borderline significance ($.05< p<.1$), ** indicate significance ($p<.05$)
• Figure 6: The two conditions evaluated in Phase 2. PC Hybrid (1PP/3PP-Passive): A guided experience where the viewer cannot navigate freely but can instantly switch between 1PP and 3PP. VR (3PP-Active): An embodied experience where the viewer observes from a 3PP and has full navigational control via physical movement. Both conditions were enhanced with user-requested features from Phase 1, including full playback controls and a proximity-based avatar fade-out to mitigate visual occlusion.