Abstract
AbstractProgressive visual analytics (PVA) has emerged in recent years to manage the latency of data analysis systems. When analysis is performed progressively, rough estimates of the results are generated quickly and are then improved over time. Analysts can therefore monitor the progression of the results, steer the analysis algorithms, and make early decisions if the estimates provide a convincing picture. In this article, we describe interface design guidelines for helping users understand progressively updating results and make early decisions based on progressive estimates. To illustrate our ideas, we present a prototype PVA tool called InsightsFeed for exploring Twitter data at scale. As validation, we investigate the tradeoffs of our tool when exploring a Twitter dataset in a user study. We report the usage patterns in making early decisions using the user interface, guiding computational methods, and exploring different subsets of the dataset, compared to sequential analysis without progression.
Highlights
While data analysis has scaled dramatically in the last decade, this scalability has only impacted “confirmatory” data analysis, or model-based analysis, i.e. analyses where the structure of the data is known in advance, as well as the best algorithms for this analysis
We focus on the human side of the progressive visual analytics [SPG14] (PVA) paradigm, especially in understanding (1) how visualizations can be adapted to better support PVA, and (2) how the user interface of PVA systems should be designed to provide the feedback and control needed to make early decisions reliably, and its effects on sensemaking
InsightsFeed targets Twitter data, but we consider it a generic PVA system and believe that our study shows how the features within PVA systems play a role in guiding the user in developing early observations, confidence, and steering computations
Summary
While data analysis has scaled dramatically in the last decade, this scalability has only impacted “confirmatory” data analysis, or model-based analysis, i.e. analyses where the structure of the data is known in advance, as well as the best algorithms for this analysis. For exploratory data analysis [Tuk77] and its modern incarnation visual analytics [Tho, KAF∗08], scalability remains limited due to the latency of traditional analysis systems These systems typically yield long response times when analyzing large datasets or when using complex algorithms. To overcome the latency issue, data analysis systems that deliver improving estimates of the results of computations have been introduced [KCL∗17, MPG∗14, PLvdM∗16] These systems engage the analyst during long computational processes by progressively visualizing their intermediate results and supporting interactive exploration by filtering data, as well as changing the parameters of the computation. This approach has been called progressive visual analytics [SPG14] (PVA) and shown to be more effective than traditional sequential (non-progressive) analysis systems for realistic tasks [ZGC∗16]. Many recent research articles have introduced adaptations of algorithms for progressive feedback and steering (e.g. [BP07, PLvdM∗16, SPG14, WM04])
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
