Progressive analytics

The place where data and human-computer interaction scientists can meet to tackle important problems related to human and algorithm coupling.

• 

  PAPM: Progressive Analytics and Pattern Mining

  Data Visualization Interpretation Systems Progressive analytics

  The project concentrates on the main difficulty of interactive mining, which is not post-mining interaction, nor pre-interaction mining, rather interaction and mining occurring at the same time. We focus on interaction for progressive analytics, our application is in progressive pattern mining of frequent event sequences of user activity traces.

  Details

  Partners: LS2N
  Funding: PhD funding
  Beginning: 2015-10-01
  End: 2018-12-31
  

  Related publications

  • Vincent Raveneau, Julien Blanchard, Yannick Prié. (2018) Progressive sequential pattern mining: steerable visual exploration of patterns with PPMT in Visualization in Data Science (VDS at IEEE VIS 2018), Berlin, Germany, 2018. [AR:30%] Show abstract The progressive visual analytics (PVA) paradigm has been proposed to describe visual analytics systems whose main goal is to reach a thorough coupling between the analyst and her system by getting rid of waiting periods classically encountered during data processing. PVA systems use algorithms that both provide intermediate results throughout their execution, and are steerable by the analyst to change the strategy used to perform the remaining computation. Our focus is on progressive sequential pattern mining, as in the seminal work of Stolper et al. (2014). Here we go further mainly by considering the temporal nature of patterns related to their occurrences. We propose a pattern-oriented data model, a pattern analysis task model, and guidelines for designing progressive pattern mining algorithms. We introduce PPMT, a tool to support an analyst progressively explore activity traces, based on a modification of the GSP algorithm. We evaluate our proposal on the technical performances of our progressive algorithm, and on the effect of steering on analysts' performances.
  • Vincent Raveneau, Julien Blanchard, Yannick Prié. (2016) Towards an open-source tool for pattern-based progressive analytics on interaction traces in Workshop "Event Event" at IEEE VIS 2016, Baltimore. 3p. Show abstract Due to the ever increasing use of data analysis tools, their performance has become an important scientific question, notably regarding the tools’ ability to assist the analyst using them. We present our first proposals toward building a data analysis tool allowing an analyst to interact with his pattern mining algorithm, while working with interaction traces. First, we present an architecture for such a system, based on the ideas of progressive analytics. We then present our work toward a first implementation of this architecture
  • Katy Tcha-Tokey, Toinon Vigier, Yannick Prié. (2016) Towards an Affordance-Based Approach for Scenario Modeling and Experience Assessment in VR in IEEE VIS 2016, Baltimore. oct. 2016. 2p (Poster) Show abstract Due to the ever increasing use of data analysis tools, their performance has become an important scientific question, notably regarding the tools’ ability to assist the analyst using them. We present our first proposals toward building a data analysis tool allowing an analyst to interact with his data mining algorithm, while working with interaction traces. First, we present an architecture for such a system, based on the ideas of progressive analytics. We then present the challenges that will need to be faced in future work.

  Related software

  • PPMT

  Additional illustrations

  

Select another theme:    Accessibility Affordances Data Visualization Digital Instruments Document Engineering Experience analysis and modelling Hypervideos Immersive Analytics Interpretation Systems Knowledge Engineering Learning Analytics Patient Experience Progressive analytics Reflective Systems Technology-Enhanced Learning Trace-based Activity Analysis Trace-based Systems VR and Psychotherapy Video Annotations Virtual Reality