Provenance network analytics: An approach to data analytics using data provenance
Provenance network analytics: An approach to data analytics using data provenance
Provenance network analytics is a novel data analytics approach that helps infer properties of data, such as quality or importance, from their provenance. Instead of analysing application data, which are typically domain-dependent, it analyses the data's provenance as represented using the World Wide Web Consortium's domain-agnostic PROV data model. Specifically, the approach proposes a number of network metrics for provenance data and applies established machine learning techniques over such metrics to build predictive models for some key properties of data. Applying this method to the provenance of real-world data from three different applications, we show that it can successfully identify the owners of provenance documents, assess the quality of crowdsourced data, and identify instructions from chat messages in an alternate-reality game with high levels of accuracy. By so doing, we demonstrate the different ways the proposed provenance network metrics can be used in analysing data, providing the foundation for provenance-based data analytics.
data provenance, data analytics, network metrics, graph classification
Huynh, Trung Dong
ddea6cf3-5a82-4c99-8883-7c31cf22dd36
Ebden, Mark
f46be90b-365e-4ea3-909a-4b92e4287f68
Fischer, Joel
a320ad79-0fb5-464b-9eac-f74918b5ea68
Roberts, Stephen
fef5d01c-92bd-44cf-93f0-923ec24f8875
Moreau, Luc
033c63dd-3fe9-4040-849f-dfccbe0406f8
Huynh, Trung Dong
ddea6cf3-5a82-4c99-8883-7c31cf22dd36
Ebden, Mark
f46be90b-365e-4ea3-909a-4b92e4287f68
Fischer, Joel
a320ad79-0fb5-464b-9eac-f74918b5ea68
Roberts, Stephen
fef5d01c-92bd-44cf-93f0-923ec24f8875
Moreau, Luc
033c63dd-3fe9-4040-849f-dfccbe0406f8
Huynh, Trung Dong, Ebden, Mark, Fischer, Joel, Roberts, Stephen and Moreau, Luc
(2018)
Provenance network analytics: An approach to data analytics using data provenance.
Data Mining and Knowledge Discovery.
(doi:10.1007/s10618-017-0549-3).
Abstract
Provenance network analytics is a novel data analytics approach that helps infer properties of data, such as quality or importance, from their provenance. Instead of analysing application data, which are typically domain-dependent, it analyses the data's provenance as represented using the World Wide Web Consortium's domain-agnostic PROV data model. Specifically, the approach proposes a number of network metrics for provenance data and applies established machine learning techniques over such metrics to build predictive models for some key properties of data. Applying this method to the provenance of real-world data from three different applications, we show that it can successfully identify the owners of provenance documents, assess the quality of crowdsourced data, and identify instructions from chat messages in an alternate-reality game with high levels of accuracy. By so doing, we demonstrate the different ways the proposed provenance network metrics can be used in analysing data, providing the foundation for provenance-based data analytics.
Text
huynh_provanalytics_dmkd_v3.pdf
- Accepted Manuscript
Text
Provenance
- Version of Record
More information
Accepted/In Press date: 26 December 2017
e-pub ahead of print date: 15 February 2018
Keywords:
data provenance, data analytics, network metrics, graph classification
Identifiers
Local EPrints ID: 416917
URI: http://eprints.soton.ac.uk/id/eprint/416917
ISSN: 1384-5810
PURE UUID: 52ba5997-3388-4899-8f24-45ab1a5f6921
Catalogue record
Date deposited: 15 Jan 2018 17:30
Last modified: 16 Mar 2024 06:06
Export record
Altmetrics
Contributors
Author:
Trung Dong Huynh
Author:
Mark Ebden
Author:
Joel Fischer
Author:
Stephen Roberts
Author:
Luc Moreau
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics