DyNetML: Interchange Format for Rich Social Network Data

Tsvetovat, Maksim; Reminga, Jeff; Carley, Kathleen M.

doi:10.2139/ssrn.2729286

Cited by 39 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the topology-specific generation procedure, we ultimately embody the true network in a DyNetML (Tsvetovat, Reminga, & Carley, 2004) formatted data file (optionally held in CPU memory, or persisted via a disk file).…”

Section: Generating the True Networkmentioning

confidence: 99%

See 1 more Smart Citation

Relating Network Topology to the Robustness of Centrality Measures

Frantz

Carley

2005

SSRN Journal

Self Cite

View full text Add to dashboard Cite

This paper reports on a simulation study of social networks that investigated how network topology relates to the robustness of measures of system-level node centrality. This association is important to understand as data collected for social network analysis is often somewhat erroneous and may-to an unknown degree-misrepresent the actual true network. Consequently the values for measures of centrality calculated from the collected network data may also vary somewhat from those of the true network, possibly leading to incorrect suppositions. To explore the robustness, i.e., sensitivity, of network centrality measures in this circumstance, we conduct Monte Carlo experiments whereby we generate an initial network, perturb its copy with a specific type of error, then compare the centrality measures from two instances. We consider the initial network to represent a true network, while the perturbed represents the observed network. We apply a six-factor full-factorial block design for the overall methodology. We vary several control variables (network topology, size and density, as well as error type, form and level) to generate 10,000 samples each from both the set of all possible networks and possible errors within the parameter space. Results show that the topology of the true network can dramatically affect the robustness profile of the centrality measures. We found that across all permutations that cellular networks had a nearly identical profile to that of uniform-random networks, while the core-periphery networks had a considerably different profile. The centrality measures for the core-periphery networks are highly sensitive to small levels of error, relative to uniform and cellular topologies. Except in the case of adding edges, as the error increases, the robustness level for the 3 topologies deteriorate and ultimately converges.

show abstract

Section: Generating the True Networkmentioning

confidence: 99%

“…As with the true network, the observed network is represented in DyNetML (Tsvetovat, Reminga, & Carley, 2004) and stored in computer memory and persisted on computer disk.…”

Section: Generating the Observed Networkmentioning

confidence: 99%

Relating Network Topology to the Robustness of Centrality Measures

Frantz

Carley

2005

SSRN Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…The subset chosen is derived from the specific research questions asked by the clients of this study The metamatrix data is represented by the DyNetML format. DyNetML (Tsvetovat, Reminga, & Carley, 2004) is a computer file format that is increasingly being used for complex social-network studies. DyNetML, as its name suggests, is an XML-based format that has expanded data features beyond other standard network-related data formats.…”

Section: Metamatrixmentioning

confidence: 99%

“…The metamatrix, which followed all associated specifications for formatting and presentation was encapsulated and represented in the form of a DyNetML-formatted (Tsvetovat, Reminga, & Carley, 2004) XML file. This made the faculty metamatrix easily usable in the growing number of social network statistical and simulation tools which incorporate DyNetML.…”

Section: Metamatrix Constructionmentioning

confidence: 99%

An Automated Methodology for Conducting a Social Network Study of a University Faculty

2005

Self Cite

View full text Add to dashboard Cite

This technical report describes the data-collection and analysis methodology used in a socialnetwork study of computer science faculty recently conducted at a top U.S. university. The study involved the construction of a social metanetwork that combines multiple dimensions of the faculty's knowledge, task, and collaborative networks. The process of collecting the source-data, then messaging the data for analysis was completely automated using custom computer software. This allowed for an entirely nonobtrusive data collection process and simplified and repeatable analytic tasks. In this report: we first introduce the metamatrix framework and discuss its utility as a tool for complex network-analysis; next, we describe the data collection methodology; then, we explain metamatrix construction process; and finally we present some closing remarks. This report does not discuss specific analysis or findings of the underlying research, which are regarded as being confidential.

show abstract

“…In Section 2, we define criteria for network representation of distributed, dynamic, uncertain environments, and provide a high level score card that compares representation capabilities of well-known NRLs, alongside enhanced representations such as CoreNetML-developed by Lockheed Martin Advanced Technology Laboratories (LM ATL) as an extension of DyNetML 1.0 (see [4] for an initial description of DyNetML and http://www.casos.cs.cmu.edu/projects/dynetml/ for the 1.0 specification). Next, in Sections 3 and 4, we illustrate how enhanced NRLs can enable dynamic battlefield assessment in a notional system where battlefield observations are input to LM ATL's Core HumAn Network System (CHANS) prototype and updated DyNetML is exported to ORA for rapid analysis of network changes.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Networks: Rapid Assessment of Changing Scenarios

Belov

Martin²,

Patti

et al. 2009

Social Computing and Behavioral Modeling

Self Cite

View full text Add to dashboard Cite

As events unfold, the underlying networks change. Most network science tools, however, assume analysts have a single snapshot of the data, or at most, a second snapshot at a different time. The underlying network representation schemes, assessment technologies, and visualizations do not lend themselves naturally to dynamic networks. Herein, we identify key criteria for network representation of dynamic, uncertain information and present a technology enabler that combines information fusion and dynamic network analysis. The value of technological solutions for network analytics in a dynamic environment are discussed.

show abstract

DyNetML: Interchange Format for Rich Social Network Data

Cited by 39 publications

References 0 publications

Relating Network Topology to the Robustness of Centrality Measures

Relating Network Topology to the Robustness of Centrality Measures

An Automated Methodology for Conducting a Social Network Study of a University Faculty

Dynamic Networks: Rapid Assessment of Changing Scenarios

Contact Info

Product

Resources

About