Applications of Cohesive Subgraph Detection Algorithms to Analyzing Socio-Technical Networks

Suthers, Dan

doi:10.24251/hicss.2017.258

Cited by 5 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different options exist for detection of sessions in interaction graphs. If interaction is not clearly demarcated by periods of non-interaction and one wishes to discover clusters of high activity, we have found that cohesive subgraph detection or "community detection" algorithms (Fortunato, 2010) such as modularity partitioning (Blondel, Guillaume, Lambiotte, & Lefebvre, 2008) applied to uptake graphs are useful (Suthers, 2017). If (as in our Tapped In data) activity is distributed across rooms and the activity within a room almost always has periods of non-activity between sessions, sessions can be identified efficiently without needing to construct a contingency graph (it can be constructed later for other purposes).…”

Section: Identifying Sessions Of Interactionmentioning

confidence: 99%

The Handbook of Learning Analytics

Gašević¹,

Merceron²

2022

View full text Add to dashboard Cite

Over the last ten years learning analytics (LA) has grown from a hypothetical future into a concrete field of inquiry and a global community of researchers and practitioners. Although the LA space may appear sprawling and complex, there are some clear through-lines that the new student or interested practitioner can use as entry points. Four of these are presented in this chapter, 1. LA as a concern or problem to be solved, 2. LA as an opportunity, 3. LA as field of inquiry and 4. the researchers and practitioners that make up the LA community. These four ways of understanding LA and its associated constructs, technologies, domains and history can hopefully provide a launch pad not only for the other chapters in this handbook but the world of LA in general. A world that, although large, is open to all who hold an interest in data and learning and the complexities that follow from the combination of the two.

show abstract

Section: Identifying Sessions Of Interactionmentioning

confidence: 99%

The Handbook of Learning Analytics

Gašević¹,

Merceron²

2022

View full text Add to dashboard Cite

show abstract

“…In SNA, a network is depicted using a set of nodes and ties (edges) among them (Marin & Wellman, 2010) network. Identification of cohesive subgraphs, commonly known as 'community detection', is used to identify groups of actors that connected with each other than others within networks (Suthers, 2017). Lambiotte, and Lefebvre (2008).…”

Section: Deviations From Basic Tenets Of Media Events: Polymorphism In Networked Eventsmentioning

confidence: 99%

Uptake, polymorphism, and the construction of networked events on Twitter

Rathnayake

2021

Telematics and Informatics

View full text Add to dashboard Cite

This study conceptualises networked events as a platform-oriented view of media events by initiating a taxonomy of bottom-up construction.Focusing on computer-mediated event construction that may involve live delivery, permeate digital platforms, and attract user engagement prior to, during, and after the occurrence of ceremonial or disruptive events, the study argues that networked events can be characterised by polymorphism-i.e., presence of distinct patterns of uptake and different interactional orientations within the same space of interactions, such as hashtags. Using a network dataset of 221,105 tweets that included the hashtag #HimToo which was used extensively during the US Senate judiciary committee hearing that investigated claims of sexual harassment against President Trump's Supreme Court nominee Brett Kavanaugh, the study demonstrates that three types of construction-i.e., actor-centric, memetic, and metaconstruction-causes polymorphism in Twitter engagement related to the event.

show abstract

“…One such algorithm is the Louvain method (Blondel, Guillaume, Lambiotte, & Lefebvre, 2008). The Louvain method performs well on benchmarks (Barabási, 2016) and can identify clusters that are interpretable in terms of social activity (Suthers, 2017;Suthers, Fusco, Schank, Chu, & Schlager, 2013). Another strong contender, InfoMap (Rosvall, Axelsson, & Bergstrom, 2009) is an information theoretic approach based on the metaphor of defining the most compact "map" to describe an ergodic random walk in the graph.…”

Section: Polymorphismmentioning

confidence: 99%

Twitter Issue Response Hashtags as Affordances for Momentary Connectedness

Rathnayake

Suthers

2018

Social Media + Society

View full text Add to dashboard Cite

Framing online collective behavior within theoretical frameworks developed to describe offline phenomena is common in social media studies. This can limit the scope of analysis because the interplay between user capabilities, intentions, and platform architecture makes online exchanges different from offline interaction. We introduce a novel conception of online publicness, momentary connectedness, which is a structure of polymorphic computer-mediated sociality that includes transactive as well as non-transactive phenomenological online activity. We suggest that Twitter issue-response hashtags can be seen as affordances for momentary connectedness where Tweets that display broad and vague audience dimensions, as well as clusters with different interactional orientations, co-exist within the same topical network. We illustrate this polymorphism of momentary connectedness with a case study of an issue-response network.

show abstract

Applications of Cohesive Subgraph Detection Algorithms to Analyzing Socio-Technical Networks

Abstract: Abstract

Cited by 5 publications

References 23 publications

The Handbook of Learning Analytics

The Handbook of Learning Analytics

Uptake, polymorphism, and the construction of networked events on Twitter

Twitter Issue Response Hashtags as Affordances for Momentary Connectedness

Contact Info

Product

Resources

About