arXiv subjects

Thomas Magelinski

Publications and source records attributed to Thomas Magelinski.

5 recordsLinked to original sources

arXiv2023

Identity-Based Attribute Prototypes Distinguish Communities on Twitter

This paper examines the link between conversational communities on Twitter and their members' expressions of social identity. It specifically tests the presence of community prototypes, or collections of attributes which define a group through meta-contrast: high in-group cohesiveness and high out-group distinctiveness. Analyzing four datasets of political discussions ranging from roughly 4 to 30 million tweets, we find strong evidence for the presence of distinctive community prototypes. We observe that community prototypes are constructed through hashtags, mentions, emojis, and identity-phrases. This finding situates prior work on the identity signaling of individual users within a larger group process playing out within communication communities. Community prototypes are then constructed for specific communities by measuring the salience of identity signals for each community. Observed community prototypes tend to be based on political ideology, location and language, or general interests. While the presence of community prototypes may be a natural group behavior, the high levels of contrast observed between communities displaying ideologically opposed prototypes indicate the presence of identity-related polarization.

cs.SI↗

arXiv2022

Contextualizing Online Conversational Networks

Online social connections occur within a specific conversational context. Prior work in network analysis of social media data attempts to contextualize data through filtering. We propose a method of contextualizing online conversational connections automatically and illustrate this method with Twitter data. Specifically, we detail a graph neural network model capable of representing tweets in a vector space based on their text, hashtags, URLs, and neighboring tweets. Once tweets are represented, clusters of tweets uncover conversational contexts. We apply our method to a dataset with 4.5 million tweets discussing the 2020 US election. We find that even filtered data contains many different conversational contexts, with users engaging in multiple contexts. Central users in the contextualized networks differ significantly from central users in the overall network. This result implies that standard network analysis on social media data can be unreliable in the face of multiple conversational contexts. We further demonstrate that dynamic analysis of conversational contexts gives a qualitative understanding of conversational flow.

cs.SI↗

arXiv2021

A Synchronized Action Framework for Responsible Detection of Coordination on Social Media

The study of coordinated manipulation of conversations on social media has become more prevalent as social media's role in amplifying misinformation, hate, and polarization has come under scrutiny. We discuss the implications of successful coordination detection algorithms based on shifts of power, and consider how responsible coordination detection may be carried out through synchronized action. We then propose a Synchronized Action Framework for detection of automated coordination through construction and analysis of multi-view networks. We validate our framework by examining the Reopen America conversation on Twitter, discovering three coordinated campaigns. We further investigate covert coordination surrounding the protests and find the task to be far more complex than examples seen in prior work, demonstrating the need for our multi-view approach. A cluster of suspicious users is identified and the activity of three members is detailed. These users amplify protest messages using the same hashtags at very similar times, though they all focus on different states. Through this analysis, we emphasize both the potential usefulness of coordination detection algorithms in investigating amplification, and the need for careful and responsible deployment of such tools.

cs.SI↗

arXiv2021

Measuring Node Contribution to Community Structure with Modularity Vitality

Community-aware centrality is an emerging research area in network science concerned with the importance of nodes in relation to community structure. Measures are a function of a network's structure and a given partition. Previous approaches extend classical centrality measures to account for community structure with little connection to community detection theory. In contrast, we propose cluster-quality vitality measures, i.e., modularity vitality, a community-aware measure which is well-grounded in both centrality and community detection theory. Modularity vitality quantifies positive and negative contributions to community structure, which indicate a node's role as a community bridge or hub. We derive a computationally efficient method of calculating modularity vitality for all nodes in O(M + NC) time, where C is the number of communities. We systematically fragment networks by removing central nodes, and find that modularity vitality consistently outperforms existing community-aware centrality measures. Modularity vitality is over 8 times more effective than the next-best method on a million-node infrastructure network. This result does not generalize to social media communication networks, which exhibit extreme robustness to all community-aware centrality attacks. This robustness suggests that user-based interventions to mitigate misinformation diffusion will be ineffective. Finally, we demonstrate that modularity vitality provides a new approach to community-deception.

cs.SI↗

arXiv2019

Graph-Hist: Graph Classification from Latent Feature Histograms With Application to Bot Detection

Neural networks are increasingly used for graph classification in a variety of contexts. Social media is a critical application area in this space, however the characteristics of social media graphs differ from those seen in most popular benchmark datasets. Social networks tend to be large and sparse, while benchmarks are small and dense. Classically, large and sparse networks are analyzed by studying the distribution of local properties. Inspired by this, we introduce Graph-Hist: an end-to-end architecture that extracts a graph's latent local features, bins nodes together along 1-D cross sections of the feature space, and classifies the graph based on this multi-channel histogram. We show that Graph-Hist improves state of the art performance on true social media benchmark datasets, while still performing well on other benchmarks. Finally, we demonstrate Graph-Hist's performance by conducting bot detection in social media. While sophisticated bot and cyborg accounts increasingly evade traditional detection methods, they leave artificial artifacts in their conversational graph that are detected through graph classification. We apply Graph-Hist to classify these conversational graphs. In the process, we confirm that social media graphs are different than most baselines and that Graph-Hist outperforms existing bot-detection models.

cs.LG↗