Toggle Main Menu Toggle Search

Open Access padlockePrints

A customisable pipeline for the semi-automateddiscovery of online activists and social campaigns onTwitter

Lookup NU author(s): Flavio Primo, Professor Alexander Romanovsky, Professor Paolo Missier

Downloads


Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Abstract

Substantial research is available on detecting in influencers on socialmedia platforms. In contrast, comparatively few studies exists on therole of online activists, defi ned informally as users who actively participatein socially-minded online campaigns. Automatically discovering activists whocan potentially be approached by organisations that promote social campaignsis important, but not easy, as they are typically active only locally, and, unlikeinuencers, they are not central to large social media networks. We make thehypothesis that such interesting users can be found on Twitter within temporallyand spatially localised contexts. We de ne these as small but topicalfragments of the network, containing interactions about social events or campaignswith a signi cant online footprint. To explore this hypothesis, we havedesigned an iterative discovery pipeline consisting of two alternating phases ofuser discovery and context discovery. Multiple iterations of the pipeline resultin a growing dataset of user pro les for activists, as well as growing set ofonline social contexts. This mode of exploration differs significantly from priortechniques that focus on in influencers, and presents unique challenges because ofthe weak online signal available to detect activists. The paper describes the designand implementation of the pipeline as a customisable software framework,where user-defined operational definition of online activism can be explored.We present an empirical evaluation on two extensive case studies, one concerninghealthcare-related campaigns in the UK during 2018, the other related toonline activism in Italy during the COVID-19 pandemic.


Publication metadata

Author(s): Primo F, Romanovsky A, de Mello R, Garcia A, Missier P

Publication type: Article

Publication status: Published

Journal: World Wide Web: Internet and Web Information Systems

Year: 2021

Pages: epub ahead of print

Online publication date: 11/06/2021

Acceptance date: 26/04/2021

Date deposited: 26/04/2021

ISSN (print): 1386-145X

ISSN (electronic): 1573-1413

Publisher: Springer

URL: https://doi.org/10.1007/s11280-021-00887-2

DOI: 10.1007/s11280-021-00887-2


Altmetrics

Altmetrics provided by Altmetric


Actions

Find at Newcastle University icon    Link to this publication


Share