Search

Contrary to expectations that the increased connectivity offered by the internet and particularly Online Social Networks (OSNs) would result in broad consensus on contentious issues, we instead frequently observe the formation of polarised echo chambers, in which only one side of an argument is entertained. These can progress to filter bubbles, actively filtering contrasting opinions, resulting in vulnerability to misinformation and increased polarisation on social and political issues. These have real-world effects when they spread offline, such as vaccine hesitation and violence. This work seeks to develop a better understanding of how echo chambers manifest in different discussions dealing with different issues over an extended period of time. We explore the activities of two groups of polarised accounts across three Twitter discussions in the Australian context. We found Australian Twitter accounts arguing against marriage equality in 2017 were more likely to support the notion that arsonists were the primary cause of the 2019/2020 Australian bushfires, and those supporting marriage equality argued against that arson narrative. We also found strong evidence that the stance people took on marriage equality in 2017 did not predict their political stance in discussions around the Australian federal election two years later. Although mostly isolated from each other, we observe that in certain situations the polarised groups may interact with the broader community, which offers hope that the echo chambers may be reduced with concerted outreach to members.

During Australia's unprecedented bushfires in 2019-2020, misinformation blaming arson resurfaced on Twitter using #ArsonEmergency. The extent to which bots were responsible for disseminating and amplifying this misinformation has received scrutiny in the media and academic research. Here we study Twitter communities spreading this misinformation during the population-level event, and investigate the role of online communities and bots. Our in-depth investigation of the dynamics of the discussion uses a phased approach -- before and after reporting of bots promoting the hashtag was broadcast by the mainstream media. Though we did not find many bots, the most bot-like accounts were social bots, which present as genuine humans. Further, we distilled meaningful quantitative differences between two polarised communities in the Twitter discussion, resulting in the following insights. First, Supporters of the arson narrative promoted misinformation by engaging others directly with replies and mentions using hashtags and links to external sources. In response, Opposers retweeted fact-based articles and official information. Second, Supporters were embedded throughout their interaction networks, but Opposers obtained high centrality more efficiently despite their peripheral positions. By the last phase, Opposers and unaffiliated accounts appeared to coordinate, potentially reaching a broader audience. Finally, unaffiliated accounts shared the same URLs as Opposers over Supporters by a ratio of 9:1 in the last phase, having shared mostly Supporter URLs in the first phase. This foiled Supporters' efforts, highlighting the value of exposing misinformation campaigns. We speculate that the communication strategies observed here could be discoverable in other misinformation-related discussions and could inform counter-strategies., Comment: 80 pages, 29 figures. Submitted to the International Journal of Social Network Analysis and Mining (SNAM) expanding upon DOI:10.1007/978-3-030-61841-4_11. arXiv admin note: text overlap with arXiv:2004.00742

Current network-based methods for detecting coordinated inauthentic behaviour on social media focus primarily on inferring links between accounts based on common "behavioural traces" [19], such as retweeting the same tweet or posting the same URL. Assuming the goal of coordination is amplification, boosting a message within a constrained period, most approaches use a temporal window to ensure the co-activity occurs within a specific timeframe [9, 14, 19, 24]. Real-world application requires considering near real-time processing, creating performance requirements, which also highlight gaps in the semantics of coordination in the literature. These methods could all exploit temporal elements of coordinated activity. We describe preliminary research regarding coordination network semantics, coordination network construction, relevant observations in three political Twitter datasets and the role of cheerleaders in revealing social bots., Comment: 14 pages, 10 figures, 2 tables, prepared for the 4th Multidisciplinary International Symposium on Disinformation in Open Online Media (MISDOOM'22)

To study the effects of Online Social Network (OSN) activity on real-world offline events, researchers need access to OSN data, the reliability of which has particular implications for social network analysis. This relates not only to the completeness of any collected dataset, but also to constructing meaningful social and information networks from them. In this multidisciplinary study, we consider the question of constructing traditional social networks from OSN data and then present several measurement case studies showing how variations in collected OSN data affects social network analyses. To this end we developed a systematic com parison methodology, which we applied to five pairs of parallel datasets collected from Twitter in four case studies. We found considerable differences in several of the datasets collected with different tools and that these variations significantly alter the results of subsequent analyses. Our results lead to a set of guidelines for researchers planning to collect online data streams to infer social networks., Comment: 45 pages, 25 figures, submitted to the International Journal of Social Network Analysis and Mining (SNAM) expanding upon an ASONAM'20 paper (arXiv:2010.08717)

Political misinformation, astroturfing and organised trolling are online malicious behaviours with significant real-world effects. Many previous approaches examining these phenomena have focused on broad campaigns rather than the small groups responsible for instigating or sustaining them. To reveal latent (i.e., hidden) networks of cooperating accounts, we propose a novel temporal window approach that relies on account interactions and metadata alone. It detects groups of accounts engaging in various behaviours that, in concert, come to execute different goal-based strategies, a number of which we describe. The approach relies upon a pipeline that extracts relevant elements from social media posts, infers connections between accounts based on criteria matching the coordination strategies to build an undirected weighted network of accounts, which is then mined for communities exhibiting high levels of evidence of coordination using a novel community extraction method. We address the temporal aspect of the data by using a windowing mechanism, which may be suitable for near real-time application. We further highlight consistent coordination with a sliding frame across multiple windows and application of a decay factor. Our approach is compared with other recent similar processing approaches and community detection methods and is validated against two relevant datasets with ground truth data, using content, temporal, and network analyses, as well as with the design, training and application of three one-class classifiers built using the ground truth; its utility is furthermore demonstrated in two case studies of contentious online discussions., Comment: 58 pages, 25 figures, submitted to the International Journal of Social Network Analysis and Mining (SNAM) as an expansion to an ASONAM'20 paper (arXiv:2010.08180)

To study the effects of Online Social Network (OSN) activity on real-world offline events, researchers need access to OSN data, the reliability of which has particular implications for social network analysis. This relates not only to the completeness of any collected dataset, but also to constructing meaningful social and information networks from them. In this multidisciplinary study, we consider the question of constructing traditional social networks from OSN data and then present a measurement case study showing how the reliability of OSN data affects social network analyses. To this end we developed a systematic comparison methodology, which we applied to two parallel datasets we collected from Twitter. We found considerable differences in datasets collected with different tools and that these variations significantly alter the results of subsequent analyses. Our results lead to a set of guidelines for researchers planning to collect online data streams to infer social networks., Comment: 19 pages, 4 figures, accepted at The 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM'20)

Political astroturfing and organised trolling are online malicious behaviours with significant real-world effects. Common approaches examining these phenomena focus on broad campaigns rather than the small groups responsible. To reveal latent networks of cooperating accounts, we propose a novel temporal window approach that relies on account interactions and metadata alone. It detects groups of accounts engaging in behaviours that, in concert, execute different goal-based strategies, which we describe. Our approach is validated against two relevant datasets with ground truth data., Comment: 20 pages, 10 images, accepted by The 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM'20)

During the summer of 2019-20, while Australia suffered unprecedented bushfires across the country, false narratives regarding arson and limited backburning spread quickly on Twitter, particularly using the hashtag #ArsonEmergency. Misinformation and bot- and troll-like behaviour were detected and reported by social media researchers and the news soon reached mainstream media. This paper examines the communication and behaviour of two polarised online communities before and after news of the misinformation became public knowledge. Specifically, the Supporter community actively engaged with others to spread the hashtag, using a variety of news sources pushing the arson narrative, while the Opposer community engaged less, retweeted more, and focused its use of URLs to link to mainstream sources, debunking the narratives and exposing the anomalous behaviour. This influenced the content of the broader discussion. Bot analysis revealed the active accounts were predominantly human, but behavioural and content analysis suggests Supporters engaged in trolling, though both communities used aggressive language., Comment: 16 pages, 8 images, presented at the 2nd Multidisciplinary International Symposium on Disinformation in Open Online Media (MISDOOM 2020), Leiden, The Netherlands. Published in: van Duijn M., Preuss M., Spaiser V., Takes F., Verberne S. (eds) Disinformation in Open Online Media. MISDOOM 2020. Lecture Notes in Computer Science, vol 12259. Springer, Cham. https://doi.org/10.1007/978-3-030-61841-4_11