Maximum Entropy Networks Applied on Twitter Disinformation Datasets

Clerck, Bart De; Utterbeeck, Filip Van; Petit, Julien; Lauwens, Ben; Mees, Wim; Rocha, Luis E. C.

doi:10.1007/978-3-030-93413-2_12

Cited by 5 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in a previous study, we showed that it was not possible to reconstruct a disinformation network when a large part of a dataset was removed by the social media platform (De Clerck et al. 2022 ).…”

Section: Discussionmentioning

confidence: 99%

“…The Bipartitte Configuration Model (BiCM) and the DBiCM are two models from the Exponential Random Graph Models (ERGM) (Park and Newman 2004;Hunter et al 2012) family that have seen the largest amount of use cases on social media data, in part due to the computational aspect, but also because it allows the use of statistical tests to reduce the fully connected network to only the statistically significant connections. They have been used to identify significant user interactions in several applications such as identifying significant content spreaders (Caldarelli et al 2021); observing that social bots play a central role in the exchange of significant content for political propaganda (Caldarelli et al 2020); identifying significant content spreaders and identifying political alliances (Becatti et al 2019); identifying significant interactions in Twitter disinformation datasets (De Clerck et al 2022); analysing a semantic network during the COVID-19 pandemic (Mattei et al 2021); characterising the behaviour of bots during the UK elections (Bruno et al 2021).…”

Section: Specific Applications On Social Networkmentioning

confidence: 99%

“…When these hashtags are not captured, it can be challenging to reconstruct the network and perform the analysis. For example, in a previous study, we showed that it was not possible to reconstruct a disinformation network when a large part of a dataset was removed by the social media platform (De Clerck et al 2022).…”

Section: Robustness and Data Collectionmentioning

confidence: 99%

“… 2019 ); identifying significant interactions in Twitter disinformation datasets (De Clerck et al. 2022 ); analysing a semantic network during the COVID-19 pandemic (Mattei et al. 2021 ); characterising the behaviour of bots during the UK elections (Bruno et al.…”

Section: Introductionmentioning

confidence: 99%

“…This paper is an extended version of the work presented in (De Clerck et al. 2022 ), where only the DBiCM was used. At present we are able to consider additional network models thanks to the acceleration methods explained in the methods section.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Maximum entropy networks for large scale social network node analysis

2022

Self Cite

View full text Add to dashboard Cite

Recently proposed computational techniques allow the application of various maximum entropy network models at a larger scale. We focus on disinformation campaigns and apply different maximum entropy network models on the collection of datasets from the Twitter information operations report. For each dataset, we obtain additional Twitter data required to build an interaction network. We consider different interaction networks which we compare to an appropriate null model. The null model is used to identify statistically significant interactions. We validate our method and evaluate to what extent it is suited to identify communities of members of a disinformation campaign in a non-supervised way. We find that this method is suitable for larger social networks and allows to identify statistically significant interactions between users. Extracting the statistically significant interaction leads to the prevalence of users involved in a disinformation campaign being higher. We found that the use of different network models can provide different perceptions of the data and can lead to the identification of different meaningful patterns. We also test the robustness of the methods to illustrate the impact of missing data. Here we observe that sampling the correct data is of great importance to reconstruct an entire disinformation operation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Specific Applications On Social Networkmentioning

confidence: 99%

Section: Robustness and Data Collectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Maximum entropy networks for large scale social network node analysis

2022

Self Cite

View full text Add to dashboard Cite

show abstract

Proof of biased behavior of Normalized Mutual Information

Mahmoudi,

Jemielniak

2024

Sci Rep

View full text Add to dashboard Cite

The Normalized Mutual Information (NMI) metric is widely utilized in the evaluation of clustering and community detection algorithms. This study explores the performance of NMI, specifically examining its performance in relation to the quantity of communities, and uncovers a significant drawback associated with the metric's behavior as the number of communities increases. Our findings reveal a pronounced bias in the NMI as the number of communities escalates. While previous studies have noted this biased behavior, they have not provided a formal proof and have not addressed the causation of this problem, leaving a gap in the existing literature. In this study, we fill this gap by employing a mathematical approach to formally demonstrate why NMI exhibits biased behavior, thereby establishing its unsuitability as a metric for evaluating clustering and community detection algorithms. Crucially, our study exposes the vulnerability of entropy-based metrics that employ logarithmic functions to similar bias.

show abstract

Entropy-based detection of Twitter echo chambers

Pratelli,

Saracco,

Petrocchi

2024

PNAS Nexus

View full text Add to dashboard Cite

Echo chambers, i.e. clusters of users exposed to news and opinions in line with their previous beliefs, were observed in many online debates on social platforms. We propose a completely unbiased entropy-based method for detecting echo chambers. The method is completely agnostic to the nature of the data. In the Italian Twitter debate about the Covid-19 vaccination, we find a limited presence of users in echo chambers (about 0.35% of all users). Nevertheless, their impact on the formation of a common discourse is strong, as users in echo chambers are responsible for nearly a third of the retweets in the original dataset. Moreover, in the case study observed, echo chambers appear to be a receptacle for disinformative content.

show abstract

Maximum Entropy Networks Applied on Twitter Disinformation Datasets

Cited by 5 publications

References 24 publications

Maximum entropy networks for large scale social network node analysis

Maximum entropy networks for large scale social network node analysis

Proof of biased behavior of Normalized Mutual Information

Entropy-based detection of Twitter echo chambers

Contact Info

Product

Resources

About