Bayesian identification of bots using temporal analysis of tweet storms

Kirn, Spencer Lee; Hinders, Mark K.

doi:10.1007/s13278-021-00783-7

Cited by 3 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we look to use the DWFP, which uses wavelets to transform a signal into a binary image. This method has the benefit of being normalized, so we look solely at the underlying behaviors without the overall volume of tweets distorting the results (Kirn and Hinders 2020 , 2021 ; Kirn 2021 ).…”

Section: Methodsmentioning

confidence: 99%

“… 2019 ; Hinders 2020 ; Rooney 2021 ). In previous work, we have shown the effectiveness of the DWFP for identifying common behavior within very large tweet storms (Kirn and Hinders 2020 ) and for identifying bot accounts (Kirn and Hinders 2021 ; Kirn 2021 ). In this work, we introduce ridge count thresholding (RCT), which isolates specific tweet storms within large collections of tweets to construct tweet storm networks .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ridge count thresholding to uncover coordinated networks during onset of the Covid-19 pandemic

Kirn

Hinders

2022

Soc. Netw. Anal. Min.

Self Cite

View full text Add to dashboard Cite

In order to combat information operations (IO) and disinformation campaigns, one must look at the behaviors of the accounts pushing specific narratives and stories through social media, not at the content itself. In this work, we present a new process for extracting tweet storms and uncovering networks of accounts that are working in a coordinated fashion using ridge count thresholding (RCT). To do this, we started with a dataset of 60 million individual tweets from the early weeks of the Covid-19 pandemic. Coherent topics are extracted from this data by testing three different preprocessing pipelines and applying Orthogonal Nonnegative Matrix Factorization (ONMF). The most effective preprocessing pipeline used hashtag preclustering to downselect the total dataset to the 7 million tweets that included the top hashtags. Each topic identified by ONMF is described by a topic-tweet signal, crafted using the time stamp included in each tweet’s metadata. These signals were broken down into tweet storms using RCT, which is calculated from the Dynamic Wavelet Fingerprint transform of each topic-tweet signal. Each tweet storm described a time of increased activity around a topic. Tweet storms identified in this way each represent some behavior in the underlying network. In total, we identified 39,817 total tweet storms that included about 2 million unique tweets. These tweet storms were used to identify networks of accounts that commonly co-occur within tweet storms to isolate those communities most responsible for driving narratives and pushing stories through social media. Through this process, we were able to identify 22 unique networks of accounts that were densely connected based on RCT tweet storm identification. Many of the identified networks exhibit obvious inauthentic behaviors that are potentially a part of an IO campaign.

show abstract

Section: Methodsmentioning

confidence: 99%