Показати скорочений опис матеріалу
dc.contributor.author | Bodnar, Petro![]() |
|
dc.date.accessioned | 2021-06-25T12:38:20Z | |
dc.date.available | 2021-06-25T12:38:20Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | Bodnar, Petro. Detecting patterns of coordinated news article dissemination / Petro Bodnar; Supervisor: Dmytro Karamshuk; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2021. – 35 p.: ill. | uk |
dc.identifier.uri | https://er.ucu.edu.ua/handle/1/2697 | |
dc.language.iso | en | uk |
dc.subject | detection of misinformation | uk |
dc.subject | Multivariate Hawkes Processes | uk |
dc.title | Detecting patterns of coordinated news article dissemination | uk |
dc.type | Preprint | uk |
dc.status | Публікується вперше | uk |
dc.description.abstracten | This study aims at devising methods for detecting coordination among content spreaders at scale. We focus on methods which uncover the latent structure of the content dissemination networks from the time-series of publications. We identify the advantages of generative models, especially self-exiting stochastic processes, for modeling information cascades and detecting structural patterns in groups of events. We validate the most popular of these models – the Multivariate Hawkes processes – on a large dataset of news websites and achieve an improvement in comparison to simpler baselines, e.g., cosine similarity between time-series of publications. | uk |