The contribution of the thesis is to propose new solutions and approaches for the study and characterization of social information manipulation. Reported social media manipulation instances, although differing in the strategy employed, share two main characteristics: (i) they employ a group of accounts within the designated social media platform, and (ii) they exploit their coordinated actions to amplify the spread and reach of manipulation. As they are the key elements of social media manipulation, both the accounts involved and the concept of coordination have been addressed by academic and industry research in order to counter the phenomenon. We investigate and address such aspects as interconnected, comprehensive, and holistic problems, going beyond current literature limitations of siloed approaches. In particular, we provide technical approaches for characterizing social media accounts and collecting data about them and frameworks for detecting coordinated behaviors and reconstruct retweet cascades.
Breaking Down Social Media Manipulation: Actors, Coordination and Dissemination
MAZZA, MICHELE
2023
Abstract
The contribution of the thesis is to propose new solutions and approaches for the study and characterization of social information manipulation. Reported social media manipulation instances, although differing in the strategy employed, share two main characteristics: (i) they employ a group of accounts within the designated social media platform, and (ii) they exploit their coordinated actions to amplify the spread and reach of manipulation. As they are the key elements of social media manipulation, both the accounts involved and the concept of coordination have been addressed by academic and industry research in order to counter the phenomenon. We investigate and address such aspects as interconnected, comprehensive, and holistic problems, going beyond current literature limitations of siloed approaches. In particular, we provide technical approaches for characterizing social media accounts and collecting data about them and frameworks for detecting coordinated behaviors and reconstruct retweet cascades.| File | Dimensione | Formato | |
|---|---|---|---|
|
PhD_report.pdf
non disponibili
Licenza:
Tutti i diritti riservati
Dimensione
111.53 kB
Formato
Adobe PDF
|
111.53 kB | Adobe PDF | |
|
Thesis.pdf
accesso aperto
Licenza:
Tutti i diritti riservati
Dimensione
42.24 MB
Formato
Adobe PDF
|
42.24 MB | Adobe PDF | Visualizza/Apri |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14242/215467
URN:NBN:IT:UNIPI-215467