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.
29-giu-2023
Italiano
data science
social media intelligence
social media manipulation
social network analysis
web science
Avvenuti, Marco
Cresci, Stefano
Tesconi, Maurizio
File in questo prodotto:
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14242/215467
Il codice NBN di questa tesi è URN:NBN:IT:UNIPI-215467