The contribution of the thesis is to propose new solutions and approaches for the detection of online information manipulations. Information manipulation strategies can take the forms of: (i) disinformation, which is manipulation in the form of online deceiving content, and (ii) misbehavior, which is manipulation in the form of online deceiving accounts. We investigate and address such issues as interconnected, comprehensive, and holistic problems, going beyond current literature limitations of siloed approaches. In particular, we provide technical approaches for the detection of online information manipulation capable of taking into consideration diverse strategies, multiple targets, multiple online platforms, and coordination and manipulation definitions beyond the binary concept.
Holistic Approaches to Investigating, Characterizing, and Detecting Online Disinformation and Misbehavior
TARDELLI, SERENA
2022
Abstract
The contribution of the thesis is to propose new solutions and approaches for the detection of online information manipulations. Information manipulation strategies can take the forms of: (i) disinformation, which is manipulation in the form of online deceiving content, and (ii) misbehavior, which is manipulation in the form of online deceiving accounts. We investigate and address such issues as interconnected, comprehensive, and holistic problems, going beyond current literature limitations of siloed approaches. In particular, we provide technical approaches for the detection of online information manipulation capable of taking into consideration diverse strategies, multiple targets, multiple online platforms, and coordination and manipulation definitions beyond the binary concept.File | Dimensione | Formato | |
---|---|---|---|
report_attivita_dottorato.pdf
accesso aperto
Dimensione
271.34 kB
Formato
Adobe PDF
|
271.34 kB | Adobe PDF | Visualizza/Apri |
tesi.pdf
accesso aperto
Dimensione
47.54 MB
Formato
Adobe PDF
|
47.54 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/20.500.14242/215735
URN:NBN:IT:UNIPI-215735