Social interactions take place in environments that influence people's behaviours and perceptions. Nowadays, the users of Online Social Network (OSN) generate a massive amount of content based on social interactions. However, OSNs wide popularity and ease of access created a perfect scenario to practice malicious activities, compromising their reliability. To detect automatic information broadcast in OSN, we developed a waveletbased model that classifies users as being human, legitimate robot, or malicious robot, as a result of spectral patterns obtained from users' textual content.We create the feature vector from the DiscreteWavelet Transform along with a weighting scheme called Lexicon-based Coefficient Attenuation. In particular, we induce a classificationmodel using the Random Forest algorithm over two real Twitter datasets. The corresponding results show the developed model achieved an average accuracy of 94.47% considering two different scenarios: Single theme and miscellaneous one.
Detection of human, legitimate bot, and malicious bot in online social networks based on wavelets / S. Barbon Jr, G. Campos, G. Marques Tavares, R. Igawa, M. L Proença Jr, R. Capobianco Guido. - In: ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS. - ISSN 1551-6857. - 14:1 suppl.(2018), pp. A26.1-A26.17. [10.1145/3183506]
Detection of human, legitimate bot, and malicious bot in online social networks based on wavelets
G. MARQUES TAVARES
;
2018
Abstract
Social interactions take place in environments that influence people's behaviours and perceptions. Nowadays, the users of Online Social Network (OSN) generate a massive amount of content based on social interactions. However, OSNs wide popularity and ease of access created a perfect scenario to practice malicious activities, compromising their reliability. To detect automatic information broadcast in OSN, we developed a waveletbased model that classifies users as being human, legitimate robot, or malicious robot, as a result of spectral patterns obtained from users' textual content.We create the feature vector from the DiscreteWavelet Transform along with a weighting scheme called Lexicon-based Coefficient Attenuation. In particular, we induce a classificationmodel using the Random Forest algorithm over two real Twitter datasets. The corresponding results show the developed model achieved an average accuracy of 94.47% considering two different scenarios: Single theme and miscellaneous one.File | Dimensione | Formato | |
---|---|---|---|
detection.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
3.99 MB
Formato
Adobe PDF
|
3.99 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.