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.
OSN frauds; text mining; writing style; wavelets; bots
Settore INF/01 - Informatica
2018
Article (author)
File in questo prodotto:
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/772378
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 27
  • ???jsp.display-item.citation.isi??? 23
social impact