Detection of Human, Legitimate Bot, and Malicious Bot in Online Social Networks Based on Wavelets

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 wavelet-based 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 Discrete Wavelet Transform along with a weighting scheme called Lexicon-based Coefficient Attenuation. In particular, we induce a classification model 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.

Multimodal detection of epilepsy with deep neural networks

“…A wavelet-based approach was introduced by [17]. Specifically, the authors exploited the discrete wavelet transform and extracted a set of features, namely wavelet magnitude, wavelet phase, wavelet domain score, and so on.…”

Not All Bots are Created Equal: The Impact of Bots Classification Techniques on Identification of Discursive Behaviors Around the COVID-19 Vaccine and Climate Change

“…For example, Subrahmanian et al (2016) suggested a method for identifying "influence bots" that affect Twitter conversations on certain topics. Barbon Jr. et al (2018) proposed a text mining technique to differentiate legitimate from malicious bots. Nevertheless, the application of these methods in policy-oriented empirical research remains very limited.…”

“…Stieglitz et al (2017), for example, argued that bots should be further classified based on their goals, with some being categorized as malicious, and others as benign. Consistently, Barbon Jr. et al (2018) argued that some bots should be thought of as legitimate as they are easy for ordinary users to discern, while others who use sophisticated tactics to disguise themselves as humans should be conceptualized as malicious. Others suggested classifying based on context, for example, in the case of political (Gorwa & Guilbeault, 2020;Woolley & Howard, 2018;Yan et al, 2021), news (Lokot & Diakopoulos, 2016), and stock market (Cresci, Lillo, et al, 2019) bots.…”

Detecção de Bots Sociais: Uma Discussão sobre o Tempo de Vida de Abordagens Tradicionais

“…Tal abordagem exige o emprego de mão de obra ou envolvimento ativo de uma larga comunidade, e pode não ser a melhor abordagem para analisar grandes volumes de dados [Ferrara et al 2016]. [Jr et al 2018] combinou abordagens comportamentais e análise textual para potencializar a detecção, analisando o tema do texto. Considerou inclusive bots legítimos e suas intenções.…”