No abstract

We developed a wavelet-based approach for account classification that detects textual dissemination by bots on an Online Social Network (OSN). Its main objective is to match account patterns with humans, cyborgs or robots, improving the existing algorithms that automatically detect frauds. With a computational cost suitable for OSNs, the proposed approach analyses the distribution of key terms. The descriptors, a wavelet-based feature vector for each user's account, work in conjunction with a new weighting scheme, called Lexicon Based Coefficient Attenuation (LBCA) and serve as inputs to one of the classifiers tested: Random Forests and Multilayer Perceptrons. Experiments were performed using a set of posts crawled during the 2014 FIFA World Cup, obtaining accuracies within the range from 94 to 100%.

In this work, we propose an approach for recognition of compromised Twitter accounts based on Authorship Verification. Our solution can detect accounts that became compromised by analysing their user writing styles. This way, when an account content does not match its user writing style, we affirm that the account has been compromised, similar to Authorship Verification. Our approach follows the profile-based paradigm and uses N-grams as its kernel. Then, a threshold is found to represent the boundary of an account writing style. Experiments were performed using a subsampled dataset from Twitter. Experimental results showed that the developed model is very suitable for compromised recognition of Online Social Networks accounts due to the capability of recognize user styles over 95% accuracy.

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.

No abstract