Name
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%. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1016/j.ins.2015.10.039 | Information Sciences |
Keywords | Field | DocType |
Account classification,Wavelets,Online social networks,Multilayer perceptrons,Random forests | Data mining,Feature vector,Weighting,Social network,Computer science,Lexicon,Artificial intelligence,Robot,Random forest,Perceptron,Machine learning,Wavelet | Journal |
Volume | Issue | ISSN |
332 | C | 0020-0255 |
Citations | PageRank | References |
7 | 0.50 | 49 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rodrigo Augusto Igawa | 1 | 11 | 2.58 |
| Sylvio Barbon | 2 | 46 | 10.97 |
| Katia Cristina Silva Paulo | 3 | 7 | 0.84 |
| Guilherme Sakaji Kido | 4 | 7 | 0.84 |
| Rodrigo Capobianco Guido | 5 | 161 | 27.59 |
| Mario Lemes Proença Júnior | 6 | 7 | 0.50 |
| Ivan Nunes da Silva | 7 | 176 | 52.11 |