A network topology approach to bot classification
| Autor: | Cornelissen, Laurenz A., Barnett, Richard J, Schoonwinkel, Petrus, Eichstadt, Brent D., Magodla, Hluma B. |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Social and Information Networks (cs.SI)
FOS: Computer and information sciences Physics - Physics and Society 021110 strategic defence & security studies Social network business.industry Computer science 0211 other engineering and technologies FOS: Physical sciences Computer Science - Social and Information Networks Topology (electrical circuits) Physics and Society (physics.soc-ph) 02 engineering and technology Network topology Social agents 020204 information systems 0202 electrical engineering electronic engineering information engineering Unsupervised learning Social media business Computer network |
| Zdroj: | SAICSIT |
| DOI: | 10.1145/3278681.3278692 |
| Popis: | Automated social agents, orbotsare increasingly becoming a prob- lem on social media platforms. There is a growing body of literature and multiple tools to aid in the detection of such agents on online social networking platforms. We propose that the social network topology of a user would be sufficient to determine whether the user is a automated agent or a human. To test this, we use a pub- licly available dataset containing users on Twitter labelled as either automated social agent or human. Using an unsupervised machine learning approach, we obtain a detection accuracy rate of 70%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|