Social networks may be employed to commit cybercrimes such as hate promotion or violence instigation. These platforms have become a scenario where Law Enforcement Agencies (LEA) must pay close attention to detect cybercrimes and monitor public safety. This paper proposes the adoption of the Natural Language Processing (NLP) models, especially a similarity model, to identify suspicious activities in social networks allowing to identify and prevent related cybercrimes. An LEA can use NLP models to find similar posts grouped in clusters, to determine their level of polarity, to find connections between users and to identify a subset of user accounts that promotes Hostile Social Manipulation (HSM), so such accounts can be reviewed extensively as part of an effort to prevent crimes.

This work would not have been possible without the inestimable contribution of:

• Julián Ramírez Sánchez
• Alejandra Campo-Archbold
• Andrés Zapata Rozo
• Daniel O. Díaz López
• Javier Pastor Galindo
• Julián Aponte Díaz

Julián Ramírez Sánchez, Alejandra Campo-Archbold, Andrés Zapata Rozo, Daniel O. Díaz López, Javier Pastor Galindo, Félix Gómez Mármol, Julián Aponte Díaz, «On the power of social networks to analyze threatening trends«, Special Issue on the Effects of Social Media on Real-World Events, IEEE Internet Computing, vol. 26, no. 2, pp. 19-26, 2022

• Journal: IEEE Internet Computing
• Category: Computer Science, Software Engineering
• Rank: 43/110
• Quartile: Q2
• Impact Factor: 2.680