Background and Objective: Doping trafficking networks represent a severe, multi-faceted threat to sports, especially for female athletes. Doping causes significant physical and psychological harm, undermines fair competition, and damages the ethical foundations of sport at all levels. Effectively identifying and countering these networks, which increasingly exploit new technologies like social media, is crucial for mitigating the extensive damage caused by doping. This research aims to analyze methods for identifying these trafficking networks by leveraging Artificial Intelligence (AI) capabilities on social media platforms.

Methods: This descriptive-analytical study is based on secondary data analysis and a review of AI technology literature. It focuses specifically on methods for extracting and analyzing textual and linguistic data related to doping trafficking from social media platforms.

Results: The findings demonstrate that AI models, such as machine learning, can generate valuable qualitative and quantitative data on traffickers' network structures and hidden transaction patterns. Processing textual and linguistic data enables the extraction of vital intelligence, including suspect identities, the scale of operations, and other key variables. The application of AI now allows for the real-time, simultaneous identification of production locations, trafficking routes, and the traffickers themselves within these networks.

Conclusion: The advanced capabilities of AI in uncovering doping trafficking networks present a powerful tool for judicial systems. It is instrumental in preventing and combating damage to athlete health and the wider sporting and social consequences of doping.