Social media platforms such as Instagram and Twitter have emerged as critical channels for marketing and selling illegal drugs. Detecting and labeling online illicit drug trafficking activities have become an important measure to combat online drug trafficking. Recently, machine learning has been applied to drug trafficking detection. However, the effectiveness of conventional supervised learning methods in detecting drug trafficking heavily relies on access to substantial amounts of labeled data, while data annotation is time-consuming and resource-intensive. Furthermore, these models often face challenges in accurately identifying trafficking activities when drug dealers use deceptive language and euphemisms to avoid detection. To overcome this limitation, we conduct the first systematic study on leveraging large language models (LLMs), such as ChatGPT, to detect illicit drug trafficking activities on social media. We propose an analytical framework to compose , which serve as the interface that humans can interact with and use LLMs to perform the detection task. Additionally, we designed a Monte Carlo dropout-based prompt optimization method to further improve performance and interpretability. Our experimental findings demonstrate that the proposed framework outperforms other baseline language models in terms of drug trafficking detection accuracy, showing a remarkable improvement of nearly 12%. By integrating prior knowledge and the proposed prompts, ChatGPT can effectively identify and label drug trafficking activities on social networks, even in the presence of deceptive language and euphemisms used by drug dealers to evade detection. The implications of our research extend to social networks, emphasizing the importance of incorporating prior knowledge and scenario-based prompts into analytical tools to improve online security and public safety.

中文翻译：

---

知识提示的 ChatGPT：加强社交媒体上的贩毒检测


Instagram 和 Twitter 等社交媒体平台已成为营销和销售非法毒品的重要渠道。侦查、标识网络非法贩毒活动已成为打击网络贩毒的重要举措。最近，机器学习已应用于贩毒检测。然而，传统监督学习方法在侦查毒品贩运方面的有效性很大程度上依赖于对大量标记数据的访问，而数据注释既耗时又耗费资源。此外，当毒贩使用欺骗性语言和委婉语以避免被发现时，这些模型在准确识别贩运活动方面常常面临挑战。为了克服这一限制，我们首次对利用大型语言模型进行了系统研究（LLMs ），例如 ChatGPT，用于检测社交媒体上的非法贩毒活动。我们提出了一个组合分析框架，作为人类可以交互和使用的界面。LLMs来执行检测任务。此外，我们设计了一种基于蒙特卡罗 dropout 的提示优化方法，以进一步提高性能和可解释性。我们的实验结果表明，所提出的框架在贩毒检测准确性方面优于其他基线语言模型，显着提高了近 12%。通过整合先验知识和建议的提示，ChatGPT 可以有效地识别和标记社交网络上的贩毒活动，即使存在毒贩用来逃避检测的欺骗性语言和委婉说法。 我们的研究的影响延伸到社交网络，强调将先验知识和基于场景的提示纳入分析工具以改善在线安全和公共安全的重要性。