Who Said That? Benchmarking Social Media AI Detection
This addresses the challenge of misinformation and manipulation on social media by offering a benchmark for AI-text detection, though it is incremental as it builds on existing detection methods with a new dataset and focus.
The paper tackles the problem of detecting AI-generated text on social media by introducing the SAID benchmark, which uses real AI-generated content from platforms like Zhihu and Quora to provide a more realistic evaluation, and finds that annotators achieve 96.5% accuracy in distinguishing AI from human text, while user-oriented detection improves accuracy.
AI-generated text has proliferated across various online platforms, offering both transformative prospects and posing significant risks related to misinformation and manipulation. Addressing these challenges, this paper introduces SAID (Social media AI Detection), a novel benchmark developed to assess AI-text detection models' capabilities in real social media platforms. It incorporates real AI-generate text from popular social media platforms like Zhihu and Quora. Unlike existing benchmarks, SAID deals with content that reflects the sophisticated strategies employed by real AI users on the Internet which may evade detection or gain visibility, providing a more realistic and challenging evaluation landscape. A notable finding of our study, based on the Zhihu dataset, reveals that annotators can distinguish between AI-generated and human-generated texts with an average accuracy rate of 96.5%. This finding necessitates a re-evaluation of human capability in recognizing AI-generated text in today's widely AI-influenced environment. Furthermore, we present a new user-oriented AI-text detection challenge focusing on the practicality and effectiveness of identifying AI-generated text based on user information and multiple responses. The experimental results demonstrate that conducting detection tasks on actual social media platforms proves to be more challenging compared to traditional simulated AI-text detection, resulting in a decreased accuracy. On the other hand, user-oriented AI-generated text detection significantly improve the accuracy of detection.