InstaSynth:使用ChatGPT生成合成Instagram数据以检测赞助内容的机遇与挑战
InstaSynth: Opportunities and Challenges in Generating Synthetic Instagram Data with ChatGPT for Sponsored Content Detection
AI总结:
本文研究了使用LLMs生成合成Instagram数据以检测赞助内容的保真度与效用目标,发现两者存在冲突,且提示工程策略不足,合成数据整体缺乏多样性。
摘要:
大型语言模型(LLMs)引发了人们的担忧,因为它们降低了生成可能被用于不道德或非法目的文本的成本,尤其是在社交媒体上。本文研究了此类模型在帮助执行与在线赞助内容披露相关的法律要求方面的潜力。我们探讨了使用LLMs生成合成Instagram标题的两个目标:第一个目标(保真度)是生成逼真的合成数据集。为此,我们实现了内容级和网络级指标,以评估合成标题是否逼真。第二个目标(效用)是创建对赞助内容检测有用的合成数据。为此,我们评估了生成的合成数据在训练分类器以识别Instagram上未披露广告方面的有效性。我们的研究表明,保真度和效用的目标可能会发生冲突,并且提示工程是一种有用但不足的策略。此外,我们发现,虽然单个合成帖子可能看起来逼真,但它们在整体上缺乏多样性、主题连接性和真实的用户互动模式。
英文摘要:
Large Language Models (LLMs) raise concerns about lowering the cost of generating texts that could be used for unethical or illegal purposes, especially on social media. This paper investigates the promise of such models to help enforce legal requirements related to the disclosure of sponsored content online. We investigate the use of LLMs for generating synthetic Instagram captions with two objectives: The first objective (fidelity) is to produce realistic synthetic datasets. For this, we implement content-level and network-level metrics to assess whether synthetic captions are realistic. The second objective (utility) is to create synthetic data that is useful for sponsored content detection. For this, we evaluate the effectiveness of the generated synthetic data for training classifiers to identify undisclosed advertisements on Instagram. Our investigations show that the objectives of fidelity and utility may conflict and that prompt engineering is a useful but insufficient strategy. Additionally, we find that while individual synthetic posts may appear realistic, collectively they lack diversity, topic connectivity, and realistic user interaction patterns.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。