[论文解读] Do You See What I See? Capabilities and Limits of Automated Multimedia Content Analysis

Carey Shenkman, Dhanaraj Thakur+1 more|arXiv (Cornell University)|Dec 15, 2021

Hate Speech and Cyberbullying Detection被引用 26

一句话总结

论文解释了自动化多媒体内容分析工具的能力与局限，聚焦于匹配模型和预测模型，并强调在未考虑约束的情况下大规模使用的风险。

ABSTRACT

The ever-increasing amount of user-generated content online has led, in recent years, to an expansion in research and investment in automated content analysis tools. Scrutiny of automated content analysis has accelerated during the COVID-19 pandemic, as social networking services have placed a greater reliance on these tools due to concerns about health risks to their moderation staff from in-person work. At the same time, there are important policy debates around the world about how to improve content moderation while protecting free expression and privacy. In order to advance these debates, we need to understand the potential role of automated content analysis tools. This paper explains the capabilities and limitations of tools for analyzing online multimedia content and highlights the potential risks of using these tools at scale without accounting for their limitations. It focuses on two main categories of tools: matching models and computer prediction models. Matching models include cryptographic and perceptual hashing, which compare user-generated content with existing and known content. Predictive models (including computer vision and computer audition) are machine learning techniques that aim to identify characteristics of new or previously unknown content.

研究动机与目标

• 通过用户生成内容的增长以及了解用于政策和监管的自动分析工具的需求来推动本研究。
• 澄清两大类工具——匹配模型与预测模型——及其各自的作用。
• 评估在大规模部署自动化多媒体分析时可能的风险与局限。
• 以对工具能力的细致理解为内容审查、自由表达与隐私等政策辩论提供信息。

提出的方法

• 将自动化内容分析工具分为两大类：匹配模型（密码学和感知哈希）和预测模型（在视觉与听觉领域的机器学习方法）。
• 描述匹配模型如何将内容与已知范例进行比较，以及预测模型如何尝试识别新内容或未知内容的特征。
• 讨论在缺乏恰当免责声明的情况下大规模使用这些工具的局限性与风险。

实验结果

研究问题

• RQ1 匹配模型和预测模型在自动化多媒体分析中的能力是什么？
• RQ2 在大规模部署这些工具时，关键的局限性与风险是什么？
• RQ3 这些工具如何为关于监管、隐私和自由表达的政策辩论提供信息或带来约束？

主要发现

• 自动化多媒体内容分析工具在与已知内容比较以及预测未知内容特征方面具有不同的能力。
• 这些工具存在重要的局限性，特别是在大规模应用时，可能影响准确性与公平性。
• 在不考虑其局限性的前提下依赖这些工具，可能在监管、隐私和言论自由辩论中带来风险。