[论文解读] Mining Anonymity: Identifying Sensitive Accounts on Twitter

Sai Teja Peddinti, Keith W. Ross+1 more|arXiv (Cornell University)|Feb 1, 2017

Spam and Phishing Detection参考文献 23被引用 6

一句话总结

本文提出了一种可扩展的、客观的方法，通过分析关注者匿名性模式而非依赖基于关键词的检测，来识别敏感的Twitter账号。通过训练机器学习分类器以区分匿名与可识别的关注者，该方法检测出拥有高比例匿名关注者的账号——表明其内容具有敏感性——并通过LDA主题建模和人工评估验证了该方法的有效性，成功识别出涉及抑郁、LGBTQ等污名化话题的账号。

ABSTRACT

We explore the feasibility of automatically finding accounts that publish sensitive content on Twitter. One natural approach to this problem is to first create a list of sensitive keywords, and then identify Twitter accounts that use these words in their tweets. But such an approach may overlook sensitive accounts that are not covered by the subjective choice of keywords. In this paper, we instead explore finding sensitive accounts by examining the percentage of anonymous and identifiable followers the accounts have. This approach is motivated by an earlier study showing that sensitive accounts typically have a large percentage of anonymous followers and a small percentage of identifiable followers. To this end, we first considered the problem of automatically determining if a Twitter account is anonymous or identifiable. We find that simple techniques, such as checking for name-list membership, perform poorly. We designed a machine learning classifier that classifies accounts as anonymous or identifiable. We then classified an account as sensitive based on the percentages of anonymous and identifiable followers the account has. We applied our approach to approximately 100,000 accounts with 404 million active followers. The approach uncovered accounts that were sensitive for a diverse number of reasons. These accounts span across varied themes, including those that are not commonly proposed as sensitive or those that relate to socially stigmatized topics. To validate our approach, we applied Latent Dirichlet Allocation (LDA) topic analysis to the tweets in the detected sensitive and non-sensitive accounts. LDA showed that the sensitive and non-sensitive accounts obtained from the methodology are tweeting about distinctly different topics. Our results show that it is indeed possible to objectively identify sensitive accounts at the scale of Twitter.

研究动机与目标

• 开发一种客观、可扩展的方法，用于识别敏感的Twitter账号，避免基于关键词检测的主观性。
• 探究关注者匿名性模式（特别是匿名与可识别关注者所占比例）是否可作为内容敏感性的可靠代理指标。
• 通过主题建模（LDA）和人工评估验证该方法，确保所检测到的账号确实讨论的是敏感主题。
• 证明该方法可泛化应用于多种社会污名化话题，而这些话题往往难以通过预定义关键词列表捕捉。

提出的方法

• 训练机器学习分类器，基于用户名、简介和元数据等配置文件特征，自动判断Twitter账号是否为匿名或可识别。
• 利用分类器计算每个目标账号的匿名关注者与可识别关注者的占比。
• 若某账号拥有高比例的匿名关注者且低比例的可识别关注者，则将其分类为敏感账号。
• 将该方法应用于约10万个账号的大规模Twitter爬取数据，涵盖4.04亿名活跃关注者。
• 对2,000个敏感与非敏感账号的子集应用潜在狄利克雷分布（LDA）主题建模以验证结果。
• 对200个账号进行人工评估，以衡量自动化分类与人工判断之间的一致性。

实验结果

研究问题

• RQ1 关注者匿名性模式能否作为Twitter上敏感内容的可靠、客观指标？
• RQ2 所提出的该方法是否能泛化至传统基于关键词的方法无法捕捉的敏感话题？
• RQ3 基于匿名性模式的自动化分类与人工判断在内容敏感性上的吻合度如何？
• RQ4 通过该方法识别出的敏感账号是否与非敏感账号在主题上存在明显差异？

主要发现

• LDA主题分析显示，该方法识别出的敏感账号所讨论的主题与非敏感账号存在显著差异，证实了主题上的区分性。
• 人工评估者与自动化分类结果高度一致，大多数敏感账号在抑郁、LGBTQ议题和色情内容等主题上被正确识别。
• 该方法成功识别出那些常被基于关键词的系统忽略的、涉及污名化或社会敏感话题的账号。
• 该方法可有效扩展至整个Twitter生态系统，在不依赖语言特定关键词的前提下，处理约10万个账号及4.04亿名关注者。
• 拥有高比例匿名关注者的账号始终与敏感内容相关联，验证了该方法的核心假设。
• 本研究证明，关注者匿名性模式可作为内容敏感性的稳健、可扩展的代理指标，即使在多样且复杂的主题中亦成立。