User generated content in social networks has become a rich source of information into health conditions. This information is not only discussed privately on social networks by the users, but is increasingly publicly given out. This article analyzes the health condition mentions in tweets. Since health mentions can be used in different contexts, whether as a joke, in a news article link, or a genuine disclosure of a health condition suffered by the user, it is important to understand the contexts of the tweets. We address this by categorizing the tweets based on context. We found each health mention to have differing disclosure rates, affecting privacy leaks differently and peaking in disclosure rate at different times of the day. We also found that personal privacy leaks and secondary privacy leaks are affected differently by each health mention.

中文翻译：

---

Twitter 上的健康提及：识别隐私泄露的案例研究


用户在社交网络中生成的内容已成为了解健康状况的丰富信息来源。这些信息不仅由用户在社交网络上私下讨论，而且越来越多地公开发布。本文分析了推文中提及的健康状况。由于健康提及可以在不同的上下文中使用，无论是作为笑话、新闻文章链接，还是真实披露用户所遭受的健康状况，因此了解推文的上下文非常重要。我们通过根据上下文对推文进行分类来解决这个问题。我们发现每个健康提及都有不同的披露率，对隐私泄露的影响不同，并且在一天中的不同时间披露率达到峰值。我们还发现，每次健康提及对个人隐私泄露和二次隐私泄露的影响不同。