Messages on social media can be an important source of information during crisis situations. They can frequently provide details about developments much faster than traditional sources (e.g., official news) and can offer personal perspectives on events, such as opinions or specific needs. In the future, these messages can also serve to assess disaster risks.One challenge for utilizing social media in crisis situations is the reliable detection of relevant messages in a flood of data. Researchers have started to look into this problem in recent years, beginning with crowdsourced methods. Lately, approaches have shifted towards an automatic analysis of messages. A major stumbling block here is the question of exactly what messages are considered relevant or informative, as this is dependent on the specific usage scenario and the role of the user in this scenario.In this review article, we present methods for the automatic detection of crisis-related messages (tweets) on Twitter. We start by showing the varying definitions of importance and relevance relating to disasters, leading into the concept of use case-dependent actionability that has recently become more popular and is the focal point of the review paper. This is followed by an overview of existing crisis-related social media data sets for evaluation and training purposes. We then compare approaches for solving the detection problem based (1) on filtering by characteristics like keywords and location, (2) on crowdsourcing, and (3) on machine learning technique. We analyze their suitability and limitations of the approaches with regards to actionability. We then point out particular challenges, such as the linguistic issues concerning social media data. Finally, we suggest future avenues of research and show connections to related tasks, such as the subsequent semantic classification of tweets.

中文翻译：

---

评论文章：检测危机事件中可操作的推文

在危机情况下，社交媒体上的消息可能是重要的信息来源。他们通常可以比传统来源（例如官方新闻）更快地提供有关发展的详细信息，并且可以提供对事件的个人观点，例如意见或特定需求。未来，这些信息还可用于评估灾害风险。在危机情况下利用社交媒体的一个挑战是在大量数据中可靠地检测相关信息。近年来，研究人员开始研究这个问题，从众包方法开始。最近，方法已经转向自动分析消息。这里的一个主要障碍是究竟哪些消息被认为是相关的或信息量大的问题，因为这取决于特定的使用场景和用户在该场景中的角色。在这篇评论文章中，我们介绍了自动检测 Twitter 上与危机相关的消息（推文）的方法。我们首先展示了与灾难相关的重要性和相关性的不同定义，从而引入了最近变得更加流行并且是评论论文的焦点的用例相关可操作性概念。接下来是对现有危机相关社交媒体数据集的概述，用于评估和培训目的。然后，我们比较了基于（1）通过关键字和位置等特征过滤，（2）众包和（3）机器学习技术来解决检测问题的方法。我们分析了这些方法在可操作性方面的适用性和局限性。然后，我们指出了特定的挑战，例如与社交媒体数据有关的语言问题。最后，我们建议未来的研究途径并展示与相关任务的联系，例如随后的推文语义分类。