This paper critically examines the affordances and limitations of big data for the study of crime and disorder. We hypothesise that disorder-related posts on Twitter are associated with actual police crime rates. Our results provide evidence that naturally occurring social media data may provide an alternative information source on the crime problem. This paper adds to the emerging field of computational criminology and big data in four ways: i) it estimates the utility of social media data to explain variance in offline crime patterns; ii) it provides the first evidence of the estimation offline crime patterns using a measure of broken windows found in the textual content of social media communications; iii) it tests if the bias present in offline perceptions of disorder is present in online communications; and iv) it takes the results of experiments to critically engage with debates on big data and crime prediction.

中文翻译：

---

大数据犯罪感知：使用开源通信来估计犯罪模式的可行性和局限性

本文批判性地研究了大数据在犯罪和无序研究中的可供性和局限性。我们假设 Twitter 上与混乱相关的帖子与实际的警察犯罪率有关。我们的结果提供证据表明，自然发生的社交媒体数据可能会提供有关犯罪问题的替代信息来源。本文以四种方式增加了计算犯罪学和大数据的新兴领域：i）它估计社交媒体数据的效用以解释离线犯罪模式的差异；ii) 它使用在社交媒体通信的文本内容中发现的破碎窗口的度量提供了估计离线犯罪模式的第一个证据；iii）它测试在线交流中是否存在离线感知障碍中存在的偏见；