Twitter predicts an event better than police

Twitter Machine learning

In recent years, there has been increased interest in real-world event detection using publicly accessible data made available through social media. Users are able to post real time dangerous situations and their reactions by using hashtags.

New research from Cardiff University, which analysed 1.6 million tweets from the London 2011 riots, has noticed that twitter can be used to detect dangerous situations up to an hour faster than police reports. The researchers used event detection algorithms that use various features of Twitter data like sentiment, frequency of tweets containing certain words and location and timing of the tweets to recognize similar clusters in the data using the techniques in unsupervised machine learning.

They made an end-to-end integrated event detection framework that has five main components: data collection, pre-processing, classification, online clustering, and summarization. The integration between classification and clustering enables events to be detected, as well as related smaller-scale disruptive events, smaller incidents that threaten social safety and security or could disrupt social order. Researchers found that they were able to map out real-time disruptive events from five minutes to an hour before the Police were aware of them.

These results support the hypothesis that information extracted from social media can be used effectively as a valuable additional source of intelligence as well as to bridge that gap between the use of “big data” and modern policing in order to maintain situational awareness and enhance public safety and decision making.
But there may be claims that social media could be used to invade people’s privacy and crack down on people’s expression of views.
To comment on this article and other content,  please visit our The Box Internet Facebook page.