Location-Based Events Detection on Micro-Blogs
This work addresses the challenge of analyzing large-scale social media data for event detection, which is incremental as it applies an existing outlier detection approach to a new domain.
The authors tackled the problem of detecting location-based events from Twitter data by proposing a neural network method to identify outliers in time series, which revealed new insights into modeling local behavior across different regions.
The increasing use of social networks generates enormous amounts of data that can be used for many types of analysis. Some of these data have temporal and geographical information, which can be used for comprehensive examination. In this paper, we propose a new method to analyze the massive volume of messages available in Twitter to identify places in the world where topics such as TV shows, climate change, disasters, and sports are emerging. The proposed method is based on a neural network that is used to detect outliers from a time series, which is built upon statistical data from tweets located on different political divisions (i.e., countries, cities). The outliers are used to identify topics within an abnormal behavior in Twitter. The effectiveness of our method is evaluated in an online environment indicating new findings on modeling local people's behavior from different places.