Monitoring Geographical Entities With Temporal Awareness In Tweets

To extract real-time information referring to a specific place from social network service texts such as tweets, it is necessary to analyze the temporal semantics of the reference. To solve this problem, we created a corpus with multiple annotations for more than 10,000 tweets using crowdsourcing. We constructed an automatic analysis model based on multiple neural networks and compared their characteristics. Our dataset and codes are released in our website (http://www.cl.ecei.tohoku.ac.jp/similar to matsuda/TA_corpus/).