The widespread growth and activity of people in microblogs and the massive production of unstructured data by individuals has made these networks a rich source of data. Also, with the strengthening of artificial intelligence algorithms and deep learning, along with the growth of processing power and reduction of latency thanks to the advent of cloud computing, fog and edge, the possibility of extracting valuable information from this massive amount of data has been provided in less time. These possibilities have led researchers to put a variety of analyzes on their agenda, including sentiment analysis, diagnosis of various mental disorders, and events detection. In this study, we focus on events detection from social media data. Events are the events of the outside world that are reflected in the posts. Among the types of events, we can mention critical events (earthquakes), personal events (marriage) and public events (elections and sports events). Event detection has a variety of applications from informing and reacting quickly to use in recommender systems and offering a variety of news according to the user's interests or offering a variety of products according to the user's personal events and generally customizing information for the user. The purpose of this study is to provide a model based on ensemble deep learning in the fog computing platform to detect events in real time and perform rapid reactions. In previous studies, the focus has been on event detection algorithms and the use of cloud computing and distributed processing is less common in this area. This research tries to fill this gap and improve the speed and accuracy of event detection.
Ali Gandomi (gandomi110@gmail.com)
...