Event detection in online social network: Methodologies, state-of-art, and evolution

Online social network such as Twitter, Facebook and Instagram are increasingly becoming the go-to medium for users to acquire information and discuss what is happening globally. Understanding real-time conversations with masses on social media platforms can provide rich insights into events, provided that there is a way to detect and characterise events. To this end, in the past twenty years, many researchers have been developing event detection methods based on the data collected from various social media platforms. The developed methods for discovering events are generally modular in design and novel in scale and speed. To review the research in this field, we line up existing works for event detection in online social networks and organise them to provide a comprehensive and in-depth survey. This survey comprises three major parts: research methodologies, the review of state-of-the-art literature and the evolution of significant challenges. Each part is supposed to attract readers with different motivations and expectations on the ‘things’ delivered in this survey. For example, the methodologies provide the life-cycle to design new event detection models, from data collection to model evaluations. A timeline and a taxonomy of existing methods are also introduced to elaborate the development of various technologies under the umbrella of event detection. These two parts benefit those with a background in event detection and want to commit a deep exploration of existing models such as discussing their pros and cons alike. The third part shows the development of the major open issues in this field. It also indicates the milestones of each challenge in terms of typical models. Our survey can contribute to the community by highlighting possible new problem statements and opening new research directions.