SocialAnalysis: A Real-Time Query and Mining System from Social Media Data Streams
In this paper, we present our recent progress of designing a real-time system, SocialAnalysis, to discover and summarize emergent social events from social media data streams. In social networks era, people always frequently post messages or comments about their activities and opinions. Hence, there exist temporal correlations between the physical world and virtual social networks, which can help us to monitor and track social events, detecting and positioning anomalous events before their outbreakings, so as to provide early warning.
The key technologies in the system include: (1) Data denoising methods based on multi-features, which screens out the query-related event data from massive background data. (2) Abnormal events detection methods based on statistical learning, which can detect anomalies by analyzing and mining a series of observations and statistics on the time axis. (3) Geographical position recognition, which is used to recognize regions where abnormal events may happen.
Unable to display preview. Download preview PDF.
- 1.Sakaki, T., Okazaki, M., Matsuo, Y.: Tweet analysis for real-time event detection and earthquake reporting system development. TKDE 25(4), 919–931 (2013)Google Scholar
- 2.Zhang, P., Zhou, C., Wang, P., Gao, B., Zhu, X., Guo, L.: E-tree: An efficient indexing structure for ensemble models on data streams. TKDE 27, 461–474 (2015)Google Scholar
- 4.Marcus, A., Bernstein, M., Badar, O.: Twitinfo: aggregating and visualizing microblogs for event exploration. In: Conference on Human Factors in Computing Systems, pp. 227–236 (2011)Google Scholar
- 5.MacEachren, A., Robinson, A., Jaiswal, A.: Geo-twitter analytics: applications in crisis management. In: 25th International Cartographic Conference, pp. 3–8 (2011)Google Scholar
- 6.Shan, D., Zhao, W., Chen, R.: Eventsearch: a system for event discovery and retrieval on multi-type historical data. In: KDD, pp. 1564–1567 (2012)Google Scholar