Event detection in social media: A survey

@article{Nurwidyantoro2013EventDI,
  title={Event detection in social media: A survey},
  author={Arif Nurwidyantoro and Edi Winarko},
  journal={International Conference on ICT for Smart Society},
  year={2013},
  pages={1-5}
}
The emergence of social media open a lot of research opportunity. Information from social media could be used for many things, such as detecting event, predicting event, and even for early warning system. This paper describe topics related to analyzing social media for detecting four types of event, that is, disaster, traffic, outbreak, and news. Several approaches used to analyze social media data are also presented. 

Tables from this paper

A survey of event detection techniques in online social networks
TLDR
A survey is done for event detection techniques in OSN based on social text streams—newswire, web forums, emails, blogs and microblogs, for natural disasters, trending or emerging topics and public opinion-based events.
Towards Adaptive Event Detection Techniques for the Twitter Social Media Data Stream
TLDR
The work conducted in this research group intends to address stream-related challenges, such as detecting events incrementally, reporting them in (near) real-time, and coping with fluctuations and spikes in the social media data stream.
Design and Evaluation of Event Detection Techniques for Social Media Data Streams
TLDR
The run-time and task-based performance of several state-of-the-art event detection as well as baseline techniques using real-world Twitter streaming data are studied and a technique for real-time event detection and tracking is presented, which focuses on the streaming nature of the data.
An Architecture for Real-Time Massive Data Extraction from Social Media
TLDR
This work proposes to develop social models aimed at the extraction and prediction of event patterns based on online social media event detection in real-time, focused on the development of highly loaded, fault-tolerant, scalable system for social media data extraction and real- time analysis.
Editorial: Survey and Experimental Analysis of Event Detection Techniques for Twitter
TLDR
A series of measures are defined to support the quantitative and qualitative comparison and demonstrate the effectiveness of these measures by applying them to event detection techniques as well as to baseline approaches using real-world Twitter streaming data.
A survey of recent methods on deriving topics from Twitter: algorithm to evaluation
TLDR
A review of recent methods proposed to derive topics from social media platform from algorithms to evaluations and the gaps in the research this far and the problems that remain to be addressed are highlighted.
An Overview of Topic Discovery in Twitter Communication through Social Media Analytics
TLDR
An overview of conventional topic discovery methods, matching methods and their expected usefulness for social media analytics in Twitter ‐ the most popular microblogging platform.
Data fusion for city life event detection
TLDR
A simple yet effective method for discovering events from spatio-temporal datasets, based on statistical anomaly detection, that can combine multiple sources of information to improve results and generate a keyword-based description of the events being detected.
Real-Time Event Analysis and Spatial Information Extraction From Text Using Social Media Data
TLDR
This thesis elaborates on two distinct approaches to extract valuable information from social media data and sketches out the potential joint use case in the domain of natural disasters.
...
...

References

SHOWING 1-10 OF 26 REFERENCES
Event Detection in Social Media Data
TLDR
This paper presents four tasks: New Event Detection, Event Tracking, Event Summarization, and Event Association, and uses them to illustrate main purposes for performing event detection in social media space, and further present their application domains.
A Support Platform for Event Detection using Social Intelligence
TLDR
A system designed to support event detection over Twitter by querying the data stream with a user-specified set of keywords, filtering out non-English messages, and probabilistically geolocating each message.
Traffic Congestion and Social Media in China
TLDR
The construction of a dynamic evolution network is described, the transformation of online users' concentration is analyzed, and the geographic distribution of travelers is studied by analyzingOnline users' attributes.
Social media alert and response to threats to citizens (SMART-C)
TLDR
An overview of the SMART-C system, which is part of the social media initiative at the Department of Homeland Security, aims to enable robust bidirectional communication between emergency management and the public at large throughout the disaster life-cycle via a multitude of devices and modalities.
Event Detection in Twitter
TLDR
This paper attempts to tackle the challenges of event detection in Twitter with EDCoW (Event Detection with Clustering of Wavelet-based Signals), which builds signals for individual words by applying wavelet analysis on the frequencybased raw signals of the words.
Towards a realtime Twitter analysis during crises for operational crisis management
TLDR
Results indicate that automated filtering of information provides valuable information for operational response and crisis communication in real-time and automated analysis of Twitter messages during crises.
Streaming First Story Detection with application to Twitter
TLDR
This work presents an algorithm based on locality-sensitive hashing which is able to overcome the limitations of traditional approaches, while maintaining competitive results in event detection on web-scale corpora.
Hot topic detection in local areas using Twitter and Wikipedia
TLDR
A system that detects hot topic in a local area and during a particular period and a classification method that mitigates the variation of posted words related to the same topic is proposed.
Bieber no more : First Story Detection using Twitter and Wikipedia
TLDR
This paper examines whether Wikipedia (when viewed as a stream of page views) can be used to improve the quality of discovered events in Twitter and suggests that Wikipedia is a powerful filtering mechanism, allowing for easy blocking of large numbers of spurious events.
Social event detection with interaction graph modeling
TLDR
It is believed that online social interaction reflect important signals among the participants on the "social affinity" of two photos, thereby helping event detection, and compute social affinity via a random-walk on a social interaction graph to determine similarity between two photos on the graph.
...
...