TEDAS: A Twitter-based Event Detection and Analysis System

By Rui Li, Kin Hou Lei, Ravi V. Khadiwala, Kevin Chen-Chuan Chang. IEEE International Conference on Data Engineering, 2012

475 citations recorded by the source corpus.

Subfields: Communication, Computer Networks and Communications, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/6ba401b333ed4ed97c78863929533acdecd1133c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

1. Carlos Castillo
2. Muhammad Imran
3. Fernando Diaz
4. Sarah Vieweg
5. Francesco Marcelloni
6. Alexandra Olteanu
7. Gabriella Kazai

In Computer Networks and Communications

1. Robert Power
2. Jing Gao
3. Qi He
4. Fernando Diaz
5. Anwitaman Datta
6. Carlos Castillo
7. Fabián Riquelme
8. Aixin Sun

In Statistical and Nonlinear Physics

1. Muhammad Imran
2. Fernando Diaz
3. Carlos Castillo
4. Sarah Vieweg
5. Francesco Marcelloni
6. Fabián Riquelme
7. Pablo Gonzalez Cantergiani
8. Robert Power

Citations in the corpus

• Measuring user influence on Twitter: A survey (2015, background): “Only in Twitter, spread of influence has been used for different purposes, such as political sciences [85], human mobility [47], transportation [79], rumor spreading [12], epidemiology [125], among many others.”
• Processing Social Media Messages in Mass Emergency (2014, methodology): “n domain yes open no no [Mathioudakis and Koudas 2010] TwitInfo Burst detection earthquakes, crises yes kw spatial yes [Marcus et al. 2011] Twevent Burst segment detection open domain yes open no no [Li et al. 2012b] TEDAS supervised classification crime, disasters no kw yes no [Li et al. 2012a] Lead”
• Twevent: segment-based event detection from tweets (2012, background): “[18] proposed to detect crime and disaster related Events (CDE) from tweets.”
• Using Social Media to Enhance Emergency Situation Awareness: Extended Abstract (2015, background): “Disaster management using Twitter has recently been studied for humanitarian crises and natural disasters such as earthquakes, bushfires, and cyclones [Sakaki et al. , 2010; Vieweg et al. , 2010; Li et al. , 2012; McMinn et al. , 2014].”
• A deep learning approach for detecting traffic accidents from social media data (2018, methodology): “The common methods for detecting the traffic-related events include Support Vector Machine (D'Andrea et al., 2015; Schulz et al., 2013), natural language processing (Li et al., 2012; Wanichayapong et al., 2011), etc. which explore the semantic features in the keywords.”
• Real-Time Detection of Traffic From Twitter Stream Analysis (2015, background): “As Table VI clearly shows, the results achieved by our SVM classifier appreciably outperform those obtained in similar works in the literature [9], [12], [24], [31] despite they refer to different datasets.”