The event tracking dashboard: From multilingual social media feeds to event patterns and anomalies

Prasanna Giridhar, Jongdeog Lee, Tarek Abdelzaher, Lance Kaplan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The proliferation of real-time information on social media opens up unprecedented opportunities for situation awareness that arise from extracting unfolding physical events from their social media footprints. The paper describes experiences with a new social media analysis toolkit for detecting and tracking such physical events. A key advantage of the explored analysis algorithms is that they require no prior training, and as such can operate out-of-the-box on new languages, dialects, jargon, and application domains (where by »new», we mean new to the machine), including detection of protests, natural disasters, acts of terror, accidents, and other disruptions. By running the toolkit over a period of time, patterns and anomalies are also detected that offer additional insights and understanding. Through analysis of contemporary political, military, and natural disaster events, the work explores the limits of the training-free approach and demonstrates promise and applicability.

Original languageEnglish (US)
Title of host publicationNext-Generation Analyst VI
PublisherSPIE
Volume10653
ISBN (Electronic)9781510618176
DOIs
StatePublished - Jan 1 2018
EventNext-Generation Analyst VI 2018 - Orlando, United States
Duration: Apr 16 2018Apr 17 2018

Other

OtherNext-Generation Analyst VI 2018
CountryUnited States
CityOrlando
Period4/16/184/17/18

Fingerprint

Social Media
Disasters
Anomaly
disasters
anomalies
Disaster
education
Situation Awareness
Accidents
Algorithm Analysis
footprints
Unfolding
accidents
Proliferation
Period of time
Military
Real-time
Demonstrate
Training

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Giridhar, P., Lee, J., Abdelzaher, T., & Kaplan, L. (2018). The event tracking dashboard: From multilingual social media feeds to event patterns and anomalies. In Next-Generation Analyst VI (Vol. 10653). [106530V] SPIE. https://doi.org/10.1117/12.2306712

The event tracking dashboard : From multilingual social media feeds to event patterns and anomalies. / Giridhar, Prasanna; Lee, Jongdeog; Abdelzaher, Tarek; Kaplan, Lance.

Next-Generation Analyst VI. Vol. 10653 SPIE, 2018. 106530V.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Giridhar, P, Lee, J, Abdelzaher, T & Kaplan, L 2018, The event tracking dashboard: From multilingual social media feeds to event patterns and anomalies. in Next-Generation Analyst VI. vol. 10653, 106530V, SPIE, Next-Generation Analyst VI 2018, Orlando, United States, 4/16/18. https://doi.org/10.1117/12.2306712
Giridhar, Prasanna ; Lee, Jongdeog ; Abdelzaher, Tarek ; Kaplan, Lance. / The event tracking dashboard : From multilingual social media feeds to event patterns and anomalies. Next-Generation Analyst VI. Vol. 10653 SPIE, 2018.
@inproceedings{4c2bc64a85c24e0b9041e43a6137e77a,
title = "The event tracking dashboard: From multilingual social media feeds to event patterns and anomalies",
abstract = "The proliferation of real-time information on social media opens up unprecedented opportunities for situation awareness that arise from extracting unfolding physical events from their social media footprints. The paper describes experiences with a new social media analysis toolkit for detecting and tracking such physical events. A key advantage of the explored analysis algorithms is that they require no prior training, and as such can operate out-of-the-box on new languages, dialects, jargon, and application domains (where by »new», we mean new to the machine), including detection of protests, natural disasters, acts of terror, accidents, and other disruptions. By running the toolkit over a period of time, patterns and anomalies are also detected that offer additional insights and understanding. Through analysis of contemporary political, military, and natural disaster events, the work explores the limits of the training-free approach and demonstrates promise and applicability.",
author = "Prasanna Giridhar and Jongdeog Lee and Tarek Abdelzaher and Lance Kaplan",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2306712",
language = "English (US)",
volume = "10653",
booktitle = "Next-Generation Analyst VI",
publisher = "SPIE",

}

TY - GEN

T1 - The event tracking dashboard

T2 - From multilingual social media feeds to event patterns and anomalies

AU - Giridhar, Prasanna

AU - Lee, Jongdeog

AU - Abdelzaher, Tarek

AU - Kaplan, Lance

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The proliferation of real-time information on social media opens up unprecedented opportunities for situation awareness that arise from extracting unfolding physical events from their social media footprints. The paper describes experiences with a new social media analysis toolkit for detecting and tracking such physical events. A key advantage of the explored analysis algorithms is that they require no prior training, and as such can operate out-of-the-box on new languages, dialects, jargon, and application domains (where by »new», we mean new to the machine), including detection of protests, natural disasters, acts of terror, accidents, and other disruptions. By running the toolkit over a period of time, patterns and anomalies are also detected that offer additional insights and understanding. Through analysis of contemporary political, military, and natural disaster events, the work explores the limits of the training-free approach and demonstrates promise and applicability.

AB - The proliferation of real-time information on social media opens up unprecedented opportunities for situation awareness that arise from extracting unfolding physical events from their social media footprints. The paper describes experiences with a new social media analysis toolkit for detecting and tracking such physical events. A key advantage of the explored analysis algorithms is that they require no prior training, and as such can operate out-of-the-box on new languages, dialects, jargon, and application domains (where by »new», we mean new to the machine), including detection of protests, natural disasters, acts of terror, accidents, and other disruptions. By running the toolkit over a period of time, patterns and anomalies are also detected that offer additional insights and understanding. Through analysis of contemporary political, military, and natural disaster events, the work explores the limits of the training-free approach and demonstrates promise and applicability.

UR - http://www.scopus.com/inward/record.url?scp=85049682157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049682157&partnerID=8YFLogxK

U2 - 10.1117/12.2306712

DO - 10.1117/12.2306712

M3 - Conference contribution

AN - SCOPUS:85049682157

VL - 10653

BT - Next-Generation Analyst VI

PB - SPIE

ER -