Applying traditional signal processing techniques to social media exploitation for situational understanding

Tarek Abdelzaher, Heather Roy, Shiguang Wang, Prasanna Giridhar, Md Tanvir Al Amin, Elizabeth K. Bowman, Michael A. Kolodny

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

Abstract

Signal processing techniques such as filtering, detection, estimation and frequency domain analysis have long been applied to extract information from noisy sensor data. This paper describes the exploitation of these signal processing techniques to extract information from social networks, such as Twitter and Instagram. Specifically, we view social networks as noisy sensors that report events in the physical world. We then present a data processing stack for detection, localization, tracking, and veracity analysis of reported events using social network data. We show using a controlled experiment that the behavior of social sources as information relays varies dramatically depending on context. In benign contexts, there is general agreement on events, whereas in conflict scenarios, a significant amount of collective filtering is introduced by conflicted groups, creating a large data distortion. We describe signal processing techniques that mitigate such distortion, resulting in meaningful approximations of actual ground truth, given noisy reported observations. Finally, we briefly present an implementation of the aforementioned social network data processing stack in a sensor network analysis toolkit, called Apollo. Experiences with Apollo show that our techniques are successful at identifying and tracking credible events in the physical world.

Original languageEnglish (US)
Title of host publicationGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII
EditorsMichael A. Kolodny, Tien Pham
PublisherSPIE
ISBN (Electronic)9781510600720
DOIs
StatePublished - Jan 1 2016
EventGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII - Baltimore, United States
Duration: Apr 18 2016Apr 20 2016

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume9831
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherGround/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII
CountryUnited States
CityBaltimore
Period4/18/164/20/16

Fingerprint

Social Media
exploitation
Exploitation
Social Networks
Signal Processing
signal processing
Signal processing
sensors
Frequency domain analysis
Filtering
Sensors
Electric network analysis
frequency domain analysis
Frequency Domain Analysis
network analysis
Sensor
Sensor networks
ground truth
Large Data
Network Analysis

Keywords

  • Social networks
  • signal processing.

ASJC Scopus subject areas

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

Cite this

Abdelzaher, T., Roy, H., Wang, S., Giridhar, P., Al Amin, M. T., Bowman, E. K., & Kolodny, M. A. (2016). Applying traditional signal processing techniques to social media exploitation for situational understanding. In M. A. Kolodny, & T. Pham (Eds.), Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII [98310R] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9831). SPIE. https://doi.org/10.1117/12.2229723

Applying traditional signal processing techniques to social media exploitation for situational understanding. / Abdelzaher, Tarek; Roy, Heather; Wang, Shiguang; Giridhar, Prasanna; Al Amin, Md Tanvir; Bowman, Elizabeth K.; Kolodny, Michael A.

Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII. ed. / Michael A. Kolodny; Tien Pham. SPIE, 2016. 98310R (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9831).

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

Abdelzaher, T, Roy, H, Wang, S, Giridhar, P, Al Amin, MT, Bowman, EK & Kolodny, MA 2016, Applying traditional signal processing techniques to social media exploitation for situational understanding. in MA Kolodny & T Pham (eds), Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII., 98310R, Proceedings of SPIE - The International Society for Optical Engineering, vol. 9831, SPIE, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII, Baltimore, United States, 4/18/16. https://doi.org/10.1117/12.2229723
Abdelzaher T, Roy H, Wang S, Giridhar P, Al Amin MT, Bowman EK et al. Applying traditional signal processing techniques to social media exploitation for situational understanding. In Kolodny MA, Pham T, editors, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII. SPIE. 2016. 98310R. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2229723
Abdelzaher, Tarek ; Roy, Heather ; Wang, Shiguang ; Giridhar, Prasanna ; Al Amin, Md Tanvir ; Bowman, Elizabeth K. ; Kolodny, Michael A. / Applying traditional signal processing techniques to social media exploitation for situational understanding. Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII. editor / Michael A. Kolodny ; Tien Pham. SPIE, 2016. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{66caea76ea5143ffa9e1ed9a159d4410,
title = "Applying traditional signal processing techniques to social media exploitation for situational understanding",
abstract = "Signal processing techniques such as filtering, detection, estimation and frequency domain analysis have long been applied to extract information from noisy sensor data. This paper describes the exploitation of these signal processing techniques to extract information from social networks, such as Twitter and Instagram. Specifically, we view social networks as noisy sensors that report events in the physical world. We then present a data processing stack for detection, localization, tracking, and veracity analysis of reported events using social network data. We show using a controlled experiment that the behavior of social sources as information relays varies dramatically depending on context. In benign contexts, there is general agreement on events, whereas in conflict scenarios, a significant amount of collective filtering is introduced by conflicted groups, creating a large data distortion. We describe signal processing techniques that mitigate such distortion, resulting in meaningful approximations of actual ground truth, given noisy reported observations. Finally, we briefly present an implementation of the aforementioned social network data processing stack in a sensor network analysis toolkit, called Apollo. Experiences with Apollo show that our techniques are successful at identifying and tracking credible events in the physical world.",
keywords = "Social networks, signal processing.",
author = "Tarek Abdelzaher and Heather Roy and Shiguang Wang and Prasanna Giridhar and {Al Amin}, {Md Tanvir} and Bowman, {Elizabeth K.} and Kolodny, {Michael A.}",
year = "2016",
month = "1",
day = "1",
doi = "10.1117/12.2229723",
language = "English (US)",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Kolodny, {Michael A.} and Tien Pham",
booktitle = "Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII",

}

TY - GEN

T1 - Applying traditional signal processing techniques to social media exploitation for situational understanding

AU - Abdelzaher, Tarek

AU - Roy, Heather

AU - Wang, Shiguang

AU - Giridhar, Prasanna

AU - Al Amin, Md Tanvir

AU - Bowman, Elizabeth K.

AU - Kolodny, Michael A.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Signal processing techniques such as filtering, detection, estimation and frequency domain analysis have long been applied to extract information from noisy sensor data. This paper describes the exploitation of these signal processing techniques to extract information from social networks, such as Twitter and Instagram. Specifically, we view social networks as noisy sensors that report events in the physical world. We then present a data processing stack for detection, localization, tracking, and veracity analysis of reported events using social network data. We show using a controlled experiment that the behavior of social sources as information relays varies dramatically depending on context. In benign contexts, there is general agreement on events, whereas in conflict scenarios, a significant amount of collective filtering is introduced by conflicted groups, creating a large data distortion. We describe signal processing techniques that mitigate such distortion, resulting in meaningful approximations of actual ground truth, given noisy reported observations. Finally, we briefly present an implementation of the aforementioned social network data processing stack in a sensor network analysis toolkit, called Apollo. Experiences with Apollo show that our techniques are successful at identifying and tracking credible events in the physical world.

AB - Signal processing techniques such as filtering, detection, estimation and frequency domain analysis have long been applied to extract information from noisy sensor data. This paper describes the exploitation of these signal processing techniques to extract information from social networks, such as Twitter and Instagram. Specifically, we view social networks as noisy sensors that report events in the physical world. We then present a data processing stack for detection, localization, tracking, and veracity analysis of reported events using social network data. We show using a controlled experiment that the behavior of social sources as information relays varies dramatically depending on context. In benign contexts, there is general agreement on events, whereas in conflict scenarios, a significant amount of collective filtering is introduced by conflicted groups, creating a large data distortion. We describe signal processing techniques that mitigate such distortion, resulting in meaningful approximations of actual ground truth, given noisy reported observations. Finally, we briefly present an implementation of the aforementioned social network data processing stack in a sensor network analysis toolkit, called Apollo. Experiences with Apollo show that our techniques are successful at identifying and tracking credible events in the physical world.

KW - Social networks

KW - signal processing.

UR - http://www.scopus.com/inward/record.url?scp=84987853187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987853187&partnerID=8YFLogxK

U2 - 10.1117/12.2229723

DO - 10.1117/12.2229723

M3 - Conference contribution

AN - SCOPUS:84987853187

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VII

A2 - Kolodny, Michael A.

A2 - Pham, Tien

PB - SPIE

ER -