Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition

Junghoon Chae, Dennis Thom, Harald Bosch, Yun Jang, Ross Maciejewski, David S. Ebert, Thomas Ertl

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

135 Citations (Scopus)

Abstract

Recent advances in technology have enabled social media services to support space-time indexed data, and internet users from all over the world have created a large volume of time-stamped, geo-located data. Such spatiotemporal data has immense value for increasing situational awareness of local events, providing insights for investigations and understanding the extent of incidents, their severity, and consequences, as well as their time-evolving nature. In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance. Hence, a relatively small volume of relevant messages may easily be obscured by a huge data set indicating normal situations. In this paper, we present a visual analytics approach that provides users with scalable and interactive social media data analysis and visualization including the exploration and examination of abnormal topics and events within various social media data sources, such as Twitter, Flickr and YouTube. In order to find and understand abnormal events, the analyst can first extract major topics from a set of selected messages and rank them probabilistically using Latent Dirichlet Allocation. He can then apply seasonal trend decomposition together with traditional control chart methods to find unusual peaks and outliers within topic time series. Our case studies show that situational awareness can be improved by incorporating the anomaly and trend examination techniques into a highly interactive visual analysis process.

Original languageEnglish (US)
Title of host publicationIEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings
Pages143-152
Number of pages10
DOIs
StatePublished - 2012
Event2012 IEEE Conference on Visual Analytics Science and Technology, VAST 2012 - Seattle, WA, United States
Duration: Oct 14 2012Oct 19 2012

Other

Other2012 IEEE Conference on Visual Analytics Science and Technology, VAST 2012
CountryUnited States
CitySeattle, WA
Period10/14/1210/19/12

Fingerprint

Data visualization
Time series
Internet
Decomposition
Control charts

Keywords

  • H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval - Information filtering, relevance feedback
  • H.5.2 [Information Interfaces and Presentation]: User Interfaces - GUI

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Chae, J., Thom, D., Bosch, H., Jang, Y., Maciejewski, R., Ebert, D. S., & Ertl, T. (2012). Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition. In IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings (pp. 143-152). [6400557] https://doi.org/10.1109/VAST.2012.6400557

Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition. / Chae, Junghoon; Thom, Dennis; Bosch, Harald; Jang, Yun; Maciejewski, Ross; Ebert, David S.; Ertl, Thomas.

IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings. 2012. p. 143-152 6400557.

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

Chae, J, Thom, D, Bosch, H, Jang, Y, Maciejewski, R, Ebert, DS & Ertl, T 2012, Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition. in IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings., 6400557, pp. 143-152, 2012 IEEE Conference on Visual Analytics Science and Technology, VAST 2012, Seattle, WA, United States, 10/14/12. https://doi.org/10.1109/VAST.2012.6400557
Chae J, Thom D, Bosch H, Jang Y, Maciejewski R, Ebert DS et al. Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition. In IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings. 2012. p. 143-152. 6400557 https://doi.org/10.1109/VAST.2012.6400557
Chae, Junghoon ; Thom, Dennis ; Bosch, Harald ; Jang, Yun ; Maciejewski, Ross ; Ebert, David S. ; Ertl, Thomas. / Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition. IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings. 2012. pp. 143-152
@inproceedings{564f06c7345f49a28501c306a29314a3,
title = "Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition",
abstract = "Recent advances in technology have enabled social media services to support space-time indexed data, and internet users from all over the world have created a large volume of time-stamped, geo-located data. Such spatiotemporal data has immense value for increasing situational awareness of local events, providing insights for investigations and understanding the extent of incidents, their severity, and consequences, as well as their time-evolving nature. In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance. Hence, a relatively small volume of relevant messages may easily be obscured by a huge data set indicating normal situations. In this paper, we present a visual analytics approach that provides users with scalable and interactive social media data analysis and visualization including the exploration and examination of abnormal topics and events within various social media data sources, such as Twitter, Flickr and YouTube. In order to find and understand abnormal events, the analyst can first extract major topics from a set of selected messages and rank them probabilistically using Latent Dirichlet Allocation. He can then apply seasonal trend decomposition together with traditional control chart methods to find unusual peaks and outliers within topic time series. Our case studies show that situational awareness can be improved by incorporating the anomaly and trend examination techniques into a highly interactive visual analysis process.",
keywords = "H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval - Information filtering, relevance feedback, H.5.2 [Information Interfaces and Presentation]: User Interfaces - GUI",
author = "Junghoon Chae and Dennis Thom and Harald Bosch and Yun Jang and Ross Maciejewski and Ebert, {David S.} and Thomas Ertl",
year = "2012",
doi = "10.1109/VAST.2012.6400557",
language = "English (US)",
isbn = "9781467347532",
pages = "143--152",
booktitle = "IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings",

}

TY - GEN

T1 - Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition

AU - Chae, Junghoon

AU - Thom, Dennis

AU - Bosch, Harald

AU - Jang, Yun

AU - Maciejewski, Ross

AU - Ebert, David S.

AU - Ertl, Thomas

PY - 2012

Y1 - 2012

N2 - Recent advances in technology have enabled social media services to support space-time indexed data, and internet users from all over the world have created a large volume of time-stamped, geo-located data. Such spatiotemporal data has immense value for increasing situational awareness of local events, providing insights for investigations and understanding the extent of incidents, their severity, and consequences, as well as their time-evolving nature. In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance. Hence, a relatively small volume of relevant messages may easily be obscured by a huge data set indicating normal situations. In this paper, we present a visual analytics approach that provides users with scalable and interactive social media data analysis and visualization including the exploration and examination of abnormal topics and events within various social media data sources, such as Twitter, Flickr and YouTube. In order to find and understand abnormal events, the analyst can first extract major topics from a set of selected messages and rank them probabilistically using Latent Dirichlet Allocation. He can then apply seasonal trend decomposition together with traditional control chart methods to find unusual peaks and outliers within topic time series. Our case studies show that situational awareness can be improved by incorporating the anomaly and trend examination techniques into a highly interactive visual analysis process.

AB - Recent advances in technology have enabled social media services to support space-time indexed data, and internet users from all over the world have created a large volume of time-stamped, geo-located data. Such spatiotemporal data has immense value for increasing situational awareness of local events, providing insights for investigations and understanding the extent of incidents, their severity, and consequences, as well as their time-evolving nature. In analyzing social media data, researchers have mainly focused on finding temporal trends according to volume-based importance. Hence, a relatively small volume of relevant messages may easily be obscured by a huge data set indicating normal situations. In this paper, we present a visual analytics approach that provides users with scalable and interactive social media data analysis and visualization including the exploration and examination of abnormal topics and events within various social media data sources, such as Twitter, Flickr and YouTube. In order to find and understand abnormal events, the analyst can first extract major topics from a set of selected messages and rank them probabilistically using Latent Dirichlet Allocation. He can then apply seasonal trend decomposition together with traditional control chart methods to find unusual peaks and outliers within topic time series. Our case studies show that situational awareness can be improved by incorporating the anomaly and trend examination techniques into a highly interactive visual analysis process.

KW - H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval - Information filtering, relevance feedback

KW - H.5.2 [Information Interfaces and Presentation]: User Interfaces - GUI

UR - http://www.scopus.com/inward/record.url?scp=84872940321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872940321&partnerID=8YFLogxK

U2 - 10.1109/VAST.2012.6400557

DO - 10.1109/VAST.2012.6400557

M3 - Conference contribution

AN - SCOPUS:84872940321

SN - 9781467347532

SP - 143

EP - 152

BT - IEEE Conference on Visual Analytics Science and Technology 2012, VAST 2012 - Proceedings

ER -