Abstract
Recently, social media, such as Twitter, has been success- fully used as a proxy to gauge the impacts of disasters in real time. However, most previous analyses of social media dur- ing disaster response focus on the magnitude and location of social media discussion. In this work, we explore the impact that disasters have on the underlying sentiment of social me- dia streams. During disasters, people may assume negative sentiments discussing lives lost and property damage, other people may assume encouraging responses to inspire and spread hope. Our goal is to explore the underlying trends in positive and negative sentiment with respect to disasters and geographically related sentiment. In this paper, we propose a novel visual analytics framework for sentiment visualiza- tion of geo-located Twitter data. The proposed framework consists of two components, sentiment modeling and geo- graphic visualization. In particular, we provide an entropy- based metric to model sentiment contained in social media data. The extracted sentiment is further integrated into a visualization framework to explore the uncertainty of public opinion. We explored Ebola Twitter dataset to show how vi- sual analytics techniques and sentiment modeling can reveal interesting patterns in disaster scenarios.
| Original language | English (US) |
|---|---|
| Title of host publication | WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 1211-1215 |
| Number of pages | 5 |
| ISBN (Print) | 9781450334730 |
| DOIs | |
| State | Published - May 18 2015 |
| Event | 24th International Conference on World Wide Web, WWW 2015 - Florence, Italy Duration: May 18 2015 → May 22 2015 |
Other
| Other | 24th International Conference on World Wide Web, WWW 2015 |
|---|---|
| Country | Italy |
| City | Florence |
| Period | 5/18/15 → 5/22/15 |
Fingerprint
ASJC Scopus subject areas
- Computer Networks and Communications
- Software
Cite this
Visualizing social media sentiment in disaster scenarios. / Lu, Yafeng; Hu, Xia; Wang, Feng; Kumar, Shamanth; Liu, Huan; Maciejewski, Ross.
WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web. Association for Computing Machinery, Inc, 2015. p. 1211-1215.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Visualizing social media sentiment in disaster scenarios
AU - Lu, Yafeng
AU - Hu, Xia
AU - Wang, Feng
AU - Kumar, Shamanth
AU - Liu, Huan
AU - Maciejewski, Ross
PY - 2015/5/18
Y1 - 2015/5/18
N2 - Recently, social media, such as Twitter, has been success- fully used as a proxy to gauge the impacts of disasters in real time. However, most previous analyses of social media dur- ing disaster response focus on the magnitude and location of social media discussion. In this work, we explore the impact that disasters have on the underlying sentiment of social me- dia streams. During disasters, people may assume negative sentiments discussing lives lost and property damage, other people may assume encouraging responses to inspire and spread hope. Our goal is to explore the underlying trends in positive and negative sentiment with respect to disasters and geographically related sentiment. In this paper, we propose a novel visual analytics framework for sentiment visualiza- tion of geo-located Twitter data. The proposed framework consists of two components, sentiment modeling and geo- graphic visualization. In particular, we provide an entropy- based metric to model sentiment contained in social media data. The extracted sentiment is further integrated into a visualization framework to explore the uncertainty of public opinion. We explored Ebola Twitter dataset to show how vi- sual analytics techniques and sentiment modeling can reveal interesting patterns in disaster scenarios.
AB - Recently, social media, such as Twitter, has been success- fully used as a proxy to gauge the impacts of disasters in real time. However, most previous analyses of social media dur- ing disaster response focus on the magnitude and location of social media discussion. In this work, we explore the impact that disasters have on the underlying sentiment of social me- dia streams. During disasters, people may assume negative sentiments discussing lives lost and property damage, other people may assume encouraging responses to inspire and spread hope. Our goal is to explore the underlying trends in positive and negative sentiment with respect to disasters and geographically related sentiment. In this paper, we propose a novel visual analytics framework for sentiment visualiza- tion of geo-located Twitter data. The proposed framework consists of two components, sentiment modeling and geo- graphic visualization. In particular, we provide an entropy- based metric to model sentiment contained in social media data. The extracted sentiment is further integrated into a visualization framework to explore the uncertainty of public opinion. We explored Ebola Twitter dataset to show how vi- sual analytics techniques and sentiment modeling can reveal interesting patterns in disaster scenarios.
UR - http://www.scopus.com/inward/record.url?scp=84968538112&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84968538112&partnerID=8YFLogxK
U2 - 10.1145/2740908.2741720
DO - 10.1145/2740908.2741720
M3 - Conference contribution
SN - 9781450334730
SP - 1211
EP - 1215
BT - WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web
PB - Association for Computing Machinery, Inc
ER -