Details
Original language | English |
---|---|
Title of host publication | ISCRAM 2019 - Proceedings |
Subtitle of host publication | 16th International Conference on Information Systems for Crisis Response and Management |
Editors | Zeno Franco, Jose J. Gonzalez, Jose H. Canos |
Pages | 923-931 |
Number of pages | 9 |
ISBN (electronic) | 9788409104987 |
Publication status | Published - 2019 |
Event | 16th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2019 - Valencia, Spain Duration: 19 May 2019 → 22 May 2019 |
Publication series
Name | Proceedings of the International ISCRAM Conference |
---|---|
Volume | 2019-May |
ISSN (electronic) | 2411-3387 |
Abstract
When a major event such as a crisis situation occurs, people post messages on social media sites such as Twitter, in order to exchange information or to share emotions. These posts can provide useful information to raise situation awareness and support decision making, e.g., by aid organizations. In this paper, we propose a novel method for social media crawling, which exploits a Bayesian inference framework to keep track of keyword changes over time and uses a counter-stream to gauge the inclusion of noise and irrelevant information. In addition, we present a framework to evaluate real-time adaptive social search algorithms in a reproducible manner, which relies on a semi-automated approach for ground-truth construction. We show that our method outperforms previous methods for very large scale events.
Keywords
- Adaptive crawler, Crsis communication, Event tracking, Real-time adaptive search
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Information Systems
- Decision Sciences(all)
- Information Systems and Management
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
ISCRAM 2019 - Proceedings: 16th International Conference on Information Systems for Crisis Response and Management. ed. / Zeno Franco; Jose J. Gonzalez; Jose H. Canos. 2019. p. 923-931 (Proceedings of the International ISCRAM Conference; Vol. 2019-May).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Real-time adaptive crawler for tracking unfolding events on Twitter
AU - Hadgu, Asmelash Teka
AU - Abualhaija, Sallam
AU - Niederée, Claudia
N1 - Funding Information: We would like to thank Damianos P. Melidis, Negacy D. Hailu and the anonymous reviewers for their valuable feedback on the manuscript.
PY - 2019
Y1 - 2019
N2 - When a major event such as a crisis situation occurs, people post messages on social media sites such as Twitter, in order to exchange information or to share emotions. These posts can provide useful information to raise situation awareness and support decision making, e.g., by aid organizations. In this paper, we propose a novel method for social media crawling, which exploits a Bayesian inference framework to keep track of keyword changes over time and uses a counter-stream to gauge the inclusion of noise and irrelevant information. In addition, we present a framework to evaluate real-time adaptive social search algorithms in a reproducible manner, which relies on a semi-automated approach for ground-truth construction. We show that our method outperforms previous methods for very large scale events.
AB - When a major event such as a crisis situation occurs, people post messages on social media sites such as Twitter, in order to exchange information or to share emotions. These posts can provide useful information to raise situation awareness and support decision making, e.g., by aid organizations. In this paper, we propose a novel method for social media crawling, which exploits a Bayesian inference framework to keep track of keyword changes over time and uses a counter-stream to gauge the inclusion of noise and irrelevant information. In addition, we present a framework to evaluate real-time adaptive social search algorithms in a reproducible manner, which relies on a semi-automated approach for ground-truth construction. We show that our method outperforms previous methods for very large scale events.
KW - Adaptive crawler
KW - Crsis communication
KW - Event tracking
KW - Real-time adaptive search
UR - http://www.scopus.com/inward/record.url?scp=85077747897&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85077747897
T3 - Proceedings of the International ISCRAM Conference
SP - 923
EP - 931
BT - ISCRAM 2019 - Proceedings
A2 - Franco, Zeno
A2 - Gonzalez, Jose J.
A2 - Canos, Jose H.
T2 - 16th International Conference on Information Systems for Crisis Response and Management, ISCRAM 2019
Y2 - 19 May 2019 through 22 May 2019
ER -