TY - GEN
T1 - Automatic information retrieval from tweets
T2 - 17th Annual International Conference on Information Systems for Crisis Response and Management, ISCRAM 2020
AU - Coche, Julien
AU - Montarnal, Aurelie
AU - Tapia, Andrea
AU - Benaben, Frederick
N1 - Publisher Copyright:
© 2020 Information Systems for Crisis Response and Management, ISCRAM. All rights reserved.
PY - 2020
Y1 - 2020
N2 - Much has been said about the value of social media messages for emergency services. The new uses related to these platforms bring users to share information, otherwise unknown in crisis events. Thus, many studies have been performed in order to identify tweets relating to a crisis event or to classify these tweets according to certain categories. However, determining the relevant information contained in the messages collected remains the responsibility of the emergency services. In this article, we introduce the issue of classifying the information contained in the messages. To do so, we use classes such as those used by the operators in the call centers. Particularly we show that this problem is related to named entities recognition on tweets. We then explain that a semi-supervised approach might be beneficial, as the volume of data to perform this task is low. In a second part, we present some of the challenges raised by this problematic and different ways to answer it. Finally, we explore one of them and its possible outcomes.
AB - Much has been said about the value of social media messages for emergency services. The new uses related to these platforms bring users to share information, otherwise unknown in crisis events. Thus, many studies have been performed in order to identify tweets relating to a crisis event or to classify these tweets according to certain categories. However, determining the relevant information contained in the messages collected remains the responsibility of the emergency services. In this article, we introduce the issue of classifying the information contained in the messages. To do so, we use classes such as those used by the operators in the call centers. Particularly we show that this problem is related to named entities recognition on tweets. We then explain that a semi-supervised approach might be beneficial, as the volume of data to perform this task is low. In a second part, we present some of the challenges raised by this problematic and different ways to answer it. Finally, we explore one of them and its possible outcomes.
UR - http://www.scopus.com/inward/record.url?scp=85108331482&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108331482&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85108331482
T3 - Proceedings of the International ISCRAM Conference
SP - 134
EP - 141
BT - ISCRAM 2020 - Proceedings
A2 - Hughes, Amanda Lee
A2 - McNeill, Fiona
A2 - Zobel, Christopher W.
PB - Information Systems for Crisis Response and Management, ISCRAM
Y2 - 23 May 2021
ER -