| |
Record |
Links |
|
Author  |
Zou, H.P.; Caragea, C.; Zhou, Y.; Caragea, D. |
|
| |
Title |
Semi-Supervised Few-Shot Learning for Fine-Grained Disaster Tweet Classification |
Type |
Conference Article |
| |
Year |
2023 |
Publication |
Proceedings of the 20th International ISCRAM Conference |
Abbreviated Journal |
Iscram 2023 |
|
| |
Volume |
|
Issue |
|
Pages |
385-395 |
|
| |
Keywords |
Crisis Tweet Classification; Semi-Supervised Few-Shot Learning; Pseudo-Labeling; TextMixUp. |
|
| |
Abstract |
The shared real-time information about natural disasters on social media platforms like Twitter and Facebook plays a critical role in informing volunteers, emergency managers, and response organizations. However, supervised learning models for monitoring disaster events require large amounts of annotated data, making them unrealistic for real-time use in disaster events. To address this challenge, we present a fine-grained disaster tweet classification model under the semi-supervised, few-shot learning setting where only a small number of annotated data is required. Our model, CrisisMatch, effectively classifies tweets into fine-grained classes of interest using few labeled data and large amounts of unlabeled data, mimicking the early stage of a disaster. Through integrating effective semi-supervised learning ideas and incorporating TextMixUp, CrisisMatch achieves performance improvement on two disaster datasets of 11.2% on average. Further analyses are also provided for the influence of the number of labeled data and out-of-domain results. |
|
| |
Address |
University of Illinois Chicago; Kansas State University |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
University of Nebraska at Omaha |
Place of Publication |
Omaha, USA |
Editor |
Jaziar Radianti; Ioannis Dokas; Nicolas Lalone; Deepak Khazanchi |
|
| |
Language |
English |
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
Hosssein Baharmand |
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
1 |
|
| |
ISSN |
2411-3387 |
ISBN |
979-8-218-21749-5 |
Medium |
|
|
| |
Track |
Social Media for Crisis Management |
Expedition |
|
Conference |
|
|
| |
Notes |
http://dx.doi.org/10.59297/FWXE4933 |
Approved |
no |
|
| |
Call Number |
ISCRAM @ idladmin @ |
Serial |
2533 |
|
| Share this record to Facebook |
