toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Record Links
Author Hongmin Li; Doina Caragea; Cornelia Caragea pdf  openurl
  Title Combining Self-training with Deep Learning for Disaster Tweet Classification Type Conference Article
  Year (down) 2021 Publication ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal Iscram 2021  
  Volume Issue Pages 719-730  
  Keywords Domain Adaptation, Self-training, Crisis Tweets Classification, BERT, CNN  
  Abstract Significant progress has been made towards automated classification of disaster or crisis related tweets using machine learning approaches. Deep learning models, such as Convolutional Neural Networks (CNN), domain adaptation approaches based on self-training, and approaches based on pre-trained language models, such as BERT, have been proposed and used independently for disaster tweet classification. In this paper, we propose to combine self-training with CNN and BERT models, respectively, to improve the performance on the task of identifying crisis related tweets in a target disaster where labeled data is assumed to be unavailable, while unlabeled data is available. We evaluate the resulting self-training models on three crisis tweet collections and find that: 1) the pre-trained language model BERTweet is better than the standard BERT model, when fine-tuned for downstream crisis tweets classification; 2) self-training can help improve the performance of the CNN and BERTweet models for larger unlabeled target datasets, but not for smaller datasets.  
  Address Department of Computer Science, Kansas State University; Department of Computer Science, Kansas State University; Department of Computer Science, University of Illinois at Chicago  
  Corporate Author Thesis  
  Publisher Virginia Tech Place of Publication Blacksburg, VA (USA) Editor Anouck Adrot; Rob Grace; Kathleen Moore; Christopher W. Zobel  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 978-1-949373-61-5 ISBN Medium  
  Track Social Media for Disaster Response and Resilience Expedition Conference 18th International Conference on Information Systems for Crisis Response and Management  
  Notes hongminli@ksu.edu Approved no  
  Call Number ISCRAM @ idladmin @ Serial 2367  
Share this record to Facebook
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: