toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author (up) Hongmin Li; Xukun Li; Doina Caragea; Cornelia Caragea pdf  openurl
  Title Comparison of Word Embeddings and Sentence Encodings for Generalized Representations in Crisis Tweet Classifications Type Conference Article
  Year 2018 Publication Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. Abbreviated Journal Iscram Ap 2018  
  Volume Issue Pages 480-493  
  Keywords Word Embeddings, Sentence Encodings, Reduced Tweet Representation, Crisis Tweet Classification  
  Abstract Many machine learning and natural language processing techniques, including supervised and domain adaptation algorithms, have been proposed and studied in the context of filtering crisis tweets. However, applying these approaches in real-time is still challenging because of time-critical requirements of emergency response operations and also diversities and unique characteristics of emergency events. In this paper, we explore the idea of building “generalized” classifiers for filtering crisis tweets that can be pre-trained, and are thus ready to use in real-time, while generalizing well on future disasters/crises data. We propose to achieve this using simple feature based adaptation with tweet representations based on word embeddings and also sentence-level embeddings, representations which do not rely on unlabeled data to achieve domain adaptations and can be easily implemented. Given that there are different types of word/sentence embeddings that are widely used, we propose to compare them to get a general idea about which type works better with crisis tweets classification tasks. Our experimental results show that GloVe embeddings in general work better with the datasets used in our evaluation, and that the supervised algorithms used in our experiments benefit from GloVe embeddings trained specifically on crisis data. Furthermore, our experimental results show that following GloVe, the sentence embeddings have great potential in crisis tweet tasks.  
  Address Kansas State University; Kansas State University; Kansas State University; Kansas State University  
  Corporate Author Thesis  
  Publisher Massey Univeristy Place of Publication Albany, Auckland, New Zealand Editor Kristin Stock; Deborah Bunker  
  Language English Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Track Social Media and Community Engagement Supporting Resilience Building Expedition Conference  
  Notes Approved no  
  Call Number Serial 1689  
Share this record to Facebook
 

 
Author (up) Xukun Li; Doina Caragea pdf  isbn
openurl 
  Title Improving Disaster-related Tweet Classification with a Multimodal Approach Type Conference Article
  Year 2020 Publication ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal Iscram 2020  
  Volume Issue Pages 893-902  
  Keywords Multimodal Model; Tweet Classification; Deep Learning  
  Abstract Social media data analysis is important for disaster management. Lots of prior studies have focused on classifying a tweet based on its text or based on its images, independently, even if the tweet contains both text and images. Under the assumptions that text and images may contain complementary information, it is of interest to construct classifiers that make use of both modalities of the tweet. Towards this goal, we propose a multimodal classification model which aggregates text and image information. Our study aims to provide insights into the benefits obtained by combining text and images, and to understand what type of modality is more informative with respect to disaster tweet classification. Experimental results show that both text and image classification can be improved by the multimodal approach.  
  Address Department of Computer Science, Kansas State University; Department of Computer Science, Kansas State University  
  Corporate Author Thesis  
  Publisher Virginia Tech Place of Publication Blacksburg, VA (USA) Editor Amanda Hughes; Fiona McNeill; Christopher W. Zobel  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 978-1-949373-27-79 ISBN 2411-3465 Medium  
  Track Social Media for Disaster Response and Resilie Expedition Conference 17th International Conference on Information Systems for Crisis Response and Management  
  Notes xukun@ksu.edu Approved no  
  Call Number Serial 2280  
Share this record to Facebook
 

 
Author (up) Xukun Li; Doina Caragea; Cornelia Caragea; Muhammad Imran; Ferda Ofli pdf  isbn
openurl 
  Title Identifying Disaster Damage Images Using a Domain Adaptation Approach Type Conference Article
  Year 2019 Publication Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management Abbreviated Journal Iscram 2019  
  Volume Issue Pages  
  Keywords image classification, disaster damage, domain adaptation, domain adversarial neural networks.  
  Abstract Approaches for effectively filtering useful situational awareness information posted by eyewitnesses of disasters,

in real time, are greatly needed. While many studies have focused on filtering textual information, the research

on filtering disaster images is more limited. In particular, there are no studies on the applicability of domain

adaptation to filter images from an emergent target disaster, when no labeled data is available for the target disaster.

To fill in this gap, we propose to apply a domain adaptation approach, called domain adversarial neural networks

(DANN), to the task of identifying images that show damage. The DANN approach has VGG-19 as its backbone,

and uses the adversarial training to find a transformation that makes the source and target data indistinguishable.

Experimental results on several pairs of disasters suggest that the DANN model generally gives similar or better

results as compared to the VGG-19 model fine-tuned on the source labeled data.
 
  Address Department of Computer Science, Kansas State University, United States of America;Department of Computer Science, University of Illinois at Chicago, United States of America;Qatar Computing Research Institute, Hamad Bin Khalifa University, Qatar  
  Corporate Author Thesis  
  Publisher Iscram Place of Publication Valencia, Spain Editor Franco, Z.; González, J.J.; Canós, J.H.  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2411-3387 ISBN 978-84-09-10498-7 Medium  
  Track T8- Social Media in Crises and Conflicts Expedition Conference 16th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2019)  
  Notes Approved no  
  Call Number Serial 1853  
Share this record to Facebook
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: