toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
  Record Links
Author (up) Jens Kersten; Jan Bongard; Friederike Klan pdf  isbn
  Title Gaussian Processes for One-class and Binary Classification of Crisis-related Tweets Type Conference Article
  Year 2022 Publication ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal Iscram 2022  
  Volume Issue Pages 664-673  
  Keywords Gaussian Process; One-class Classification; Twitter; Overload Reduction; Crisis Informatics  
  Abstract Overload reduction is essential to exploit Twitter text data for crisis management. Often used pre-trained machine learning models require training data for both, crisis-related and off-topic content. However, this task can also be formulated as a one-class classification problem in which labeled off-topic samples are not required. Gaussian processes (GPs) have great potential in both, binary and one-class settings and are therefore investigated in this work. Deep kernel learning combines the representative power of text embeddings with the Bayesian formalism of GPs. Motivated by this, we investigate the potential of deep kernel models for the task of classifying crisis-related tweet texts with special emphasis on cross-event applications. Compared to standard binary neural networks, first experiments with one-class GP models reveal a great potential for realistic scenarios, offering a fast and flexible approach for interactive model training without requiring off-topic training samples and comprehensive expert knowledge (only two model parameters involved).  
  Address German Aerospace Center– Jena, Germany; German Aerospace Center– Jena, Germany; German Aerospace Center– Jena, Germany  
  Corporate Author Thesis  
  Publisher Place of Publication Tarbes, France Editor Rob Grace; Hossein Baharmand  
  Language English Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2411-3387 ISBN 978-82-8427-099-9 Medium  
  Track Social Media for Crisis Management Expedition Conference  
  Notes Approved no  
  Call Number ISCRAM @ idladmin @ Serial 2446  
Share this record to Facebook
Select All    Deselect All
 |   | 

Save Citations:
Export Records: