Kiran Zahra, Muhammad Imran, & Frank O Ostermann. (2018). Understanding eyewitness reports on Twitter during disasters. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 687–695). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Social media platforms such as Twitter provide convenient ways to share and consume important information during disasters and emergencies. Information from bystanders and eyewitnesses can be useful for law enforcement agencies and humanitarian organizations to get firsthand and credible information about an ongoing situation to gain situational awareness among other uses. However, identification of eyewitness reports on Twitter is challenging for many reasons. This work investigates the sources of tweets and classifies them into three types (i) direct eyewitnesses, (ii) indirect eyewitness, and (iii) vulnerable accounts. Moreover, we investigate various characteristics associated with each kind of eyewitness account. We observe that words related to perceptual senses (feeling, seeing, hearing) tend to be present in direct eyewitness messages, whereas emotions, thoughts, and prayers are more common in indirect witnesses. We believe these characteristics can help make more efficient computational methods and systems in the future for automatic identification of eyewitness accounts.
|
Venkata Kishore Neppalli, Cornelia Caragea, & Doina Caragea. (2018). Deep Neural Networks versus Naive Bayes Classifiers for Identifying Informative Tweets during Disasters. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 677–686). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In this paper, we focus on understanding the effectiveness of deep neural networks by comparison with the effectiveness of standard classifiers that use carefully engineered features. Specifically, we design various feature sets (based on tweet content, user details and polarity clues) and use these feature sets individually or in various combinations, with Naïve Bayes classifiers. Furthermore, we develop neural models based on Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) with handcrafted architectures. We compare the two types of approaches in the context of identifying informative tweets posted during disasters, and show that the deep neural networks, in particular the CNN networks, are more effective for the task considered.
|
