Hemant Purohit, & Jennifer Chan. (2017). Classifying User Types on Social Media to inform Who-What-Where Coordination during Crisis Response. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 656–665). Albi, France: Iscram.
Abstract: Timely information is essential for better dynamic situational awareness, which leads to efficient resource planning, coordination, and action. However, given the scale and outreach of social media�a key information sharing platform during crises, diverse types of users participate in discussions during crises, which affect the vetting of information for dynamic situational awareness and response coordination activities. In this paper, we present a user analysis on Twitter during crises for three major user types�Organization, Organizationaffiliated (a person�s self-identifying affiliation with an organization in his/her profile), and Non-affiliated (person not identifying any affiliation), by first classifying users and then presenting their communication patterns during two recent crises. Our analysis shows distinctive patterns of the three user types for participation and communication on social media during crises. Such a user-centric approach to study information sharing during crisis events can act as a precursor to deeper domain-driven content analysis for response agencies.
|
|
Shane Errol Halse, Aurélie Montarnal, Andrea Tapia, & Frederick Benaben. (2018). Bad Weather Coming: Linking social media and weather sensor data. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 507–515). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In this paper we leverage the power of citizen supplied data. We examined how both physical weather sensor data (obtained from the weather underground API) and social media data (obtained from Twitter) can serve to improve local community awareness during a severe weather event. A local tornado warning was selected due to its small scale and isolated geographic area, and only Twitter data found from within this geo-locational area was used. Our results indicate that during a severe weather event, an increase in weather activity obtained from the local weather sensors does correlate with an increase in local social media usage. The data found on social media also contains additional information from, and about the community of interest during the event. While this study focuses on a small scale event, it provides the groundwork for use during a much larger weather event.
|
|
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.
|
|
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.
|
|
Reza Mazloom, HongMin Li, Doina Caragea, Muhammad Imran, & Cornelia Caragea. (2018). Classification of Twitter Disaster Data Using a Hybrid Feature-Instance Adaptation Approach. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 727–735). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Huge amounts of data that are generated on social media during emergency situations are regarded as troves of critical information. The use of supervised machine learning techniques in the early stages of a disaster is challenged by the lack of labeled data for that particular disaster. Furthermore, supervised models trained on labeled data from a prior disaster may not produce accurate results, given the inherent variation between the current and the prior disasters. To address the challenges posed by the lack of labeled data for a target disaster, we propose to use a hybrid feature-instance adaptation approach based on matrix factorization and the k nearest neighbors algorithm, respectively. The proposed hybrid adaptation approach is used to select a subset of the source disaster data that is representative for the target disaster. The selected subset is subsequently used to learn accurate Naive Bayes classifiers for the target disaster.
|
|