|   | 
Details
   web
Records
Author Shannon Daly; James A. Thom
Title Mining and Classifying Image Posts on Social Media to Analyse Fires Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Flickr; Image Analytics; Geotags; Geocoding
Abstract We propose a methodology to study the occurrence of fires through image posts on Flickr; crowd-sourcing information from a noisy social media dataset can estimate the presence of fires. We collect several years worth of photos and associated metadata using fire-related search terms. We use an image classification model to detect geotagged photos that are further analysed to determine if a fire event did occur at a particular time and place. Furthermore, a case study investigates image features and spatio-temporal elements in the metadata, as well as location information contained in camera EXIF data.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number ISCRAM @ idladmin @ Serial 1395
Share this record to Facebook
 

 
Author Muhammad Imran; Prasenjit Mitra; Jaideep Srivastava
Title Cross-Language Domain Adaptation for Classifying Crisis-Related Short Messages Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Social Media; Tweets Classification; Domain Adaptation
Abstract Rapid crisis response requires real-time analysis of messages. After a disaster happens, volunteers attempt to classify tweets to determine needs, e.g., supplies, infrastructure damage, etc. Given labeled data, supervised machine learning can help classify these messages. Scarcity of labeled data causes poor performance in machine training. Can we reuse old tweets to train classifiers? How can we choose labeled tweets for training? Specifically, we study the usefulness of labeled data of past events. Do labeled tweets in different language help? We observe the performance of our classifiers trained using different combinations of training sets obtained from past disasters. We perform extensive experimentation on real crisis datasets and show that the past labels are useful when both source and target events are of the same type (e.g. both earthquakes). For similar languages (e.g., Italian and Spanish), cross-language domain adaptation was useful, however, when for different languages (e.g., Italian and English), the performance decreased.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1396
Share this record to Facebook
 

 
Author Cornelia Caragea; Adrian Silvescu; Andrea Tapia
Title Identifying Informative Messages in Disasters using Convolutional Neural Networks Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Informative Tweets Classification; Disaster Events; Convolutional Neural Networks
Abstract Social media is a vital source of information during any major event, especially natural disasters. Data produced through social networking sites is seen as ubiquitous, rapid and accessible, and it is believed to empower average citizens to become more situationally aware during disasters and coordinate to help themselves. However, with the exponential increase in the volume of social media data, so comes the increase in data that are irrelevant to a disaster, thus, diminishing peoples? ability to find the information that they need in order to organize relief efforts, find help, and potentially save lives. In this paper, we present an approach to identifying informative messages in social media streams during disaster events. Our approach is based on Convolutional Neural Networks and shows significant improvement in performance over models that use the ?bag of words? and n-grams as features on several datasets of messages from flooding events.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1397
Share this record to Facebook
 

 
Author Emma Potter
Title Balancing conflicting operational and communications priorities: social media use in an emergency management organization Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Emergency Management; Social Media; Internal Communication; Disasters; Ethnography
Abstract Social media are now widely used by affected members of the public during an emergency. As these platforms have become mainstream, governments have responded to the public?s expectation that information is available online, particularly during disasters. Emergency management organizations (EMOs) now widely use social media to communicate with the public alongside occasional intelligence gathering. While EMOs increasingly use social media, breakdowns in internal communication can inhibit the dissemination of timely information to their online followers. Drawing on a two-year ethnography at the Queensland Fire and Emergency Services (QFES), an Australian EMO, this paper outlines how the organization uses social media to disseminate information during emergencies and identifies the internal tensions around its use. These tensions include the prioritization of operational duties over public information responsibilities, and the difficulties around requesting and receiving information from operational personnel located on the ground.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1398
Share this record to Facebook
 

 
Author Louis Ngamassi; Thiagarajan Ramakrishnan; Shahedur Rahman
Title Examining the Role of Social Media in Disaster Management from an Attribution Theory Perspective Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Attribution Theory; Social Media; Disaster Management; Disaster Management Phases
Abstract This paper is related to the use of social media for disaster management by humanitarian organizations. The past decade has seen a significant increase in the use of social media to manage humanitarian disasters. It seems, however, that it has still not been used to its full potential. In this paper, we examine the use of social media in disaster management through the lens of Attribution Theory. Attribution Theory posits that people look for the causes of events, especially unexpected and negative events. The two major characteristics of disasters are that they are unexpected and have negative outcomes/impacts. Thus, Attribution Theory may be a good fit for explaining social media adoption patterns by emergency managers. We propose a model, based on Attribution Theory, which is designed to understand the use of social media during the mitigation and preparedness phases of disaster management. We also discuss the theoretical contributions and some practical implications. This study is still in its nascent stage and is research in progress.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1399
Share this record to Facebook
 

 
Author Briony Jennifer Gray
Title Social Media and Disasters: A New Conceptual Framework Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Social Media; Conceptual Framework; Disaster Management; Web Accessibility; Information Reliability
Abstract Conceptual frameworks which seek to integrate social media uses into disaster management strategies are employed in a range of events. With continued variations to social media practices, developments in technology, and changes in online behaviors, it is imperative to provide conceptual frameworks which are relevant, current and insightful. This paper conceptualizes a range of recent literature through an inductive methodology, and presents the themes of Web accessibility and online information reliability as broad and emerging considerations for the identification of social media uses during disasters. It presents a new conceptual framework of current social media uses which may be used to supplement existing frameworks. The framework has been applied to a dataset of Tweets from the 2015 Nepal earthquake to demonstrate its validity. Suggestions for future applications are discussed.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1400
Share this record to Facebook
 

 
Author Daniel Link; Bernd Hellingrath; Jie Ling
Title A Human-is-the-Loop Approach for Semi-Automated Content Moderation Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Disaster Management; Social Media Analysis; Human-Is-The-Loop; Content Moderation; Supervised Machine Learning
Abstract Online social media has been recognized as a valuable information source for disaster management whose volume, velocity and variety exceed manual processing capacity. Current machine learning systems that support the processing of such data generally follow a human-in-the-loop approach, which has several inherent limitations. This work applies the human-is-the-loop concept from visual analytics to semi-automate a manual content moderation workflow, wherein human moderators take the dominant role. The workflow is instantiated with a supervised machine learning system that supports moderators with suggestions regarding the relevance and categorization of content. The instantiated workflow has been evaluated using in-depth interviews with practitioners and serious games. which suggest that it offers good compatibility with work practices in humanitarian assessment as well as improved moderation quality and higher flexibility than common approaches.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1401
Share this record to Facebook
 

 
Author Jidi Zhao; Linlin Wang
Title Research on Public Opinion Propagation in Micro-Blogging Based on Epidemic Models Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Mb-RP Model; Micro-Blogging; Public Opinion; Propagation Rules
Abstract Micro-blogging has become an important communication channel for public opinion topics with its own characteristics such as openness, timeliness and interactive and so on. Studying the propagation rules for public opinion topics in micro-blogging is important to monitor and understand Micro-blogging public opinion. In this paper, we study the spreading process of public opinion in micro-blogging, identify key elements in the process and propose an Mb-RP (Micro-blogging Read-Post) propagation model based on the traditional SIR (Susceptible- Infective-Recovered) epidemic model. Through statistical analysis of a case on Sina Weibo, we assign values to parameters in the model and conduct simulations. Simulation results show that the model established in this paper can well fit real data. Further study of the model indicates that, compared with the attention cycle and the average amount of readings per post, the forwarding rate has the most influence on Micro-blogging information propagation.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1402
Share this record to Facebook
 

 
Author Shane Errol Halse; Andrea Tapia; Anna Squicciarini; Cornelia Caragea
Title Tweet Factors Influencing Trust and Usefulness During Both Man-Made and Natural Disasters Type Conference Article
Year 2016 Publication ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2016
Volume Issue Pages
Keywords Twitter; Sandy; Hurricane; Boston Bombing; Trust; Usefulness
Abstract To this date, research on crisis informatics has focused on the detection of trust in Twitter data through the use of message structure, sentiment, propagation and author. Little research has examined the usefulness of these messages in the crisis response domain. Toward detecting useful messages in case of crisis, in this paper, we characterize tweets, which are perceived useful or trustworthy, and determine their main features. Our analysis is carried out on two datasets (one natural and one man made) gathered from Twitter concerning hurricane Sandy in 2012 and the Boston Bombing 2013. The results indicate that there is a high correlation and similar factors (support for the victims, informational data, use of humor and type of emotion used) influencing trustworthiness and usefulness for both disaster types. This could have impacts on how messages from social media data are analyzed for use in crisis response.
Address
Corporate Author Thesis
Publisher Federal University of Rio de Janeiro Place of Publication Rio de Janeiro, Brasil Editor A. Tapia; P. Antunes; V.A. Bañuls; K. Moore; J. Porto
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3388 ISBN 978-84-608-7984-9 Medium
Track (up) Social Media Studies Expedition Conference 13th International Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1403
Share this record to Facebook