Faisal Luqman, & Martin Griss. (2011). Leveraging mobile context for effective collaboration and task management. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Collaboration and task management is challenging in distributed, dynamically-formed teams, typical in large scale disaster response scenarios. Ineffective collaboration may potentially result in poor performance and loss of life. The increased adoption of sensor rich mobile devices allow for mobile context to be leveraged. In this paper, we present Overseer, an agent-based system that exploits context information from mobile devices to facilitate collaboration and task allocation. We describe how mobile context can be used to create dynamic role-based assignments to enhance collaboration and effective task management.
|
Ly Dinh, Sumeet Kulkarni, Pingjing Yang, & Jana Diesner. (2023). Reliability of Methods for Extracting Collaboration Networks from Crisis-related Situational Reports and Tweets. In V. L. Thomas J. Huggins (Ed.), Proceedings of the ISCRAM Asia Pacific Conference 2022 (pp. 181–195). Palmerston North, New Zealand: Massey Unversity.
Abstract: Assessing the effectiveness of crisis response is key to improving preparedness and adapting policies. One method for response evaluation is reviewing actual response activities and interactions. Response reports are often available in the form of natural language text data. Analyzing a large number of such reports requires automated or semi automated solutions. To improve the trustworthiness of methods for this purpose, we empirically validate the reliability of three relation extraction methods that we used to construct interorganizational collaboration networks by comparing them against human-annotated ground truth (crisis-specific situational reports and tweets). For entity extraction, we find that using a combination of two off-the-shelf methods (FlairNLP and SpaCy) is optimal for situational reports data and one method (SpaCy) for tweets data. For relation extraction, we find that a heuristics-based model that we built by leveraging word co-occurrence and deep and shallow syntax as features and training it on domain-specific text data outperforms two state-of-the-art relation extraction models (Stanford OpenIE and OneIE) that were pre-trained on general domain data. We also find that situational reports, on average, contain less entities and relations than tweets, but the extracted networks are more closely related to collaboration activities mentioned in the ground truth. As it is widely known that general domain tools might need adjustment to perform accurately in specific domains, we did not expect the tested off-the-shelf tools to perform highly accurately. Our point is to rather identify what accuracy one could reasonably expect when leveraging available resources as-is for domain specific work (in this case, crisis informatics), what errors (in terms of false positives and false negatives) to expect, and how to account for that.
|
Ma Ma, H. Zhang, & Yi Liu. (2014). Development of a joint official microblog platform to improve interactive communication with the public under a centralized system. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 782–786). University Park, PA: The Pennsylvania State University.
Abstract: Social media bring both challenges and opportunities to crisis management. This paper summarizes the difficulties in crisis communication under a centralized jurisdiction system by looking into online collective behaviors in mainland China. The paper then introduces the development of an official microblog and proposes a joint official microblog platform to improve interactive communication in a centralized system. The functional design of this platform is introduced in detail and the future improvement of the platform is discussed.
|
Mahshid Marbouti, Craig Anslow, & Frank Maurer. (2018). Evaluation results for a Social Media Analyst Responding Tool. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 480–492). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: We take a human-centered design approach to develop a fully functional prototype, SMART (“Social Media Analyst Responding Tool”), informed by emergency practitioners. The prototype incorporates machine learning techniques to identify relevant information during emergencies. In this paper, we report the result of a user study to gather qualitative feedback on SMART. The evaluation results offer recommendations into the design of Social Media analysis tools for emergencies. The evaluation findings show the interest of emergency practitioners into designing such solutions; it reflects their need to not only identify relevant information but also to further perceive the outcome of their actions in social media. We found out there is a notable emphasis on the sentiment from these practitioners and social media analysis tools need to do a better job of handling negative sentiment within the emergency concept.
|
Mahshid Marbouti, Irene Mayor, Dianna Yim, & Frank Maurer. (2017). Social Media Analyst Responding Tool: A Visual Analytics Prototype to Identify Relevant Tweets in Emergency Events. 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. 572–582). Albi, France: Iscram.
Abstract: Public and humanitarian organizations monitor social media to extract useful information during emergencies. In this paper, we propose a new method for identifying situation awareness (SA) tweets for emergencies. We take a human centered design approach to developing a visual analytics prototype, SMA-RT (“Social Media Analyst Responding Tool”), informed by social media analysts and emergency practitioners. Our design offers insights into the main requirements of social media monitoring tools used for emergency purposes. It also highlights the role that human and technology can play together in such solutions. We embed a machine learning classifier to identify SA tweets in a visual interactive tool. Our classifier aggregates textual, social, location, and tone based features to increase precision and recall of SA tweets.
|
Marc-André Kaufhold, & Christian Reuter. (2017). The Impact of Social Media for Emergency Services: A Case Study with the Fire Department Frankfurt. 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. 603–612). Albi, France: Iscram.
Abstract: The use of social media is not only part of everyday life but also of crises and emergencies. Many studies focus on the concrete use of social media during a specific emergency, but the prevalence of social media, data access and published research studies allows the examination in a broader and more integrated manner. This work-in-progress paper presents the results of a case study with the Fire Department Frankfurt, which is one of the biggest and most modern fire departments in Germany. The findings relate to social media technologies, organizational structure and roles, information validation, staff skills and resources, and the importance of volunteer communities. In the next step, the results will be integrated into the frame of a comparative case study with the overall aim of examining the impact of social media on how emergency services respond and react in an emergency.
|
Marion Lara Tan, Raj Prasanna, Kristin Stock, Emma Hudson-Doyle, Graham Leonard, & David Johnston. (2019). Enhancing the usability of a disaster app: exploring the perspective of the public as users. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: Limited research has studied how citizens? perspectives as end-users can contribute to improving the usability of disaster apps. This study addresses this gap by exploring end-user insights with the use of a conceptual disaster app in the New Zealand (NZ) context. NZ has multiple public alerting authorities that have various technological options in delivering information to the population?s mobile devices; including social media platforms, apps, as well as the Emergency Mobile Alert system. However, during critical events, the multiplicity of information may become overwhelming. A disaster app, conceptualised in the NZ context, aims to aggregate, organise, and deliver information from official sources to the public. After the initial conceptual design, a usability inquiry was administered by interviewing members of the public. Partial results of the inquiry show that the public?s perspective has value; in the process of understanding the new user?s viewpoint, usability highlights and issues are identified.
|
Marta Poblet Balcell, Stan Karanasios, & Vanessa Cooper. (2018). Look after Your Neighbours: Social Media and Vulnerable Groups during Extreme Weather Events. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 408–415). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: Emergency management organisations across the world routinely use social media to reach out populations for preparedness and response to extreme weather events. In this paper we present a preliminary analysis of social media strategies towards vulnerable populations in the State of Victoria (Australia). Using the notion of vulnerability in an emergency management context (e.g. older persons, socially/geographically isolated persons, people with disabilities, refugee/recent migrant communities) we explore whether and how organisations address vulnerable groups with targeted messages. Our initial findings suggest that organisations do not tend to interact directly with these groups. Rather, reliance on 'information brokers' (intermediary organisations and individuals with an expected duty of care) seems to be a preferred strategy.
|
Maryam Shahbazi, Christian Ehnis, Majid Shahbazi, & Deborah Bunker. (2018). Tweeting from the Shadows: Social Media Convergence Behaviour During the 2017 Iran-Iraq Earthquake. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 416–427). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: Official policies, socioeconomic and demographic factors influence how individuals cope with, and respond to natural disasters. Understanding the impact of these factors in social media crisis communications studies is difficult. This paper focuses on convergence behaviour during social media crisis communication in an environment where the access to commercial social media platforms is highly restricted. This study is designed as a case which analyses 41,745 Tweets communicated during an earthquake event and for the two weeks after. This research aims to understand how different communities use social media services for communication during extreme events. The content of the Tweets shows users' attitudes toward government policies as well as the social difficulties of ethnic groups reflecting on the use of social media in crises communication. The results indicate a “political effect” on this online crisis communication. This behaviour was not expected and has been underreported in the current body of knowledge.
|
Matti Wiegmann, Jens Kersten, Friederike Klan, Martin Potthast, & Benno Stein. (2020). Analysis of Detection Models for Disaster-Related Tweets. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 872–880). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media is perceived as a rich resource for disaster management and relief efforts, but the high class imbalance between disaster-related and non-disaster-related messages challenges a reliable detection. We analyze and compare the effectiveness of three state-of-the-art machine learning models for detecting disaster-related tweets. In this regard we introduce the Disaster Tweet Corpus~2020, an extended compilation of existing resources, which comprises a total of 123,166 tweets from 46~disasters covering 9~disaster types. Our findings from a large experiments series include: detection models work equally well over a broad range of disaster types when being trained for the respective type, a domain transfer across disaster types leads to unacceptable performance drops, or, similarly, type-agnostic classification models behave more robust at a lower effectiveness level. Altogether, the average misclassification rate of~3,8\% on performance-optimized detection models indicates effective classification knowledge but comes at the price of insufficient generalizability.
|
McCreadie, R., & Buntain, C. (2023). CrisisFACTS: Buidling and Evaluating Crisis Timelines. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 320–339). Omaha, USA: University of Nebraska at Omaha.
Abstract: Between 2018 and 2021, the Incident Streams track (TREC-IS) developed standard approaches for classifying information types and criticality of tweets during crises. While successful in producing substantial collections of labeled data, TREC-IS as a data challenge had several limitations: It only evaluated information at type-level rather than what was reported; it only used Twitter data; and it lacked measures of redundancy in system output. This paper introduces Crisis Facts and Cross-Stream Temporal Summarization (CrisisFACTS), a new data challenge piloted in 2022 and developed to address these limitations. The CrisisFACTS framework recasts TREC-IS into an event-summarization task using multiple disaster-relevant data streams and a new fact-based evaluation scheme, allowing the community to assess state-of-the-art methods for summarizing disaster events Results from CrisisFACTS in 2022 include a new test-collection comprising human-generated disaster summaries along with multi-platform datasets of social media, crisis reports and news coverage for major crisis events.
|
David F. Merrick, & Tom Duffy. (2013). Utilizing community volunteered information to enhance disaster situational awareness. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 858–862). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Social media allows the public to engage in the disaster response and recovery process in new and exciting ways. Many emergency management agencies in the United States are embracing social media as a new channel for alerts, warnings, and public outreach, but very few are mining the massive amounts of data available for use in disaster response. The research reflected in this paper strives to help emergency management practitioners harness the power of community volunteered information in a way that is still novel in most parts of the country. Field verification and research combined with survey results attempts to identify and solve many of the barriers to adoption that currently exist. By helping practitioners understand the virtues and limitations of this type of data and information, this research will encourage the use of community volunteered information in the emergency operations center.
|
Manne Messemaker, Jeroen Wolbers, Willem Treurniet, & Kees Boersma. (2013). Shaping societal impact: Between control and cooperation. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 901–905). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: In our modem society, the impact of large-scale spfety and security incidents can be large and diverse. Yet. this societal impact is makeable and controllable to a limited extent. At best, the effect of concrete response actions is that the direct damage is somewhat reduced and that the recovery is accelerated. Proper crisis communication can make the biggest difference with respect to overall societal impact. We argue that crisis communication must strike a balance between a directive approach of chaos, command and control and a more empathic approach of continuity, coordination and cooperation. On the basis of a concrete case we analyze how crisis communication reflects the incident response approach and how societal impact is affected.
|
Michael Aupetit, & Muhammad Imran. (2017). Interactive Monitoring of Critical Situational Information on Social Media. 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. 673–683). Albi, France: Iscram.
Abstract: According to many existing studies, the data available on social media platforms such as Twitter at the onset of a crisis situation could be useful for disaster response and management. However, making sense of this huge data coming at high-rate is still a challenging task for crisis managers. In this work, we present an interactive social media monitoring tool that uses a supervised classification engine and natural language processing techniques to provide a detailed view of an on-going situation. The tool allows users to apply various filtering options using interactive timelines, critical entities, and other logical operators to get quick access to situational information. The evaluation of the tool conducted with crisis managers shows its significance for situational awareness and other crisis management related tasks.
|
Mohammed Benali, A. R. G. (2017). Towards a Crowdsourcing-based Approach to enhance Decision Making in Collaborative Crisis Management. 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. 554–563). Albi, France: Iscram.
Abstract: Managing crises is considered as one of the most complicated organizational and managerial task. Indeed, dealing with such situations calls for many groups from different institutions and organizations to interact and collaborate their efforts in a timely manner to reduce their effects. However, response organizations are challenged by several problems. The urgent need of a shared and mutual situational awareness, information and knowledge about the situation are distributed across time and space and owned by both organizations and people. Additionally, decisions and actions have to be achieved promptly, under stress and time pressure. The contribution outlined in this paper is suggesting a crowdsourcing-based approach for decision making in collaborative crisis management based on the literature requirements. The objective of the approach is to support situational awareness and enhance the decision making process by involving citizens in providing opinions and evaluations of potential response actions.
|
Muhammad Imran, Firoj Alam, Umair Qazi, Steve Peterson, & Ferda Ofli. (2020). Rapid Damage Assessment Using Social Media Images by Combining Human and Machine Intelligence. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 761–773). Blacksburg, VA (USA): Virginia Tech.
Abstract: Rapid damage assessment is one of the core tasks that response organizations perform at the onset of a disaster to understand the scale of damage to infrastructures such as roads, bridges, and buildings. This work analyzes the usefulness of social media imagery content to perform rapid damage assessment during a real-world disaster. An automatic image processing system, which was activated in collaboration with a volunteer response organization, processed ~280K images to understand the extent of damage caused by the disaster. The system achieved an accuracy of 76% computed based on the feedback received from the domain experts who analyzed ~29K system-processed images during the disaster. An extensive error analysis reveals several insights and challenges faced by the system, which are vital for the research community to advance this line of research.
|
Muhammad Imran, Prasenjit Mitra, & Jaideep Srivastava. (2016). Cross-Language Domain Adaptation for Classifying Crisis-Related Short Messages. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
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.
|
Aibek Musaev, De Wang, & Calton Pu. (2014). LITMUS: Landslide detection by integrating multiple sources. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 677–686). University Park, PA: The Pennsylvania State University.
Abstract: Disasters often lead to other kinds of disasters, forming multi-hazards such as landslides, which may be caused by earthquakes, rainfalls, water erosion, among other reasons. Effective detection and management of multihazards cannot rely only on one information source. In this paper, we evaluate a landslide detection system LITMUS, which combines multiple physical sensors and social media to handle the inherent varied origins and composition of multi-hazards. LITMUS integrates near real-time data from USGS seismic network, NASA TRMM rainfall network, Twitter, YouTube, and Instagram. The landslide detection process consists of several stages of social media filtering and integration with physical sensor data, with a final ranking of relevance by integrated signal strength. Applying LITMUS to data collected in October 2013, we analyzed and filtered 34.5k tweets, 2.5k video descriptions and 1.6k image captions containing landslide keywords followed by integration with physical sources based on a Bayesian model strategy. It resulted in detection of all 11 landslides reported by USGS and 31 more landslides unreported by USGS. An illustrative example is provided to demonstrate how LITMUS' functionality can be used to determine landslides related to the recent Typhoon Haiyan.
|
Ahmed Nagy, & Jeannie Stamberger. (2012). Crowd sentiment detection during disasters and crises. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Microblogs are an opportunity for scavenging critical information such as sentiments. This information can be used to detect rapidly the sentiment of the crowd towards crises or disasters. It can be used as an effective tool to inform humanitarian efforts, and improve the ways in which informative messages are crafted for the crowd regarding an event. Unique characteristics of microblogs (lack of context, use of jargon etc) in Tweets expressed by a message-sharing social network during a disaster response require special handling to identify sentiment. We present a systematic evaluation of approaches to accurately and precisely identify sentiment in these Tweets. This paper describes sentiment detection expressed in 3698 Tweets, collected during the September 2010, San Bruno, California gas explosion and resulting fires. The data collected was manually coded to benchmark our techniques. We start by using a library of words with annotated sentiment, SentiWordNet 3.0, to detect the basic sentiment of each Tweet. We complemented that technique by adding a comprehensive list of emoticons, a sentiment based dictionary and a list of out-of-vocabulary words that are popular in brief, online text communications such as lol, wow, etc. Our technique performed 27% better than Bayesian Networks alone, and the combination of Bayesian networks with annotated lists provided marginal improvements in sentiment detection than various combinations of lists. © 2012 ISCRAM.
|
Nasik Muhammad Nafi, Avishek Bose, Sarthak Khanal, Doina Caragea, & William H. Hsu. (2020). Abstractive Text Summarization of Disaster-Related Documents. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 881–892). Blacksburg, VA (USA): Virginia Tech.
Abstract: Abstractive summarization is intended to capture key information from the full text of documents. In the application domain of disaster and crisis event reporting, key information includes disaster effects, cause, and severity. While some researches regarding information extraction in the disaster domain have focused on keyphrase extraction from short disaster-related texts like tweets, there is hardly any work that attempts abstractive summarization of long disaster-related documents. Following the recent success of Reinforcement Learning (RL) in other domains, we leverage an RL-based state-of-the-art approach in abstractive summarization to summarize disaster-related documents. RL enables an agent to find an optimal policy by maximizing some reward. We design a novel hybrid reward metric for the disaster domain by combining \underline{Vec}tor Similarity and \underline{Lex}icon Matching (\textit{VecLex}) to maximize the relevance of the abstract to the source document while focusing on disaster-related keywords. We evaluate the model on a disaster-related subset of a CNN/Daily Mail dataset consisting of 104,913 documents. The results show that our approach produces more informative summaries and achieves higher \textit{VecLex} scores compared to the baseline.
|
Neda Mohammadi, John E. Taylor, & Ryan Pollyea. (2017). Spatiotemporal Dynamics of Public Response to Human-Induced Seismic Perturbations. 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. 666–672). Albi, France: Iscram.
Abstract: There is general consensus that subsurface wastewater injections associated with unconventional oil and gas operations are responsible for the rapid increase of earthquake activity in the mid-U.S. Understanding the public response to these earthquakes is crucial for policy decisions that govern developing situational awareness and addressing perceived risks. However, we lack sufficient information on the reactive and recovery response behavior of the public tending to occur in the spatiotemporal vicinity of these events. Here, we review the spatiotemporal distribution of public response to the September 3, 2016, M5.8 earthquake in Pawnee, Oklahoma, USA, via a social media network (Twitter). Our findings highlight a statistically significant correlation between the spatial and temporal distribution of public response; and suggest the possible presence of a spatial distance decay, as well as a temporal far-field eect. Understanding the underlying structure of these correlations is fundamental to establishing deliberate policy decisions and targeted response actions.
|
Nilani Algiriyage, Rangana Sampath, Raj Prasanna, Kristin Stock, Emma Hudson-Doyle, & David Johnston. (2021). Identifying Disaster-related Tweets: A Large-Scale Detection Model Comparison. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 731–743). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media applications such as Twitter and Facebook are fast becoming a key instrument in gaining situational awareness (understanding the bigger picture of the situation) during disasters. This has provided multiple opportunities to gather relevant information in a timely manner to improve disaster response. In recent years, identifying crisis-related social media posts is analysed as an automatic task using machine learning (ML) or deep learning (DL) techniques. However, such supervised learning algorithms require labelled training data in the early hours of a crisis. Recently, multiple manually labelled disaster-related open-source twitter datasets have been released. In this work, we create a large dataset with 186,718 tweets by combining a number of such datasets and evaluate the performance of multiple ML and DL algorithms in classifying disaster-related tweets in three settings, namely ``in-disaster'', ``out-disaster'' and ``cross-disaster''. Our results show that the Bidirectional LSTM model with Word2Vec embeddings performs well for the tweet classification task in all three settings. We also make available the preprocessing steps and trained weights for future research.
|
Nils Bourgon, Benamara Farah, Alda Mari, Véronique Moriceau, Gaetan Chevalier, Laurent Leygue, et al. (2022). Are Sudden Crises Making me Collapse? Measuring Transfer Learning Performances on Urgency Detection. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 701–709). Tarbes, France.
Abstract: This paper aims at measuring transfer learning performances across different types of crises related to sudden or unexpected events (like earthquakes, terror attacks, explosions, technological incidents) that cannot be foreseen by emergency services and on the occurrence of which they have virtually no control. Although sudden crises are present in most existing crisis datasets, as far as we are aware, no one studied their impact on classifiers performances when evaluated in an out-of-type scenario in which models are tested on a particular type of crisis unseen during training. Our contribution is threefold: (1) A new dataset of about 3,800 French tweets related to four sudden events that occurred in France annotated for both relatedness (i.e., useful vs. not useful for emergency responders) and urgency (i.e., not useful vs. urgent vs. not urgent), (2) A set of monotask and multitask zero-shot learning experiments to transfer knowledge across events and types, and finally, (3) Experiments involving few-shot learning to measure the amount of sudden events instances needed during training to guarantee good performances. When compared to a cross-event setting, our preliminary results are encouraging and show that transfer from predictable ecological crisis to sudden events is feasible and constitutes a first step towards real-time crisis management systems from social media content.
|
Susanna Nilsson, Joel Brynielsson, Magdalena Granasen, Charlotte Hellgren, Sinna Lindquist, Mikael Lundin, et al. (2012). Making use of new media for pan-European crisis communication. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Social or new media have over the past years become an integrated part of human communication, both as a means to establish and maintain social relationships, but also as a means of sharing and co-creating information. New media comes with an array of possibilities for individuals as well as organisations, corporations and authorities. Within the field of crisis communication new media possibilities, such as online sharing and social networking, has had an impact on the way crisis information is disseminated and updated. This paper addresses the issues related to using new media as a means of communicating crisis information and broadcasting alerting messages to the general population, and also discusses the role of new media in future pan-European alerting. It focuses on current and on-going research on social media for crisis communication. An extensive systematic literature review was done to identify factors that affect the use of social media for alerting and warning. These factors were mirrored in experiences, collected through interviews, in crisis communication organisations in three European regions (Sweden, Czech Republic and Spain). The factors finally form the basis for suggestions regarding the design of technological tools for both communication and information collection as part of a pan-European alerting system. © 2012 ISCRAM.
|
Ntalla Athanasia, & Ponis T. Stavros. (2015). Twitter as an instrument for crisis response: The Typhoon Haiyan case study. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: The research presented in this paper attempts an initial evaluation of Twitter as an instrument for emergency response in the context of a recent crisis event. The case of the 2013 disaster, when typhoon Haiyan hit Philippines is examined by analyzing nine consecutive days of Twitter messages and comparing them to the actual events. The results indicate that during disasters, Twitter users tend to post messages to enhance situation awareness and to motivate people to act. Furthermore, tweets were found reliable and provided valuable information content, supporting the argument that Twitter presents a very good potential to become a useful tool in situations where rapid emergency response is essential.
|