Household Digital Twin for Disaster Response

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Bonke, Chaitali; Sun, Jun; Owusu, Gabriel; Wang, Yin

Abstract: Using simulation of digital twins can help save lives and reduce the impact of ... Expand

Abstract: Using simulation of digital twins can help save lives and reduce the impact of disasters on households. By accessing a virtual process and making recommendations to families before a disaster hits, the risk of harm can be minimized. Developing a household digital twin for disaster response can lay the foundation for effective household disaster management. This study proposes a design of household digital twin for disaster response and demonstrates how the platform can be used to simulate hazardous processes before they occur for damage control. Collapse

Topics: production management digital twin hurricane recommender system emergency management

Methods: design artifact simulation

Moving Emergency Response Forward: Leveraging Machine-Learning Classification of Disaster-Related Images Posted on Social Media

2023 | Journal of Management Information Systems | Citations: 0

Authors: Johnson, Matthew; Murthy, Dhiraj; Robertson, Brett W.; Smith, William Roth; Stephens, Keri K.

Abstract: Social media platforms are increasingly used during disasters. In the United Sta ... Expand

Abstract: Social media platforms are increasingly used during disasters. In the United States, users often consider these platforms to be reliable news sources and they believe first responders will see what they publicly post. While having ways to request help during disasters might save lives, this information is difficult to find because non-relevant content on social media completely overshadows content reflective of who needs help. To resolve this issue, we develop a framework for classifying hurricane-related images that have been human-annotated. Our approach uses transfer learning and classifies each image using the VGG-16 convolutional neural network and multi-layer perceptron classifiers according to the urgency, relevance, and time period, in addition to the presence of damage and relief motifs. We find that our framework not only successfully functions as an accurate method for hurricane-related image classification but also that real-time classification of social media images using a small training set is possible. Collapse

Topics: social media Twitter hurricane natural hazard application programming interface

Methods: machine learning deep learning literature study convolutional neural network classification method

Diffusion of real versus misinformation during a crisis event: A big data-driven approach

2023 | International Journal of Information Management | Citations: 0

Authors: King, Kelvin K.; Wang, Bin

Abstract: Misinformation has captured the interest of academia in recent years with severa ... Expand

Abstract: Misinformation has captured the interest of academia in recent years with several studies looking at the topic broadly with inconsistent results. In this research, we attempt to bridge the gap in the literature by examining the impacts of user-, time-, and content-based characteristics that affect the virality of real versus misinformation during a crisis event. Using a big data-driven approach, we collected over 42 million tweets during Hurricane Harvey and obtained 3589 original verified real or false tweets by cross-checking with fact-checking websites and a relevant federal agency. Our results show that virality is higher for misinformation, novel tweets, and tweets with negative sentiment or lower lexical density. In addition, we reveal the opposite impacts of sentiment on the virality of real news versus misinformation. We also find that tweets on the environment are less likely to go viral than the baseline religious news, while real social news tweets are more likely to go viral than misin­ formation on social news. Collapse

Topics: Twitter misinformation social media hurricane big data

Methods: machine learning computational algorithm natural language processing decision tree classification gradient boosting

Multi-Channel Convolutional Neural Network for the Identification of Eyewitness Tweets of Disaster

2023 | Information Systems Frontiers | Citations: 0

Authors: Kumar, Abhinav; Singh, Jyoti Prakash; Rana, Nripendra P.; Dwivedi, Yogesh K.

Abstract: During a disaster, a large number of disaster-related social media posts are wid ... Expand

Abstract: During a disaster, a large number of disaster-related social media posts are widely disseminated. Only a small percentage of disaster-related information is posted by eyewitnesses. The post of a disaster eyewitness offers an accurate depiction of the disaster. Therefore, the information posted by the eyewitness is preferred over the other source of information as it is more effective at helping organize rescue and relief operations and potentially saving lives. In this work, we propose a multi-channel convolutional neural network (MCNN) that uses three different word-embedding vectors together to classify disaster-related tweets into eyewitness, non-eyewitness, and don’t know classes. We compared the performance of the proposed multi-channel convolutional neural network with several attention-based deep-learning models and conventional machine learning-models such as recurrent neural network, gated recurrent unit, Long-Short-Term-Memory, convolutional neural network, logistic regression, support vector machine, and gradient boosting. The proposed multi-channel convolutional neural network achieved an F1-score of 0.84, 0.88, 0.84, and 0.86 with four disaster-related datasets of floods, earthquakes, hurricanes, and wildfires, respectively. The experimental results show that the training MCNN model with different word embedding together performs better than the conventional machine-learning models and several other deep-learning models. Collapse

Topics: Twitter earthquake hurricane crowdsourcing social media

Methods: machine learning deep learning convolutional neural network experiment GloVe

Transforming Sensemaking and Perceptions on Meteorological Data to Inform Emergency Decision-Making

2023 | Group Decision and Negotiation | Citations: 0

Authors: Lobosco, Dacy Câmara; de Carvalho, Paulo Victor Rodrigues

Abstract: After the catastrophe that occurred in the mountainous region of Rio de Janeiro, ... Expand

Abstract: After the catastrophe that occurred in the mountainous region of Rio de Janeiro, especially in the city of Nova Friburgo in January of 2011, caused by heavy rains, the population's perception of the risks associated with heavy rains was greatly affected. In the other hand, the civil defense agencies have great difficulties to predict the impacts of rainfall due to the limitations of the existing monitoring systems and due to the existing vulnerable communities. This paper describes how sharing sensemaking between the involved parties can transform the population's perceptions about rainfall impact to meteorological data for civil defense by filling gaps in the existing monitoring system and enable civil defense teams to inform and to guide the expectations of population for a more efficient response in emergency situations. Based on the Design Science Research methodology that seeks to develop and design solutions to solve a specific class of problem, a mobile phone application to share information between members of communities and the civil defense team was developed and tested. The test to verify the sensemaking transformation was done through a case study involving volunteers from the community and the civil defense team of Nova Friburgo during a real rainfall situation. The results showed that the continuous and iterative flow of information enables the sharing of sensemaking, indicating the importance of this process for decision-making during emergency response actions. Collapse

Topics: sensemaking decision making emergency management mobile application smartphone

Methods: survey qualitative interview design science case study literature study

Theories: cognitive dissonance theory

Machine and human roles for mitigation of misinformation harms during crises: An activity theory conceptualization and validation

2023 | International Journal of Information Management | Citations: 0

Authors: Tran, Thi; Valecha, Rohit; Rao, H. Raghav

Abstract: During crises, there is a need for a large amount of information in a short peri ... Expand

Abstract: During crises, there is a need for a large amount of information in a short period. Such need creates the base for misinformation to spread within and outside the affected community. This may result in misinformation harms that can generate serious short term or long-term consequences. In such situations, there is a need for a joint human-machine effort to mitigate misinformation. Though there has been research in the area of management of AI in the recent past, there has been scarce work in examining situations where machines and humans interact for mitigating misinformation. In order to systematically analyze misinformation and suggest mechanisms for mitigation, we draw on Activity Theory to conceptualize a suitable framework. Such a framework will enable investigating human-machine interactions through loops of “misinformation generation” and “misinformation mitigation” activities for mitigating misinformation harms. The paper also validates the framework using three different target audiences, undergraduates, graduates and professionals. Collapse

Topics: misinformation social media emergency management human computer interaction usability

Methods: case study theoretical contribution design science

Theories: activity theory

Transformer-Based Multi-Task Learning for Crisis Actionability Extraction

2023 | International Conference on Information Systems | Citations: 0

Authors: Zhang, Yuhao; Lo, Siaw Ling; Myint, Phyo Yi Win

Abstract: Social media has become a valuable information source for crisis informatics. W ... Expand

Abstract: Social media has become a valuable information source for crisis informatics. While various methods were proposed to extract relevant information during a crisis, their adoption by field practitioners remains low. In recent fieldwork, actionable information was identified as the primary information need for crisis responders and a key component in bridging the significant gap in existing crisis management tools. In this paper, we proposed a Crisis Actionability Extraction System for filtering, classification, phrase extraction, severity estimation, localization, and aggregation of actionable information altogether. We examined the effectiveness of transformer-based LSTM-CRF architecture in Twitter-related sequence tagging tasks and simultaneously extracted actionable information such as situational details and crisis impact via Multi-Task Learning. We demonstrated the system's practical value in a case study of a real-world crisis and showed its effectiveness in aiding crisis responders with making well-informed decisions, mitigating risks, and navigating the complexities of the crisis. Collapse

Topics: Twitter social media systems design hurricane knowledge base

Methods: BERT case study GloVe machine learning experiment

Introduction to the Special Issue

2023 | Journal of Management Information Systems | Citations: 0

Authors: de Vreede ID, Gert-Jan; Nunamaker Jr., Jay F.

Abstract: Recent years have proven to be among the most challenging on record for organiza ... Expand

Abstract: Recent years have proven to be among the most challenging on record for organizations and society at large. Information systems (IS) professionals versed in analytics and data science have become one of the scarcest organizational resources. Based on a review of past DL research in information systems, they also develop a Knowledge Contribution Framework to distinguish between DL contributions for computational, behavioral, or economic information systems research. Collapse

Topics: design thinking IT investment IT career geographic information system hurricane

Methods: design methodology design artifact literature study personal interview case study

Bike Share Systems and Equitable Disaster Management: Utilization in Low-income Neighborhoods Amid Subway Flood Damage

2022 | International Conference on Information Systems | Citations: 0

Authors: Choi, Yunmin; Baek, Jiye

Abstract: We focus on the equity problem of the IT-enabled public bike share systems and ... Expand

Abstract: We focus on the equity problem of the IT-enabled public bike share systems and posit that shared bicycles become a heavily reliant mode of transportation in low-income neighborhoods during abrupt suspensions of subway systems caused by disasters. Although bike share is known to provide many social benefits, it has been often criticized for having low usage and lazy expansion among low-income neighborhoods. We leverage a natural experiment setting to estimate the effect of flood damage to subway lines on the demand for public bike share service. Through a quasi-experiment analysis, we find that the effect of flood significantly increases bike share usage in low-income neighborhoods while not profoundly affecting usage in high-income neighborhoods. From the results, we shed light on the previously undiscovered role of bike share in the disaster management context and its role in mitigating the transportation disturbance of low-income commuters. Collapse

Topics: emergency management natural hazard hurricane climate change ride sharing platform

Methods: experimental group longitudinal research robustness check natural experiment difference in differences

Uncovering a new form of digitally-enabled agility: an improvisational perspective

2022 | European Journal of Information Systems | Citations: 0

Authors: Levallet, Nadège; Chan, Yolande

Abstract: Agile organisations address changes with ease and speed. These changes are tackl ... Expand

Abstract: Agile organisations address changes with ease and speed. These changes are tackled through the concept of ongoing agility, using a sense-respond process, composed of sensing, decision-making, and acting. Increasingly, however, unexpected events require a different agility response. In this study, we propose and empirically examine how improvisational agility – conceptualised as organisation improvisational capability, the ability to sense and respond to unexpected events with speed and creativity – is a type of agility better suited for unanticipated events. Specifically, we focus on the improvisational agility sense-respond process. Using four exploratory cases, we find that organisations can leverage existing ongoing agility mechanisms for improvisational agility and, through learning, can leverage improvisational agility in ongoing agility. We also explain how different components of information management capability support improvisational agility, depending on the unexpected events and the need for speed or creativity. Collapse

Topics: decision making organization learning database system information management information system use

Methods: case study qualitative interview literature study experiment theory development

Theories: dynamic capabilities theory