Humanitarian crises, such as the 2014 West Africa Ebola epidemic, challenge information management and thereby threaten the digital resilience of the responding organizations. Crisis information management (CIM) is characterised by the urgency to respond despite the uncertainty of the situation. Coupled with high stakes, limited resources and a high cognitive load, crises are prone to induce biases in the data and the cognitive processes of analysts and decision-makers. When biases remain undetected and untreated in CIM, they may lead to decisions based on biased information, increasing the risk of an inefficient response. Literature suggests that crisis response needs to address the initial uncertainty and possible biases by adapting to new and better information as it becomes available. However, we know little about whether adaptive approaches mitigate the interplay of data and cognitive biases. We investigated this question in an exploratory, three-stage experiment on epidemic response. Our participants were experienced practitioners in the fields of crisis decision-making and information analysis. We found that analysts fail to successfully debias data, even when biases are detected, and that this failure can be attributed to undervaluing debiasing efforts in favor of rapid results. This failure leads to the development of biased information products that are conveyed to decision-makers, who consequently make decisions based on biased information. Confirmation bias reinforces the reliance on conclusions reached with biased data, leading to a vicious cycle, in which biased assumptions remain uncorrected. We suggest mindful debiasing as a possible counter-strategy against these bias effects in CIM.

Most water and development interventions aim to contribute to long-term sustainable impacts. Given the uncertainties involved in these longer-term water development projects, adaptive planning approaches hold promise to connect planning, implementation and evaluation. Recent innovations report promising results, but find limited wide-spread practice due to a relatively large distance from current operational realities. Therefore, in this article we set out to investigate the real-world benefits and barriers for adaptive planning, monitoring and evaluation as a tool for water development interventions. To do so, we have stripped the advanced theoretic adaptive planning approach to its essentials, for exploration in an ongoing water development project. Application of the resulting three essential adaptive planning steps to a water development project in Khulna, Bangladesh shows that these steps are feasible and can support a more adaptive planning and management. In particular, they have helped to surface critical assumptions and uncertainties, as well as associated adaptation actions for the case. These were related to spatial development, water quality, finance, and management capacity. However, results also show that the actual use of the proposed steps is likely to be hindered by strategic misrepresentation. Our findings suggest this as an additional and more fundamental barrier to the widespread use of adaptive planning practices. We reflect on this barrier of strategic misrepresentation and on possible mechanisms to counter it, in order to enable water development actors to make their planning and evaluation arrangements more adaptive.

Humanitarian disasters are highly dynamic and uncertain. The shifting situation, volatility of information, and the emergence of decision processes and coordination structures require humanitarian organizations to continuously adapt their operations. In this study, we aim to make headway in understanding adaptive decision-making in a dynamic interplay between changing situation, volatile information, and emerging coordination structures. Starting from theories of sensemaking, coordination, and decision-making, we present two case studies that represent the response to two different humanitarian disasters: Typhoon Haiyan in the Philippines, and the Syria Crisis, one of the most prominent ongoing conflicts. For both, we highlight how volatile information and the urge to respond via sensemaking lead to fragmentation and misalignment of emergent coordination structures and decisions, which, in turn, slow down adaptation. Based on the case studies, we derive propositions and the need to continuously align laterally between different regions and hierarchically between operational and strategic levels to avoid persistence of coordination-information bubbles. We discuss the implications of our findings for the development of methods and theory to ensure that humanitarian operations management captures the critical role of information as a driver of emergent coordination and adaptive decisions.

Resilient critical airport infrastructures affected by a disaster need to sustain minimal functionality and quickly resume full operation, while at the same time coping with the increased operational demands imposed by the unfolding disaster response. In this paper, we develop a resilience framework and model-driven approach that focuses on the ability of the infrastructure to rapidly adapt to a new steady state under these conditions. This requires both the extension of capacity as well as the adaptation of key processes. Through discrete event simulations, we study the implications of different policies to improve airport resilience under different disaster impact scenarios for a stylized case. Our results show that although decision-makers may be tempted to focus on short-term measures that can be implemented immediately, resilience is improved most by a combination of rapid process changes and longer-term measures that structurally increase airport capacity.

In the immediate aftermath of a disaster, local and international aid organisations deploy to deliver life-saving aid to the affected population. Yet pre-disaster road maps and road transportation models do not capture disruptions to the transportation network caused by the disaster or the dynamic changes of the situation, resulting in uncertainty and inefficiency in planning and decision-making. The integration of data in near real time on the status of the road infrastructure in the affected region can help aid organisations to keep track of the rapidly shifting conditions on the ground and to assess the implications for their logistics planning and operations. In this paper, we present a rapid graph-theoretical reachability information system based on a combination of OpenStreetMap and open humanitarian data. The system supports logistics planning in determining road access to affected communities. We demonstrate the results of our approach in a case study on the 2018 earthquake in Papua New Guinea. Our findings show the reachability of affected communities depending on the actual status of the road network, allowing for the prioritization of targeted locations and the identification of alternative routes to get there.

The online spread of rumours in disasters can create panic and anxiety and disrupt crisis operations. Hence, it is crucial to take measure against such a distressing phenomenon since it can turn into a crisis by itself. In this work, the automatic rumour detection in natural disasters is addressed from an imbalanced learning perspective due to the rumour dearth versus non-rumour abundance in social networks. We first provide two datasets by collecting and annotating tweets regarding the Hurricane Florence and Kerala flood. We then capture the properties of rumours and non-rumours in those disasters using 83 theory-based and early-available features, 47 of which are proposed for the first time. The proposed features show a high discrimination power that help us distinguish rumours from non-rumours more reliably. Next, We build the rumour identification models using imbalanced learning to address the scarcity of rumours compared to non-rumour. Additionally, to replicate the rumour detection in the real-world situation, we practice cross-incident learning by training the classifier with the samples of one incident and test it with the other one. In the end we measure the impact of imbalanced learning using Bayesian Wilcoxon Signed-rank test and observe a significant improvement in the classifiers performance.

Rumour is a collective emergent phenomenon with a potential for provoking a crisis. Modelling approaches have been deployed since five decades ago; however, the focus was mostly on epidemic behaviour of the rumours which does not take into account the differences between agents. We use social practice theory to model agent decision-making in organizational rumourmongering. Such an approach provides us with an opportunity to model rumourmongering agents with a layer of cognitive realism and study the impacts of various intervention strategies for prevention and control of rumours in organizations.

The global impacts of disaster risks are on the rise. Moreover, evidence shows that the severity of damage will increase exponentially. In 2019, there were 395 natural disasters that caused 11,755 deaths. Literature and practice indicate that diversification of disaster risk management (DRM) approaches can make communities more resilient. One notable bottleneck in adopting diverse DRM approaches is the historical dominance of natural and technological sciences with little contribution from social sciences. Thus, a heterogeneous social-technical approach to DRM is rare and risk governance challenges are hardly understood. We conducted a systematic literature and practice review and extracted data to develop and answer five sub-questions. After that, we reviewed relevant information and selected eight risk evaluation approaches. We made comparisons and used the input to design the Risk Evaluation Diversity-aiding Approach (RED-A). The approach consists of 12 criteria and a checklist with 22 items. RED-A provides guidance to DRM researchers and practitioners when conducting socio-technical risk evaluations. It helps identify cognitive biases in the ongoing DRM process that may largely impact the quality of risk evaluation procedures. The goal of the 22-item checklist is to ensure that the 12 RED-A criteria are incorporated as much as possible to support the progressive transition towards a heterogeneous social-technical DRM approach. Finally, the RED-A criteria and checklist are applied in the Solotvyno municipality context (in Ukraine), to illustrate the use of the approach.

The effectiveness of machine learning algorithms depends on the quality and amount of data and the operationalization and interpretation by the human analyst. In humanitarian response, data is often lacking or overburdening, thus ambiguous, and the time-scarce, volatile, insecure environments of humanitarian activities are likely to inflict cognitive biases. This paper proposes to research the effects of data ambiguity and cognitive biases on the interpretability of machine learning algorithms in humanitarian decision making.

The Kenyan government has made significant advances in water resources management at the local authority (county) level with little or no cooperation at the drainage basin level. Research on critical determinants of cooperation amongst transboundary water negotiation teams is limited. In this paper, we assess whether personal attribute diversity (PAD) is a stronger factor than demographic diversity (gender, age, and education play) in determining whether the negotiation team will cooperate or make unilateral actions. We use a negotiation game to study decisions taken by water policymakers. After that, we conduct a multiple discriminant analysis (MDA) to assess the influence of PAD, gender, age, and education on water negotiation outcomes. The findings indicate that PAD plays a significant role in determining whether the group will cooperate or compete. Gender, education, and age barely influence the outcome. Only upon removal of the PAD variable do we see an increase in the discriminant power of gender and education. Age has minimal influence on the negotiation outcomes. We apply the research at a lower level of governance (Nzoia River Basin). However, results might be extrapolated to a bigger basin, like the Nile Basin, through future multiple level analysis which takes account of the complex socio-technical systems.

This paper concentrates on methods to facilitate interaction and exchange knowledge between different expert groups. The specific case examined is on expert groups from the aviation and humanitarian context. Both are highly complex, multidisciplinary systems where stakeholders work under high time pressure and uncertainty and in a complex decision-making environment. Especially during a sudden on-set (natural) disaster, stakeholders from the humanitarian field and airport management need to work closely together to guarantee the most efficient way of handling issues like overwhelmed customs officials, unsolicited aid donations and unsafe or unprepared warehouses. While several approaches are available, the question still remains: which method works best to create a mutual understanding between these two worlds. To answer it, three different approaches have been examined: (1) discussion rounds with experts (2) gaming-related method and (3) simulation game. The set-ups as well as the results will be described and pros and cons of each method discussed.

This study addresses the problem of rumour scarcity versus non-rumour abundance in automatic rumour detection. To tackle this issue, we portray rumour as an anomaly by showing how disproportionate is the number of rumours versus non-rumours. This imbalance is scrutinized by comparing the rate of news production versus rate of fact-check production. Then, we exploit one-class classification approach to distinguish rumour from non-rumour. One-class classification separates rumour from non-rumour via training the classifier with only non-rumour. To train the one-class classifier, we extract 33 short-term features, regarding the purpose of this research in early detection of rumours. We evaluate the performance of our model by accuracy and F-score. In terms of F-score, our model outperforms the state-of-the-art and reaches to very close proximity of highest accuracy on the same dataset.

Kenya Water Services Regulatory Board (WASREB) Impact Report indicates a stagnation in water coverage at 55 percent, for the last three years, contrary to the 2015 target of 80 percent. One main reason for the stagnation is weak cross-county cooperation between hydrologically interdependent governments. WASREB has little guidance on what indicators to use to enhance cross-county water cooperation. Through literature review, we assess whether the UN-Water methodology for assessing Sustainable Development Goals (SDG) 6.5.2 would provide useful guidelines. Based on the literature review outcomes, we design a water policy game known as Nzoia WeShareIt. After that, we play seven-game sessions in four county governments (Busia, Bungoma, Kakamega, and Trans Nzoia), on 11-22 July 2016. We use the in-game and post-game questionnaire data to measure learning outcomes on interdependence and cooperation. The findings indicate that Nzoia WeShareIt policy game as a form of experiential learning increased understanding on the value of cross-county cooperation. The study constitutes a practical guideline to WASREB and a quick reference tool to be explored when designing indicators to monitor cross-county cooperation. We also propose a mixed method approach that incorporates team interdependence indicators as distinct and separate indicators from cooperation. Moreover, we recommend strengthening SDG 6.5.2 indicator to measure transboundary water cooperation inputs, processes and outcomes.

Rumor spreading in online social networks can inflict serious damages on individual, organizational, and societal levels. This problem has been addressed via computational approach in recent years. The dominant computational technique for the identification of rumors is the binary classification that uses rumor and non-rumor for the training. In this method, the way of annotating training data points determines how each class is defined for the classifier. Unlike rumor samples that often are annotated similarly, non-rumors get their labels arbitrarily based on annotators' volition. Such an approach leads to unreliable classifiers that cannot distinguish rumor from non-rumor consistently. In this paper, we tackle this problem via a novel classification approach called one-class classification (OCC). In this approach, the classifier is trained with only rumors, which means that we do not need the non-rumor data points at all. For this study, we use two primary Twitter data sets in this field and extract 86 features from each tweet. We then apply seven one-class classifiers from three different paradigms and compare their performance. Our results show that this approach can recognize rumors with a high level of F1-score. This approach may influence the predominant mentality of scholars about computational rumor detection and puts forward a new research path toward dealing with this problem.

Humanitarian organizations are increasingly challenged by the amount of data available to drive their decisions. Useful data can come from many sources, exists in different formats, and merging it into a basis for analysis and planning often exceeds organizations’ capacities and resources. At the same time, affected communities’ participation in decision making processes is often hindered by a lack of information and data literacy capacities within the communities. We describe a participatory disaster risk analysis project in the central Philippines where the community and a humanitarian NGO worked towards a joint understanding of disaster risks and coping capacities through data integration and IT-supported analysis. We present findings from workshops, focus group discussions and semi-structured interviews, showing the reciprocal effects of the collaborative work. While the community valued the systematically gathered and structured evidence that supported their own risk perceptions and advocacy efforts, the humanitarian NGO revisited established work practices for data collection for analysis and planning.

Equitable and reasonable utilization is a core principle in the distribution of water resources. However, its practical application in the Nile Basin has been a significant challenge, leading to a water allocation deadlock. To address the deadlock, we used the van Eeten (1999) four-step process for defining new agendas. To reconstruct the debate, nine possible water allocation methods are developed using the Stone (2002) framework. After that, the arguments are compared and contrasted using interpretative policy analysis and the relevant factors to determine equitable and reasonable utilization in the Nile basin. Unfortunately, none of the nine possible water allocation methods satisfied all of the factors of assessing equitable and reasonable utilization. Therefore, we identified a crosswalk position that combines three water allocation methods. This combination consists of: (1) a group-based distribution; (2) a value-based distribution; and (3) a consensus-based distribution. Since the crosswalk position does not address current and potential uses, we recommend a new agenda to recast the issue. This agenda entails a change in the recipient of the water resources, the allocated item, and the process of decision-making. Finally, we discuss the potential of applying the proposed methodology in Nile sub-basins and other river basins within Sub-Saharan Africa.

In early 2016, we designed Nzoia WeShareIt game to support joint decision-making, in a complex river basin, through policy practice in the form of water allocation trade-offs between food, energy, and nature. Nzoia WeShareIt game is a multi-player hybrid cooperation game. This concept report is a detailed description of the Nzoia WeShareIt game elements and their application. The report comprises of four main parts: the introduction, the body which details the game elements, a section dealing with the publications, which is the main project outcome and the appendices. In this report, the game elements section consists of fifteen parts. The first part is the introduction, followed by a description of the fourteen game elements. Two critical components of the game elements section are the explanation of the game contents and the game cycles including the steps of play. The five steps of play are harvest, trade, payment of the penalty, invest and re-allocate. The appendices comprise of three parts: an explanation of the transition from BIOMAdneSS to WeShareIt, a detailed description of the changes we made when transitioning to Nile and Nzoia WeShareIt and a picture collage. The picture collage consists of various pictures of the Nile WeShareIt session and the seven Nzoia WeShareIt game sessions. Finally, we provide a list of bibliography.

The Horizon 2020 interim evaluation (2017) indicates a steep increase in citizen engagement in European Union Citizen Science (CS) projects, with less than 1% in budgetary terms and minimal influence. Research findings attribute weak CS influence to the restriction of citizen actions to data collection, with minimal or no engagement in co-design, co-creation, data analysis, and elucidation of results. We design a participatory GIS and CS methodology aimed at engaging the citizens in the entire Earth Observation (EO) project cycle. The methodology also seeks to address previous CS project challenges related to data quality, data interoperability, citizen-motivation, and participation. We draw the high-level requirements from the SENDAI framework of action and the three pillars of active citizen engagement, as enshrined in Principle 10 of the Rio Declaration and the Aarhus Convention. The primary input of the methodology is the Haklay (2018) approach for participatory mapping and CS, and the Reed (2009) stakeholder analysis framework. The proposed methodology comprises of three main parts: system analysis, stakeholder analysis, and a six-step methodology. We designed the six-step methodology using an iterative and flexible approach, to take account of unforeseen changes. Future research will focus on implementing the methodology and evaluating its effectiveness in the Solotvyno Saltmine case study in Ukraine.

The incidence of natural disasters worldwide is increasing. As a result, a growing number of people is in need of humanitarian support, for which limited resources are available. This requires an effective and efficient prioritization of the most vulnerable people in the preparedness phase, and the most affected people in the response phase of humanitarian action. Data-driven models have
the potential to support this prioritization process. However, the applications of these models in a country requires a certain level of data preparedness. To achieve this level of data preparedness on a large scale we need to know how to facilitate, stimulate and coordinate data-sharing between humanitarian actors. We use a data ecosystem perspective to develop success criteria for establishing a “humanitarian data ecosystem”. We first present the development of a general framework with data ecosystem governance success criteria based on a systematic literature review. Subsequently, the applicability of this framework in the humanitarian sector is assessed through a case study on the “Community Risk Assessment and Prioritization toolbox” developed by the Netherlands Red Cross. The empirical evidence led to the adaption the framework to the specific criteria that need to be addressed when aiming to establish a successful humanitarian data ecosystem.

In the aftermath of disasters, information is of the essence for humanitarian decision makers in the field. Their concrete information needs is highly context-influenced and often they find themselves unable to access the right information at the right time. We propose a novel ICT-based approach to address these information needs more accurately. First, we select a group of in-field decision makers and collect their concrete information needs in the disaster aftermath. We then review to what extent existing data and tools can already address these needs. We conclude that existing solutions fall short in meeting important information needs of the selected group. We describe the design of an information system prototype to address these gaps more accurately. We combine data of the International Aid Transparency Initiative and the Humanitarian Data Exchange to form the data-backend of our system. We describe our implementation approach and evaluation plan.