Search Results (15)

Social media has become a vital source for humanitarian organizations to gather information during crises. However, existing multimodal classification methods operate primarily as isolated systems, while neglecting external references crucial for accurate judgment. Furthermore, while user comments can provide valuable context, they are often scarce during the early stages of a crisis. To address these limitations, we propose a framework named Mix-Persona Comment Generation with Geographically Enhanced Context Retrieval for LLM Instruction Fine-tuning (MPCG-GECR). To mitigate comment scarcity, we employ a Synthetic Persona Generator (SPG) that prompts LLMs to adopt diverse mix-personas, generating synthetic comments that simulate multi-perspective public discourse. To incorporate external references, we introduce a Geographically Enhanced Context Retrieval (GECR) module. Unlike standard retrieval approaches, GECR utilizes a hybrid re-ranking strategy to identify samples that are both multimodally similar and geographically consistent, serving as reliable reference anchors for the LLM. By integrating these social perspectives and geographic references into a unified instruction-tuning format, we transform the classification task into a context-aware text generation problem and fine-tune the LLM using Low-Rank Adaptation (LoRA). Extensive experiments on the CrisisMMD and DMD datasets demonstrate that MPCG-GECR effectively overcomes data scarcity and context isolation, significantly outperforming existing methods. Full article

As natural disasters and crises increase globally in both frequency and severity, researchers have been exploring innovative technological solutions to manage them effectively. This systematic review examines the integration of artificial intelligence (AI) with social media platforms for crisis management, identifying and categorizing key components of AI-driven systems into data and learning aspects. It introduces a dual-aspect analytical taxonomy that provides a structured framework for analyzing how data and learning dimensions interact in AI-driven crisis management solutions. Following the PRISMA methodology, the review analyzed 30 high-impact, peer-reviewed journal articles published in English between 2020 and 2024 across major academic databases. The quality of the studies was assessed based on journal ranking and methodological rigor to ensure reliability and minimize bias. The analysis revealed several interconnected trends: text remains the dominant data modality (60%), while multimodal analysis (33%) and image-based analysis (7%) are gaining traction. Throughout these studies, deep learning models consistently demonstrated superior performance compared to traditional machine learning approaches, with hybrid methodologies significantly enhancing overall model efficiency. Notably, the majority of research (73%) concentrated on during-disaster phases, highlighting the critical need for real-time intervention solutions. Twitter/X emerged as the overwhelming primary data source (73%), creating potential platform dependency issues. Despite considerable advancements, the field continues to face persistent challenges, including an over-reliance on single platforms, insufficient real-time AI models, and complexities in multimodal data fusion. To advance crisis management capabilities, future research directions should address cross-domain generalizability, enhance real-time processing capabilities, and develop improved fusion techniques that can ultimately lead to more effective and timely disaster response systems. Full article

This study investigates Spanish-language public discourse on YouTube following the unprecedented Iberian Peninsula blackout of 28 April 2025. Leveraging comments extracted via the YouTube Data API and analyzed with the OpenAI GPT-4o-mini model, it systematically examined 76,398 comments from 360 of the most relevant videos posted on the day of the event. The analysis explored emotional responses, sentiment trends, misinformation prevalence, civic engagement, and attributions of blame within the immediate aftermath of the blackout. The results reveal a discourse dominated by negativity and anger, with 43% of comments classified as angry and an overall negative sentiment trend. Misinformation was pervasive, present in 46% of comments, with most falsehoods going unchallenged. The majority of users attributed the blackout to government or political failures rather than technical causes, reflecting a profound distrust in institutions. Notably, while one in five comments included a call to action, only a minority offered constructive solutions, focusing mainly on infrastructure and energy reform. These findings highlight the crucial role of multilingual, real-time crisis communication and the unique information needs of Spanish-speaking populations during emergencies. By illuminating how rumors, emotions, and calls for accountability manifest in digital spaces, this study contributes to the literature on crisis informatics, digital resilience, and inclusive sustainability policy. Full article

Earthquakes are sudden-onset disasters requiring rapid, accurate information for effective crisis response. Social media (SM) platforms provide abundant geospatial data but are often unstructured and produced by diverse users, posing challenges in filtering relevant content. Traditional content filtering methods rely on natural language processing (NLP), which underperforms with mixed-language posts or less widely spoken languages. Moreover, these approaches often neglect the spatial proximity of users to the event, a crucial factor in determining relevance during disasters. This study proposes an NLP-free model that assesses the spatial credibility of SM content by analysing users’ spatial trajectories. Using earthquake-related tweets, we developed a machine learning-based classification model that categorises posts as directly relevant, indirectly relevant, or irrelevant. The Random Forest model achieved the highest overall classification accuracy of 89%, while the k-NN model performed best for detecting directly relevant content, with an accuracy of 63%. Although promising overall, the classification accuracy for the directly relevant category indicates room for improvement. Our findings highlight the value of spatial analysis in enhancing the reliability of SM data (SMD) during crisis events. By bypassing textual analysis, this framework supports relevance classification based solely on geospatial behaviour, offering a novel method for evaluating content trustworthiness. This spatial approach can complement existing crisis informatics tools and be extended to other disaster types and event-based applications. Full article

Drug addiction is a rising concern globally that has deeply attracted the attention of the healthcare sector. The United States is not an exception, and the drug addiction crisis there is even more serious, with 10% of adults having faced substance use disorder, while around 75% of this number has been reported as not having received any treatment. Surprisingly, there are annually over 70,000 deaths reported as being due to drug overdose. Researchers are continually searching for solutions, as the current strategies have been ineffective. Health informatics platforms like electronic health records, telemedicine, and the clinical decision support system have great potential in tracking the healthcare data of patients on an individual basis and provide precise medical support in a private space. Such technologies have been found to be useful in identifying the risk factors of drug addiction among people and mitigating them. Moreover, the platforms can be used to check prescriptions of addictive drugs such as opioids and caution healthcare providers. Programs such as the Prescription Drug Monitoring Program (PDMP) and the Drug and Alcohol Services Information Systems (DASIS) are already in action in the US, but the situation demands more in-depth studies in order to mitigate substance use disorders. Artificial intelligence (AI), when combined with health informatics, can aid in the analysis of large amounts of patient data and aid in classifying nature of addiction to assist in the provision of personalized care. Full article

Husserl told readers that there are two ways to understand his theory, namely “starting from the world of life” or “starting from psychology”. We believe that theoretical informatics and information philosophy can be combined with the Husserl phenomenological movement as two important options to overcome the crisis of contemporary natural science. The purposes of this article are to analyze the ontological and epistemological roots of the scientific “crisis”; to criticize the one-sidedness of the mainstream of Western science and philosophy over the past 2300 years; to develop and perfect the foundation and core of information science: “theoretical informatics”; to apply the experience of “Information Psychology” to the “discipline informatization” in Law, Ethics, Linguistics, etc.; and to abstract information ontology, epistemology, and axiology based on theoretical informatics. Full article

The creation of ecological aesthetics is a response to the ecological crisis in the field of aesthetics. Based on the grand goal of the construction of an ecological civilization, research on ecological aesthetics has emerged. However, ecological aesthetics has failed to keep pace with the times in terms of informatization. If the ecological aesthetics of an information civilization wants to realize an energy-level transition and surpass the traditional vision, it is necessary to pay attention to its information factor. In order for the eco-aesthetics of an information civilization to make an energy leap beyond the traditional eco-aesthetic vision, it is necessary to pay attention to the information factor of eco-aesthetics. Information thinking generated from information science and information philosophy can provide a new solution to the dilemma in ecological aesthetics in modern times. Full article

The end goal of technological advancement used in crisis response and recovery is to prevent, reduce or mitigate the impact of a crisis, thereby enhancing sustainable recovery. Advanced technological approaches such as social media, machine learning (ML), social network analysis (SNA), and big data are vital to a sustainable crisis management decisions and communication. This study selects 28 articles via a systematic process that focuses on ML, SNA, and related technological tools to understand how these tools are shaping crisis management and decision making. The analysis shows the significance of these tools in advancing sustainable crisis management to support decision making, information management, communication, collaboration and cooperation, location-based services, community resilience, situational awareness, and social position. Moreover, the findings noted that managing diverse outreach information and communication is increasingly essential. In addition, the study indicates why big data and language, cross-platform support, and dataset lacking are emerging concerns for sustainable crisis management. Finally, the study contributes to how advanced technological solutions effectively affect crisis response, communication, decision making, and overall crisis management. Full article

Background: An increase in opioid use has led to an opioid crisis during the last decade, leading to declarations of a public health emergency. In response to this call, the Houston Emergency Opioid Engagement System (HEROES) was established and created an emergency access pathway into long-term recovery for individuals with an opioid use disorder. A major contributor to the success of the program is retention of the enrolled individuals in the program. Methods: We have identified an increase in dropout from the program after 90 and 120 days. Based on more than 700 program participants, we developed a machine learning approach to predict the individualized risk for dropping out of the program. Results: Our model achieved sensitivity of 0.81 and specificity of 0.65 for dropout at 90 days and improved the performance to sensitivity of 0.86 and specificity of 0.66 for 120 days. Additionally, we identified individual risk factors for dropout, including previous overdose and relapse and improvement in reported quality of life. Conclusions: Our informatics approach provides insight into an area where programs may allocate additional resources in order to retain high-risk individuals and increase the chances of success in recovery. Full article

The given article focuses on the benefit of harvested Ambient Geographic Information (AGI) as complementary data sources for severe weather events and provides methodical approaches for the spatio-temporal analysis of such data. The perceptions and awareness of Twitter users posting about severe weather patterns were explored as there were aspects not documented by official damage reports or derived from official weather data. We analysed Tweets regarding the severe storm event Friederike to map their spatio-temporal patterns. More than 50% of the retrieved >23.000 tweets were geocoded by applying supervised information retrievals, text mining, and geospatial analysis methods. Complementary, central topics were clustered and linked to official weather data for cross-evaluation. The data confirmed (1) a scale-dependent relationship between the wind speed and the societal echo. In addition, the study proved that (2) reporting activity is moderated by population distribution. An in-depth analysis of the crowds’ central topic clusters in response to the storm Friederike (3) revealed a plausible sequence of dominant communication contents during the severe weather event. In particular, the merge of the studied AGI and other environmental datasets at different spatio-temporal scales shows how such user-generated content can be a useful complementary data source to study severe weather events and the ensuing societal echo. Full article

The authors decided to investigate the impact of the lockdown period and the resulting limitations in informatics education, especially programming, in out-of-school electronics courses using traditional and distance learning modes in primary school COVID-19 pandemic settings. Two extracurricular courses were held successively; the first electronics course was performed in a traditional out-of-school learning mode using Arduino kits, while the other was held using the TinkerCad circuits virtual environment in distance learning mode. A structured questionnaire was administered to students to map their knowledge of programming. The questionnaire consists of three emotional dimensions: enjoyment, satisfaction and motivation. The fourth dimension was dedicated to the students’ programming outcomes. Three emotional dimensions were addressed to primary school students, while the fourth dimension was addressed to the tutors’ observations toward the students’ programming outcomes. The obtained results revealed that learning modes have no significant impact on students perceiving the programming issues. However, three emotional dimensions revealed a significant difference in the students’ enjoyment, satisfaction and motivation in favor of the traditional learning mode. Our findings are of particular interest in light of possible crisis-prompted distance education in the future but can also serve to inform government institutions and policymakers seeking to develop effective concepts for successful distance learning. Full article

Disaster events and their economic impacts are trending, and climate projection studies suggest that the risks of disaster will continue to increase in the near future. Despite the broad and increasing social effects of these events, the empirical basis of disaster research is often weak, partially due to the natural paucity of observed data. At the same time, some of the early research regarding social responses to disasters have become outdated as social, cultural, and political norms have changed. The digital revolution, the open data trend, and the advancements in data science provide new opportunities for social science disaster research. We introduce the term computational social science of disasters (CSSD), which can be formally defined as the systematic study of the social behavioral dynamics of disasters utilizing computational methods. In this paper, we discuss and showcase the opportunities and the challenges in this new approach to disaster research. Following a brief review of the fields that relate to CSSD, namely traditional social sciences of disasters, computational social science, and crisis informatics, we examine how advances in Internet technologies offer a new lens through which to study disasters. By identifying gaps in the literature, we show how this new field could address ways to advance our understanding of the social and behavioral aspects of disasters in a digitally connected world. In doing so, our goal is to bridge the gap between data science and the social sciences of disasters in rapidly changing environments. Full article

Due to instant availability of data on social media platforms like Twitter, and advances in machine learning and data management technology, real-time crisis informatics has emerged as a prolific research area in the last decade. Although several benchmarks are now available, especially on portals like CrisisLex, an important, practical problem that has not been addressed thus far is the rapid acquisition, benchmarking and visual exploration of data from free, publicly available streams like the Twitter API in the immediate aftermath of a crisis. In this paper, we present such a pipeline for facilitating immediate post-crisis data collection, curation and relevance filtering from the Twitter API. The pipeline is minimally supervised, alleviating the need for feature engineering by including a judicious mix of data preprocessing and fast text embeddings, along with an active learning framework. We illustrate the utility of the pipeline by describing a recent case study wherein it was used to collect and analyze millions of tweets in the immediate aftermath of the Las Vegas shootings in 2017. Full article

Pathogenic antibiotic resistant bacteria pose one of the most important health challenges of the 21st century. The overuse and abuse of antibiotics coupled with the natural evolutionary processes of bacteria has led to this crisis. Only incremental advances in antibiotic development have occurred over the last 30 years. Novel classes of molecules, such as engineered antibodies, antibiotic enhancers, siderophore conjugates, engineered phages, photo-switchable antibiotics, and genome editing facilitated by the CRISPR/Cas system, are providing new avenues to facilitate the development of antimicrobial therapies. The informatics revolution is transforming research and development efforts to discover novel antibiotics. The explosion of nanotechnology and micro-engineering is driving the invention of antimicrobial materials, enabling the cultivation of “uncultivable” microbes and creating specific and rapid diagnostic technologies. Finally, a revival in the ecological aspects of microbial disease management, the growth of prebiotics, and integrated management based on the “One Health” model, provide additional avenues to manage this health crisis. These, and future scientific and technological developments, must be coupled and aligned with sound policy and public awareness to address the risks posed by rising antibiotic resistance. Full article

Early warning consists of monitoring precursors of a potential hazard to understand if it is evolving to a real risk and then be able to orchestrate an early response before the event happens in order to reduce its impact and damages. It mainly consists on collecting updated and reliable data that can help emergency operators to understand how a situation is evolving and project its consequences, that is, to support situation awareness on a potential risk. This process could be improved by integrating volunteers and citizens into the data collection process given that they are intelligent sensors equipped with mobile devices that can be used almost everywhere to collect and share information. In this paper we introduce a system relying upon ubiquitous computing to integrate citizens in checking the evolution of potential hazards. An asynchronous focus group technique to assess the system with EM professionals is also described in the paper. Full article