EPJ Data Science is delighted to present a topical issue on Data for the Wellbeing of Most Vulnerable.
The scale, reach, and real-time nature of digital trace generation is opening new frontiers for understanding the vulnerabilities in our societies, including inequalities and fragility in the face of a changing world. Tracking seasonal illnesses like the flu, aiding response efforts in emergencies, and quantifying systemic inequalities are just some of the applications of big data to the study of vulnerabilities. Vulnerable populations may include children, elderly, racial or ethnic minorities, socioeconomically disadvantaged, underinsured or those with certain medical conditions. Unfortunately, they are often absent in commonly used data sources. Further, data and algorithmic biases, especially in the light of the recent generative AI models, spotlight the awareness needed to build inclusive and fair systems when dealing with crisis management.
The emergence of crises, ranging from natural disasters to pandemics, underscores the necessity of leveraging digital data for crisis response and management. This data, characterized by its immediacy and granularity, can inform timely and targeted interventions, making it a pivotal resource for researchers and practitioners working on crisis management and support for vulnerable populations.
Thus, the aim of this topical collection is to encourage the community to use new sources of data as well as methodologies to study the wellbeing of vulnerable populations. The selection of appropriate data sources, identification of vulnerable groups, and ethical considerations in the subsequent analysis are of great importance in the extension of the benefits of big data revolution to these populations. As such, the topic is highly multidisciplinary, bringing together researchers and practitioners in computer science and AI, epidemiology, demography, linguistics, and many others.
Relevant topics include, but are not limited to:
- The use of digital data in tracking and responding to crises
- Establishing cohorts, data de-biasing
- Validation via individual-level or aggregate-level data
- Linking data to outbreak patterns and other well-being indicators
- Population data sources for validation
- Correlation analysis and other statistical methods
- Longitudinal analysis on social media
- Spatial, linguistic, and temporal analyses
- Privacy, ethics, and informed consent
- Biases and quality concerns around vulnerable groups in LLMs
- Data quality issues specific to datasets in crisis contexts
We encourage submissions from all relevant disciplines. Manuscripts will be subject to a rigorous peer-review process, and accepted papers will be published in a dedicated article collection of EPJ Data Science.
Guest Editors:
Kyriaki Kalimeri, ISI Foundation, Turin, Italy
Daniela Paolotti, ISI Foundation, Turin, Italy
Mattia Mazzoli, ISI Foundation, Turin, Italy
Andreas Kaltenbrunner, Universitat Oberta de Catalunya and Universitat Pompeu Fabra, Barcelona, Spain
Submission deadline: September 15, 2024
Submission Guidelines:
- Papers should be original and not previously published or under review elsewhere.
- If a version of the work was published elsewhere, it should have at least 40% new material.
- Papers should follow the formatting guidelines of EPJ Data Science.
- Papers should be submitted through the journal's online submission system by the submission deadline.
- All submissions will undergo a single-blind peer-review process by two to three experts.
- Submissions will be evaluated and accepted on a rolling basis.
- Accepted publications will be published on the journal website as soon as prepared by the copyediting team.
- Note that EPJ Data Science is an open access journal, with an applicable Article Processing Charge (APC) in case the paper is accepted.
_________________________________