BCBia Carneiro

Bia Carneiro

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bia Carneiro has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Responsible use of artificial intelligence and machine learning for food security early warning systems

    by Weston Anderson, Inbal Becker-Reshef, Nicholas Bodanac, Bia Carneiro, Dave English, Andrew Hoell, Tim Hoffine, YanYan Liu, Mélissande Machefer, Michele Meroni, et al.


  • Open Access

    Real-time Nowcasting of Food Insecurity with Google Trends Data

    by Nicola Caravaggio, Bia Carneiro, Giuliano Resce

    This research explores the potential of Google Trends (GT) as a tool for generating a daily index of food insecurity at the national level, focusing on countries monitored by the Famine Early Warning Systems Network (FEWS NET) and the U.S. Global Fragility Act (GFA). Drawing inspiration from previous studies on GT’s predictive capabilities, the authors employ Natural Language Processing (NLP) to analyze FEWS NET’s food security reporting and identify key predictors of food insecurity using a LASSO regression approach. The predictors are then queried on GT to construct a daily sentiment index for each country. Unlike other approaches, the study considers multiple languages and weighs search terms based on LASSO coefficients. The resulting Synthetic Search Interest (SSI) Index for food insecurity demonstrates a statistically significant correlation with the UN’s Food and Agriculture Organization’s (FAO) share of the population in severe food insecurity, affirming GT’s potential as a monitoring tool. This research introduces a novel methodology and valuable insights for leveraging real-time data to enhance early warning systems in food security. JEL Classification: C53, C82, Q18.


  • Open Access

    Text mining and machine learning reveal global determinants of food insecurity

    by Bia Carneiro, Giuliano Resce, Nicola Caravaggio, Agapito Emanuele Santangelo, Giosuè Ruscica, Giulia Tucci, Grazia Pacillo, Gary Eilerts, Peter Läderach, Kevin Coffey

    This study applies Natural Language Processing (NLP) and Machine Learning (ML) to investigate global historical trends in food security. Using USAID’s Famine Early Warning Systems Network’s (FEWS NET) comprehensive reports spanning over two dozen countries, it explores prevalent dimensions such as shocks, outcomes, and coping capacities, offering insights into long-term food security conditions. Results highlight the prevalence of market and climate impacts across the countries and period considered. Based on results from the topic classification, ML models were applied to determine the most important factors that predict food insecurity. The analysis confirmed market shocks as the main predictors of food insecurity globally. The approach demonstrates the potential for extracting valuable insights from narrative sources that can support decision-making and strategic planning. This integrated approach not only enhances understanding of food security but also presents a versatile tool applicable beyond the context of humanitarian aid.


  • Open Access

    Who talks about climate, peace and security? A social media analysis to identify key global actors

    by Giulia Tucci, Bia Carneiro, Giulia Caroli, Grazia Pacillo

    Uncovering key actors within a policy network provides pathways for engagement, consensus-building, partnership development, and understanding the diffusion of knowledge in a given debate. Given the unprecedented scale of the climate emergency, the emerging field of climate security has rapidly gained centrality in academic and policy fora, as well as in the public debate. Yet, a systematic analysis of the main actors engaged in this space is missing. This study draws from digital methods and network analysis techniques to employ a method for identifying relevant actors, focusing on Twitter (now X) from 2014 to 2022, with the objective of systematically spotting the major actors driving and shaping public discussions around climate security. The research also demonstrates how institutions can position themselves within such issue networks through a case study of the CGIAR, the largest publicly funded global research partnership for a food-secure future dedicated to transforming food, land, and water systems in a climate crisis that has recently positioned itself in this community. Results reveal that the climate security debate on social media is predominantly institutional, with research bodies and international organizations from the Global North as central elements. While CGIAR is a relatively new actor, it is already centrally located in the network, maintaining strong connections with other major players, which places it in a strategic position to enhance its influence and reach. Understanding this discursive landscape is crucial for institutions and organizations to identify opportunities for effective engagement, partnership, and positioning in such an increasingly salient field of research and practice.

  • Open Access

    Determinants of food insecurity: a text mining approach

    by Bia Carneiro, Giuliano Resce, Giosuè Ruscica, Gary Eilerts, Nicola Caravaggio, Agapito Santangelo, Giulia Tucci, Grazia Pacillo, Peter Läderach, Kevin Coffey

    This study applies Natural Language Processing (NLP) and Machine Learning (ML) to investigate global historical trends in food security. Using USAID’s Famine Early Warning Systems Network’s (FEWS NET) comprehensive reports spanning over two dozen countries, it explores prevalent dimensions such as shocks, outcomes, and coping capacities, offering insights into long-term food security conditions. Results highlight the prevalence of market and climate impacts across the countries and period considered. Based on results from the topic classification, ML models were applied to determine the most important factors that predict food insecurity. The analysis confirmed market shocks as the main predictors of food insecurity, globally. The approach demonstrates the potential for extracting valuable insights from narrative sources that can support decision-making and strategic planning. This integrated approach not only enhances understanding of food security but also presents a versatile tool applicable beyond the context of humanitarian aid.

  • Open Access

    Nowcasting food insecurity interest Google Trends data

    by Nicola Caravaggio, Bia Carneiro, Giuliano Resce

    This research explores the potential of Google Trends (GT) data as a tool for generating a daily index of food insecurity at the national level, focusing on regions monitored by the Famine Early Warning Systems Network (FEWS NET) and the Global Fragility Act (GFA). Drawing inspiration from previous studies on GT's predictive capabilities, the authors employ Natural Language Processing (NLP) to analyse food security reporting from FEWS NET documents. We identify key predictors of food insecurity using a LASSO regression approach and construct a daily economic sentiment index (DESI) for each country. Unlike traditional methods, the study considers multiple languages and weights search terms based on LASSO coefficients. The resulting Synthetic Search Interest (SSI) index for food insecurity demonstrates a statistically significant correlation with FAO's share of the population in severe food insecurity, affirming GT's potential as a monitoring tool. The research contributes a novel methodology and insights into leveraging real-time data for early warnings in food security.

  • Open Access

    A multi-platform framework for nowcasting social phenomena: a case study for food insecurity

    by Bia Silveira Carneiro, Giuliano Resce, Giulia Tucci, Giosuè Ruscica, Nicola Caravaggio, Laura Fanelli, Agapito Emanuele Santangelo, Pietro Cruciata

    Given the growing significance of internet-based information flows, this research proposes a conceptual framework that integrates digital platforms to nowcast social phenomena, applied to the context of food security monitoring in the Global South. Building on the foundations of Digital Methods and online issue mapping, our research objective is to establish a multi-modal, multi-media model that monitors events from different perspectives to identify potential early warning signals arising from the data, ultimately informing policy actors and supporting early action. We apply three analytical processes: social listening, media monitoring and search interest analysis. Exploratory analysis on data from Zimbabwe point to the feasibility of the models applied to identify food security dimensions in text and search engine data. Further analysis is needed to interpret converging and diverging trends across the data streams, and their implications to food insecurity early warning.

  • Open Access

    Climate security dialogues on Twitter: An annotated dataset

    by Bia Carneiro, Giulia Tucci


  • Open Access

    Food insecurity trends in the Famine Early Warning Systems Network

    by Giosuè Ruscica, Bia Carneiro, Chiara Perfetto, Giuliano Resce, Giulia Tucci

    Periodic country analyses elaborated by the Famine Early Warning Systems Network of the United States Agency for International Development (FEWS NET) comprises a unique source of knowledge encompassing consistent reporting in over two dozen countries. This paper proposes a systematic assessment of this documentation to provide a comprehensive historical overview of food insecurity in FEWS NET covered countries. We apply an integrated machine learning approach, particularly through text mining techniques, to analyse reports. Results show a wide heterogeneity in topic prevalence, both at the temporal and geographical scales. Overall, the evidence shows that advances in machine learning and big data research offer great potential for international development agencies to leverage the vast information generated from reports to gain new insights, providing analytics that can support and improve decision-making.