Congo

Large language models as measurement instruments in applied economics: A 10-country public-discourse panel on food and nutrition security in Africa, 2010–2025

Large language models (LLM) are increasingly used in applied economics to convert unstructured text into structured empirical measures. This paper examines their use as measurement instruments through a 10-country public-discourse panel on food and nutrition security in Africa from 2010 to 2025. The panel covers Somalia, South Sudan, Sudan, Democratic Republic of the Congo, Nigeria, Ethiopia, Kenya, Niger, Mali, and Burkina Faso, and contains 206 document-level records drawn from public early-warning, humanitarian, government, and technical sources. Each record is organized by country, date, source type, geography, benchmark type, benchmark phase where available, leakage risk, and a set of generated coding variables describing food-security dimension, text severity, narrative frame, tone, attribution, and evidence type. The paper treats LLM-coded outputs not as ground truth, but as generated variables subject to measurement error, source-selection bias, benchmark leakage, and uncertainty arising from incomplete or uneven source text. A conservative validation sample is limited to records with completed source-grounded excerpts, while an exploratory validation sample uses the broader metadata-supported corpus to examine phase coverage across benchmark categories. The results illustrate both the promise and the limits of LLM-assisted public-discourse measurement. Public documents can be transformed into transparent, auditable indicators of food-security stress, but their validity depends on document sampling, excerpt quality, benchmark independence, source diversity, and careful distinction between technical classifications and independent discourse. The paper contributes to the emerging literature on LLMs in economics by shifting attention from general productivity uses toward the practical conditions under which LLM-assisted text measurement can support applied research and policy analysis. A reproducibility package accompanies the study and includes the coded data, validation samples, codebook, data dictionary, AI-use disclosure, leakage documentation, and scripts for reproducing the descriptive results.

Gender attitudes in agriculture and positivity bias: A survey experiment in four countries in Sub-Saharan Africa

Extensive prior research has demonstrated that reducing gender discrimination enhances women’s empowerment, promotes more inclusive livelihoods, increases agricultural productivity, and improves other development outcomes. This study aims to contribute to documenting and informing the measurement of gender attitudes that relate directly to reaching, benefiting, and empowering women through agricultural innovations. By analyzing data from 8,051 survey respondents across study sites in Democratic Republic of the Congo, Ethiopia, Nigeria, and Rwanda, our findings emphasize both commonalities and differences in gender attitudes across different contexts. Furthermore, by including a survey-based experiment during data collection, we assess whether gender-attitude statements vary depending on whether they are presented in a positive frame (focusing on equality) or in a negative frame (focusing on inequality). On average, rural women and men respondents across all countries supported more than half of the gender-equality statements. Some gender-inequality attitudes persisted across the four countries but varied in magnitude and by location, age group, and specific statement or theme. Framing matters: respondents exposed to a positive framing supported 16 percent more gender-equality statements than those exposed to a negative framing. The study highlights two main implications. First, the findings indicate the importance of considering both restrictive attitudes and those that reflect gender-equality opportunities as being in the vanguard. Accordingly, gender-focused interventions should adopt strategies that challenge normative views of women as supporting rather than leading actors in agriculture and economic activities. Second, gender-attitude measures do not perfectly align with country-level gender-equality indicators or with empowerment at the intrahousehold level. They therefore capture a distinct dimension and merit their own indicators.

The complex economics of a complete ban on child labor in the cobalt supply chain: The case of the DR Congo