Development economics · Humanitarian early warning · Applied NLP

Turning bilingual news into an auditable food-crisis verification queue

I designed a research prototype that converts English and Arabic news into location-level evidence for food-insecurity monitoring across Iraq, Jordan, Lebanon, Palestine, and Syria. The system helps analysts decide where to investigate—not whether a crisis exists.

5Mashriq countries
2news languages
167risk-factor phrases
357geographic entities
12risk themes

The question

Can fast-moving news strengthen food-security surveillance when outcome data arrive late?

Food crises are local, dynamic, and costly to miss. Yet the classifications used to measure food insecurity are often released less frequently than news. Articles can surface drought, price pressure, conflict, displacement, crop failure, and access constraints sooner—but media signals are noisy, unevenly distributed, and easy to over-interpret.

The objective was therefore not to label places as “in crisis.” It was to create a transparent screening tool that ranks locations for analyst verification, preserves the evidence behind every flag, and can later be tested against future IPC or Cadre Harmonisé outcomes.

Design principles

The constraints became part of the methodology

Data scarcity

No labels, no false precision

With one month of articles and no food-security outcome, a supervised model would not be credible. I built an evidence index and a leakage-safe evaluation plan instead.

Multilingual evidence

English and Arabic stay visible

Language-specific retrieval is reported separately before signals are combined, making coverage gaps and translation risk inspectable.

Operational accountability

Every score links back to evidence

Analysts can inspect the article, source, language, matched phrase, theme, and location behind a flag before escalating it.

Methodology

From raw articles to a policy-facing review queue

  1. 01

    Audit and repair the taxonomy

    I standardized punctuation and encoding, repaired a malformed coup d’état entry that broke the category join, and validated all 167 factors against 12 themes.

  2. 02

    Build a reproducible bilingual seed lexicon

    The supplied Arabic column was empty. I added one deterministic Arabic seed phrase per factor, normalized diacritics and common spelling variants, and documented the need for native-speaker adjudication and dialect expansion.

  3. 03

    Retrieve phrases without substring leakage

    A longest-first token n-gram matcher prevents a term such as rise from matching surprise or being double-counted inside price rise. Exact hashes remove duplicate articles.

  4. 04

    Resolve geography conservatively

    Articles are matched to the supplied country, province, and district aliases. The resolver keeps the most specific unambiguous location and falls back to a shared parent rather than inventing precision.

  5. 05

    Separate signal from confidence

    A beta-binomial empirical-Bayes model partially pools sparse locations. The signal score summarizes risk prevalence, mention intensity, and thematic breadth; confidence separately reflects article volume, source diversity, and bilingual support.

  6. 06

    Connect prediction to decisions

    The analysis applies a cost-sensitive prevention framework: a desk review, field verification, and material intervention should each have different thresholds because their costs and effectiveness differ.

Analytical workflow

Four steps turn reporting into a review queue

  1. 01 Inputs News, risk taxonomy and place names
  2. 02 Measure Bilingual phrase and location matching
  3. 03 Estimate Partially pooled location-level signals
  4. 04 Act Evidence-linked analyst review queue

Results

A complete measurement prototype—with an explicit boundary on what it proves

What the implementation delivered

  • All 167 risk factors retained, categorized, and assigned an Arabic seed phrase.
  • Hierarchical matching across 357 countries, provinces, and districts.
  • Article-level evidence tables and bilingual retrieval diagnostics.
  • A location ranking with uncertainty, source diversity, and language corroboration.
  • Robustness tests across multiple empirical-Bayes prior strengths.
  • An operational plan for forward validation, calibration, monitoring, and governance.
Two direct-labelled bar charts showing risk-factor taxonomy coverage and phrases retrieved from the validation fixture
Retrieval diagnostics. The left panel audits what the dictionary can detect; the right panel shows what the test corpus triggers. The synthetic fixture validates behavior but supports no geographic conclusion.
Illustrative location verification queue separating signal score from evidence confidence
Decision-oriented output. Signal and confidence are deliberately separate. A high-signal, low-confidence location should trigger verification—not an automated declaration or intervention.

From prototype to forecast

How I would test whether news adds value

Build a vintage-correct district-month panel

Join future IPC/CH outcomes to lagged news, crisis history, food prices, CHIRPS rainfall, vegetation anomalies, conflict and humanitarian-access events, displacement, population, seasonality, and neighboring-district signals.

Compare nested baselines

Evaluate prevalence-only, crisis-history, structured-only, news-only, and combined models. The relevant claim is the incremental performance of news over history and structured early-warning data.

Validate forward in time and across space

Use expanding time windows and geographic holdouts. Report precision-recall performance, top-K recall under analyst capacity, Brier score, calibration, and country/language subgroups.

Choose thresholds from policy costs

Translate calibrated risk into actions using intervention cost, effectiveness, and the cost of a missed crisis. Monitor source outages, media imbalance, geographic coverage, and score drift after deployment.

Why this work matters

Relevance to development institutions

The project connects text-as-data, spatial targeting, uncertainty, and decision theory to a real operational problem. It is designed for settings where timeliness matters, labels are scarce, and false confidence can misallocate limited attention or resources.

Capabilities demonstrated

Development economics Food security Multilingual NLP Geospatial analytics Bayesian shrinkage Rare-event forecasting Decision theory Responsible AI Research design

More work

Explore more applied data projects

Return to the portfolio for more work at the intersection of development economics, policy, and data science.

View portfolio