Tracing the Lexicon of War: A Diachronic NLP Study of Iraqi Newspapers (1980–2025)
Bibliographic record
Abstract
Objectives: This article uses natural language processing (NLP) to trace how Iraqi newspapers have spoken about war, peace, and the nation from 1980 to 2025. Drawing on a diachronic corpus of Arabic press texts that spans the Iran–Iraq War, the 1991 Gulf War, sanctions, the 2003 invasion, sectarian conflict, the fight against ISIS, and the fragile “post-war” present, it asks how the lexicon of war evolves and how imaginaries of nation and peace appear and recede across these crises. Methods: The study compiles a 12-million-word corpus from three major Iraqi newspapers, sampled at five-year intervals. After cleaning and normalisation, the corpus is segmented into eight historical periods. Using word-frequency analysis, collocation measures, and word-embedding models, the article tracks shifts in the usage and semantic neighbourhoods of keywords such as ḥarb (war), salām (peace), waṭan (homeland), shaʿb (people), and amān (security). Results: The analysis shows that the lexicon of war is not static: terms of victory and glory dominant in the 1980s gradually give way to vocabularies of siege, sanctions, and martyrdom in the 1990s, and later to the language of sectarianism, terrorism, and reconstruction after 2003. Quantitatively, ḥarb remains more frequent than salām in every period—for example, 420 vs. 36 tokens per million in 1980–1984 and 310 vs. 82 in 2015–2025—so that the salām:ḥarb ratio almost triples from 0.09 to 0.26 over the corpus. References to “peace” rise after 2014 but are often collocated with terms such as “fragile,” “conditional,” and “agreement,” signalling an anxious rather than triumphant peace. Conclusions: The findings illustrate how diachronic NLP complements close reading by uncovering patterns of continuity and change that event-specific analysis often misses.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.006 | 0.010 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".