MétaCan
Menu
← Back to cohort
Record W6990204217

Cultural Analytics and Environmental News: A Novel LLM Approach to Cross-Cultural Understanding of Narrative Morals

2024· dissertation· en· W6990204217 on OpenAlexfundno aff

Bibliographic record

VenueeScholarship@McGill (McGill) · 2024
Typedissertation
Languageen
FieldSocial Sciences
TopicEducational Curriculum and Learning Methods
Canadian institutionsnot available
FundersMcGill University
KeywordsNarrativeAnalyticsNarrative inquiryPerspective (graphical)Field (mathematics)Reflection (computer programming)
DOInot available

Abstract

fetched live from OpenAlex

Cette étude examine l'utilisation de modèles de langage avancés (LLMs) tels que GPT-4 pour découvrir et analyser les messages narratifs latents dans les articles de presse relatifs à l'environnement issus des médias nord-américains et chinois. Avec la définition du “message narratif” comme la morale intrinsèque ou la leçon intégrée dans une histoire, l'extraction morale assistée par LLM est appliquée à un ensemble de données comprenant environ 15 000 articles de presse en anglais et en mandarin, catégorisés par thèmes liés au climat et alignements idéologiques. L'analyse des résultats extraits s'étend sur trois dimensions comparatives : les sources nord-américaines versus chinoises, les perspectives libérales versus conservatrices, et les sources étatiques (Chine continentale) versus offshore (Hong Kong et Taïwan). Les résultats mettent en lumière des différences marquées dans la manière dont les agents et les valeurs narratives sont présentés à travers différents contextes culturels et idéologiques. Par exemple, les médias nord-américains ont tendance à mettre en avant des thèmes individualistes et axés sur la crise, tandis que les médias chinois soulignent des récits centrés sur le développement et la coopération. Cette recherche souligne les capacités des LLMs à disséquer et à influencer la communication sur le climat et l'environnement, offrant de nouvelles perspectives sur les systèmes de croyances collectifs qui encadrent le discours public sur les problèmes environnementaux dans différents contextes culturels

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 imitation

Not 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.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.012
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.014
Threshold uncertainty score0.031

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.012
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0040.002
Science and technology studies0.0070.019
Scholarly communication0.0140.018
Open science0.0020.006
Research integrity0.0020.005
Insufficient payload (model declined to judge)0.0090.001

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.

Opus teacher head0.087
GPT teacher head0.380
Teacher spread0.294 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueeScholarship@McGill (McGill)→Same topicEducational Curriculum and Learning Methods→French-language works237,207→