The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse

2026-06-19 · Source: cs.CL updates on arXiv.org · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, quick

Summary

The Meaning Intelligence Framework (MIF) is introduced as a nine-dimension annotation and evaluation schema designed for Nigerian public discourse, aiming to distinguish surface sentiment from true communicative intent. This framework addresses a critical limitation in existing benchmarks like NaijaSenti and AfriSenti, which primarily focus on three-way sentiment polarity. The authors argue that AI system failures in Nigerian discourse stem from context failure rather than translation issues, where an utterance's pragmatic force varies by speaker, audience, and situation. The MIF operationalizes this by scoring dimensions such as register, true intent, irony, and coded subtext. Evaluating Gemini 2.5 Flash, the study found a "Register Gap": zero-shot register classification accuracy was 33.3%, improving to 73.3% (+40 points) when the model received the MIF schema in-context. The composite Meaning Intelligence Score increased by 5.4 points (from 73.2 to 78.6), with notable gains in coded-subtext detection (+10 points) and strategic action recommendation (+10.3 points). A 30-item calibration dataset, annotation guidelines, and the framework specification are publicly released.

Key takeaway

For NLP Engineers developing AI for nuanced public discourse, especially in diverse linguistic environments, relying solely on surface sentiment is insufficient. You should integrate multi-dimensional frameworks like the Meaning Intelligence Framework (MIF) to capture true communicative intent and pragmatic force. Providing explicit context schemas to your language models can significantly improve their understanding of register, coded subtext, and strategic action recommendations, moving beyond simple polarity classification.

Key insights

Context-aware, multi-dimensional frameworks significantly improve AI understanding of nuanced public discourse by addressing pragmatic context failure.

Principles

• AI failures in discourse often stem from context, not translation.
• Multi-dimensional schemas enhance pragmatic force understanding.
• In-context schema provision boosts model performance.

Method

The Meaning Intelligence Framework (MIF) applies a nine-dimension annotation schema to discourse, evaluating language models like Gemini 2.5 Flash with zero-shot versus schema-informed prompting on a calibration dataset.

In practice

• Implement multi-dimensional schemas for nuanced discourse analysis.
• Supply explicit context frameworks to LLMs for improved accuracy.
• Prioritize pragmatic force over surface sentiment in evaluations.

Topics

• Meaning Intelligence Framework
• Nigerian Public Discourse
• Contextual AI
• Natural Language Understanding
• Language Model Evaluation
• Pragmatic Analysis

Best for: Research Scientist, AI Scientist, NLP Engineer

Related on AIssential

• The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse — AI systems fail on Nigerian discourse due to context failure, not translation, requiring deeper meaning intelligence.
• A Cross-Genre Analysis of Discourse Relation Signaling in the GUM Corpus — The paper analyzes discourse relation signaling across diverse genres in the GUM Corpus.
• An NLP-Driven Framework for Curriculum-Labor Market Alignment: Schema-Constrained LLM Extraction, ESCO-Anchored Semantic Matching, and Multi-Dimensional Gap Quantification — An NLP framework uses LLMs and semantic matching to quantify curriculum-labor market competency gaps with high reliability.
• Beyond semantics: the challenges of annotating pragmatic and discourse phenomena — Annotating abstract semantic and pragmatic information is challenging due to its implicit, context-dependent nature.
• Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis — A new SRL framework offers explicit predicate-argument structure and 10x faster inference with modern encoders.
• From Comments to Trends: Studi NLP dan Computational Linguistics dalam Mendeteksi Topik Viral dari… — NLP and computational linguistics are crucial for detecting social media trends from vast, informal, and diverse comment data.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.CL updates on arXiv.org.