Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ochieng, Millicent, Thieme, Anja, Ezeani, Ignatius, Ueno, Risa, Maina, Samuel, Ronen, Keshet, Gonzalez, Javier, O'Neill, Jacki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918115836690432
author Ochieng, Millicent
Thieme, Anja
Ezeani, Ignatius
Ueno, Risa
Maina, Samuel
Ronen, Keshet
Gonzalez, Javier
O'Neill, Jacki
author_facet Ochieng, Millicent
Thieme, Anja
Ezeani, Ignatius
Ueno, Risa
Maina, Samuel
Ronen, Keshet
Gonzalez, Javier
O'Neill, Jacki
contents Sentiment analysis in low-resource, culturally nuanced contexts challenges conventional NLP approaches that assume fixed labels and universal affective expressions. We present a diagnostic framework that treats sentiment as a context-dependent, culturally embedded construct, and evaluate how large language models (LLMs) reason about sentiment in informal, code-mixed WhatsApp messages from Nairobi youth health groups. Using a combination of human-annotated data, sentiment-flipped counterfactuals, and rubric-based explanation evaluation, we probe LLM interpretability, robustness, and alignment with human reasoning. Framing our evaluation through a social-science measurement lens, we operationalize and interrogate LLMs outputs as an instrument for measuring the abstract concept of sentiment. Our findings reveal significant variation in model reasoning quality, with top-tier LLMs demonstrating interpretive stability, while open models often falter under ambiguity or sentiment shifts. This work highlights the need for culturally sensitive, reasoning-aware AI evaluation in complex, real-world communication.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04199
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts
Ochieng, Millicent
Thieme, Anja
Ezeani, Ignatius
Ueno, Risa
Maina, Samuel
Ronen, Keshet
Gonzalez, Javier
O'Neill, Jacki
Computation and Language
Sentiment analysis in low-resource, culturally nuanced contexts challenges conventional NLP approaches that assume fixed labels and universal affective expressions. We present a diagnostic framework that treats sentiment as a context-dependent, culturally embedded construct, and evaluate how large language models (LLMs) reason about sentiment in informal, code-mixed WhatsApp messages from Nairobi youth health groups. Using a combination of human-annotated data, sentiment-flipped counterfactuals, and rubric-based explanation evaluation, we probe LLM interpretability, robustness, and alignment with human reasoning. Framing our evaluation through a social-science measurement lens, we operationalize and interrogate LLMs outputs as an instrument for measuring the abstract concept of sentiment. Our findings reveal significant variation in model reasoning quality, with top-tier LLMs demonstrating interpretive stability, while open models often falter under ambiguity or sentiment shifts. This work highlights the need for culturally sensitive, reasoning-aware AI evaluation in complex, real-world communication.
title Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts
topic Computation and Language
url https://arxiv.org/abs/2508.04199