Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications

arXiv cs.CL Papers
emotion-analysis natural-language-processing interpretability faithfulness nsm explanation

Summary

This paper proposes an emotion analysis interface using Natural Semantic Metalanguage (NSM) to generate faithful, interpretable explanations for emotion classifications, trading slight accuracy for verifiability.

arXiv:2607.00661v1 Announce Type: new Abstract: Explanations for emotion classifiers are usually produced post hoc, with no guarantee that they reflect the computation behind the label. We present an explication interface for event-based emotion analysis. A parser maps the input text to an explication, a short script in the closed vocabulary of Natural Semantic Metalanguage organized into twelve typed slots, and a fixed decision list of rules transcribed from published semantic definitions computes the label from the explication alone. The faithfulness guarantee is therefore causal and definitional, while all empirical risk lives in the learned parser, which the per-line entailment interface makes auditable against the input. On crowd-sourced event descriptions, our fine-tuned parser reaches 0.33 accuracy and 0.48 selective accuracy on a small held-out set, suggesting that the interface trades insignificant accuracy difference to a black-box model for a verifiable, inspectable decision basis for first-person event-based emotion analysis. We also release EmoExpl-1200 with per-line verification metadata and the full rule set.
Original Article
View Cached Full Text

Cached at: 07/02/26, 05:38 AM 

# Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications
Source: [https://arxiv.org/abs/2607.00661](https://arxiv.org/abs/2607.00661)
[View PDF](https://arxiv.org/pdf/2607.00661)

> Abstract:Explanations for emotion classifiers are usually produced post hoc, with no guarantee that they reflect the computation behind the label\. We present an explication interface for event\-based emotion analysis\. A parser maps the input text to an explication, a short script in the closed vocabulary of Natural Semantic Metalanguage organized into twelve typed slots, and a fixed decision list of rules transcribed from published semantic definitions computes the label from the explication alone\. The faithfulness guarantee is therefore causal and definitional, while all empirical risk lives in the learned parser, which the per\-line entailment interface makes auditable against the input\. On crowd\-sourced event descriptions, our fine\-tuned parser reaches 0\.33 accuracy and 0\.48 selective accuracy on a small held\-out set, suggesting that the interface trades insignificant accuracy difference to a black\-box model for a verifiable, inspectable decision basis for first\-person event\-based emotion analysis\. We also release EmoExpl\-1200 with per\-line verification metadata and the full rule set\.

## Submission history

From: Frank Xing \[[view email](https://arxiv.org/show-email/da38cbf4/2607.00661)\] **\[v1\]**Wed, 1 Jul 2026 09:10:14 UTC \(100 KB\)

Similar Articles