Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications
2026-07-01 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors created a system to explain how emotion labels are assigned to event descriptions by breaking down the input into a simple script using a fixed set of meanings. Instead of guessing the emotions afterward, their method uses clear rules to decide emotions directly from this script, making the process easier to understand and check. Their approach is not as accurate as some black-box models but offers transparency and lets people verify how emotions are determined. They also provide a dataset and all the rules they used for others to explore.
emotion classificationNatural Semantic Metalanguageexplanation interfaceevent-based emotion analysissemantic parsingdecision rulesfaithfulnesscrowd-sourced datamodel interpretability
Authors
Frank Xing, Erik Cambria
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.