[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83516-en":3,"doc-seo-83516-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83516,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Faithful by Definition Emotion Analysis via Natural Semantic Metalanguage Explications","Explanations for emotion classifiers often fail to reflect the computation behind predicted labels. This work introduces an explication interface for event-based emotion analysis grounded in Natural Semantic Metalanguage. A text parser converts input into a twelve-slot, closed-vocabulary explication, while a fixed, rule-based mapper computes the label from the explication alone, ensuring causal definitional faithfulness. Empirical risk is confined to the learnable parser, whose per-line entailment verification enables auditability. On crowd-sourced events, a fine-tuned parser achieves 0.33 accuracy and 0.48 selective accuracy on a small held-out set, and releases EmoExpl-1200 with verification metadata and complete rules.","Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications  \nFrank Xing* and Erik Cambria\\#  \n*University of Reading \\#Nanyang Technological University  \n[z.xing@henley.ac.uk](z.xing@henley.ac.uk) [cambria@ntu.edu.sg](cambria@ntu.edu.sg)  \nAbstract  \nExplanations 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 eventbased 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, anda 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.  \n1 Introduction  \nEmotion analysis now informs content moderation, publichealth screening, customer research, and the evaluation of conversational agents (Rajamanickam et al. 2020; Ma et al. 2020) . In these settings a label alone is rarely sufficient; practitioners need to know why the system produced it, and regulators increasingly require the same. The dominant explanation formats do not meet this need. Post-hoc token attributions frequently disagree with the model’s actual decision process (Jacovi and Goldberg 2020), and free-text rationales generated alongside an answer can rationalize the computation instead of reporting it (Lanham et al. 2023; Madsen, Chandar, and Reddy 2024) . The field has responded mainly by measuring unfaithfulness more carefully, by using counterfactual conflicts, or by optimizing explanations toward faithfulness proxies; all routes are post hoc (Cesarini et al. 2024) and leave the central guarantee missing.  \nThis paper pursues a constructive alternative for one task family: the prediction pathway itself serves as the explanation. We operationalize Natural Semantic Metalanguage (NSM), a linguistic-semantics program that defines word meanings through a closed set of semantic primes (Section 2), as a two-segment definitional pathway yˆ = g (fθ (x)) . A parser  \nPreprint. Copyright with authors.  \nfrustration  \nX feels something  \nsometimes a person thinks something like this: I want to do something  \nI can’t do this  \nbecause of this, this person feels something bad X feels like this  \nFigure 1: A prototypical NSM explication that defines frustration entirely in semantic primes (Wierzbicka 1999) .  \nfθ maps text to an explication in a twelve-slot schema over the prime vocabulary, and a transparent mapper g, derived from the published definitions, computes the label from the explication and nothing else. The second segment is fixed by semantic theory; the first segment, which targets a cognitively and sensorily more primitive representation, is the only part that must be learned (Figure 2) .  \nThree developments make the design feasible now. LLMs can generate explications that respect the prime vocabulary (Baartmans et al. 2025); constrained decoding enforces the closed vocabulary so legality is a guaranteed decoder property; mature natural language inference (NLI) models make per-proposition verification practical at corpus scale; and appraisal-annotated corpora supply event descriptions with the cognitive granularity the schema requires (Troiano, Oberländer, and Klinger 2023) .  \nThe paper makes three contributions. First, we introduce the Emotion Expl","cbCaia58kRjtAtru","https://ap.wps.com/l/cbCaia58kRjtAtru","pdf",325412,1,12,"English","en",105,"# Introduction\n# Background and Notation\n## Natural Semantic Metalanguage\n## Emotion Explication Schema (EES)\n# Methodology and Experiments\n## Parser learning and entailment verification\n## Dataset: EmoExpl-1200\n# Contributions and Rule Revision Protocol","[{\"question\":\"How does the method ensure explanation faithfulness for emotion classification?\",\"answer\":\"The label is computed from a Natural Semantic Metalanguage explication using a fixed decision list, so the explication-to-label step is causally faithful by construction. The learned component is limited to mapping text into the explication.\"},{\"question\":\"What are the two segments in the proposed prediction pathway?\",\"answer\":\"The system uses a learnable parser that maps input text to a twelve-slot NSM explication, then applies a transparent, fixed mapper derived from published semantic definitions to compute the emotion label.\"},{\"question\":\"What is EmoExpl-1200 and what does it provide?\",\"answer\":\"EmoExpl-1200 is an instance-level explication-annotated corpus built from crowd-sourced event descriptions. It includes per-line verification metadata and releases the full rule set used by the fixed mapper.\"}]",1784188568,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"faithful-by-definition-emotion-analysis-via-natural-semantic-metalanguage-explications","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/faithful-by-definition-emotion-analysis-via-natural-semantic-metalanguage-explications/83516/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How does the method ensure explanation faithfulness for emotion classification?","Question",{"text":74,"@type":75},"The label is computed from a Natural Semantic Metalanguage explication using a fixed decision list, so the explication-to-label step is causally faithful by construction. The learned component is limited to mapping text into the explication.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What are the two segments in the proposed prediction pathway?",{"text":79,"@type":75},"The system uses a learnable parser that maps input text to a twelve-slot NSM explication, then applies a transparent, fixed mapper derived from published semantic definitions to compute the emotion label.",{"name":81,"@type":72,"acceptedAnswer":82},"What is EmoExpl-1200 and what does it provide?",{"text":83,"@type":75},"EmoExpl-1200 is an instance-level explication-annotated corpus built from crowd-sourced event descriptions. It includes per-line verification metadata and releases the full rule set used by the fixed mapper.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":120},"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]