Improving Neural Argumentative Stance Classification in Controversial Topics with Emotion-Lexicon Features

2026-02-26

AI Summary

This study addresses the limited integration of fine-grained sentiment information and poor generalization in existing stance classification approaches for contentious argumentative texts. To overcome these limitations, the authors propose the eNRC sentiment lexicon, which extends the Bias-Corrected NRC lexicon by enriching it with contextualized embeddings derived from DistilBERT, thereby capturing nuanced sentiment cues. These contextualized sentiment features are then incorporated into a neural stance classification model. The approach demonstrates, for the first time, the effectiveness of lexicon-enhanced sentiment representation for stance classification across multiple controversial topics and domains. Evaluated on five benchmark datasets, the method achieves up to a 6.2 percentage point improvement in F1 score over baselines using the original NRC lexicon and outperforms large language model–based alternatives. All resources are publicly released to support further research.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Argumentation mining comprises several subtasks, among which stance classification focuses on identifying the standpoint expressed in an argumentative text toward a specific target topic. While arguments-especially about controversial topics-often appeal to emotions, most prior work has not systematically incorporated explicit, fine-grained emotion analysis to improve performance on this task. In particular, prior research on stance classification has predominantly utilized non-argumentative texts and has been restricted to specific domains or topics, limiting generalizability. We work on five datasets from diverse domains encompassing a range of controversial topics and present an approach for expanding the Bias-Corrected NRC Emotion Lexicon using DistilBERT embeddings, which we feed into a Neural Argumentative Stance Classification model. Our method systematically expands the emotion lexicon through contextualized embeddings to identify emotionally charged terms not previously captured in the lexicon. Our expanded NRC lexicon (eNRC) improves over the baseline across all five datasets (up to +6.2 percentage points in F1 score), outperforms the original NRC on four datasets (up to +3.0), and surpasses the LLM-based approach on nearly all corpora. We provide all resources-including eNRC, the adapted corpora, and model architecture-to enable other researchers to build upon our work.

Problem

• stance classification
• argumentation mining
• emotion lexicon
• controversial topics
• neural classification

Innovation

• emotion-lexicon expansion
• stance classification
• contextualized embeddings
• argumentation mining
• controversial topics