Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mohammad Yeghaneh Abkenar, Weixing Wang, Manfred Stede, Davide Picca, Mark A. Finlayson, Panagiotis Ioannidis

TL;DR

This work works on five datasets from diverse domains encompassing a range of controversial topics and presents an approach for expanding the Bias-Corrected NRC Emotion Lexicon using DistilBERT embeddings, which are fed into a Neural Argumentative Stance Classification model.

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.

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

TL;DR

This work works on five datasets from diverse domains encompassing a range of controversial topics and presents an approach for expanding the Bias-Corrected NRC Emotion Lexicon using DistilBERT embeddings, which are fed into a Neural Argumentative Stance Classification model.

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.
Paper Structure (26 sections, 2 equations, 9 figures, 2 tables)

This paper contains 26 sections, 2 equations, 9 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Contributions
  3. Background & Related work
  4. Background
  5. Argumentation Mining
  6. Emotion Lexicons
  7. Stance Classification
  8. Related Work
  9. Development of eNRC: An Expansion of NRC
  10. Clustering and Embedding Distribution
  11. Trimodal Similarity Patterns
  12. Dimensionality Reduction and Clustering
  13. Cluster-based Normalization
  14. Threshold-based Lexicon Expansion
  15. Threshold Selection and Category Separation
  16. ...and 11 more sections

Figures (9)

  • Figure 1: An example with five segments from the Argumentative Microtext corpus (Part 1), showing stance labels (For or Against) toward a controversial target topic.
  • Figure 2: Trimodal similarity distributions across emotion categories in the original NRC lexicon.
  • Figure 3: Three-cluster structure of NRC word embeddings in PCA-reduced space
  • Figure 4: Aligned similarity distributions after cluster-based normalization.
  • Figure 5: Analysis of lexicon expansion under varying similarity thresholds.
  • ...and 4 more figures