Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Classifying Agency Expressions in Historic Human Rights Hearings Using Hybrid BiLSTM-Transformer Model with Attention

Domain:

natural language processingpeace and security

Record type:

paper
Creator:
Li,
Publisher:
Sta
Host:avatar
This paper uses a hybrid bidirectional long short-term memory (BiLSTM) transformer model with syntactic, polarity and context feature extractions to classify expressions of agency from witness hearings held during the 1996-97 South Africa Truth and Reconciliation Commission (SA TRC). During hearings, witnesses recalled the details and impact of apartheid-era human rights violations that they experienced. Training on a dataset of 2,286 labeled witness expressions with an 80/20 test/validation split stratified by label class, the hybrid model achieves a 0.90 validation F1 score across all-label prediction (agency and non-agency), and 0.50-0.60 validation accuracy scores on agency-relevant (low, mixed, high) labels. The model slightly outperforms a baseline finetuned RoBERTa model, especially across agency-relevant labels. Word attention weights are further visualized to assess high-importance words during the hybrid BiLSTM model classification process. The hybrid BiLSTM model is then deployed on 125 unseen hearings transcripts, representing 5,346 witness expressions. These expressions are qualitatively assessed to identify key themes concerning education and livelihoods recovery. Overall, the paper demonstrates the broader utility of modeling agency expression in human rights research.

Visit

doi.orgpurl.stanford.edu

Tasks

text classification

Tags

agencyhybrid biLSTM transformer modelhuman developmenttransitional justicesentiment classificationnatural language processingSouth Africawitness hearingsattention visualization

Licenses

Creative Commons Attribution Non Commercial 4.0 Internationalhttps://creativecommons.org/licenses/by-nc/4.0/legalcode

Similar

ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion RecognitionA Lightweight Landmark-Based Model for Bahasa Lip-Reading Using Attention-BiLSTMDirect English-to-Yoruba speech Translation model using Transformer with Augmented Attention MechanismMode Decomposition Bi-Directional Long Short-Term Memory (BiLSTM) Attention Mechanism and Transformer (AMT) Model for Ozone (O3) Prediction in Johannesburg, South AfricaMultimodal based Amharic fake news detection using CNN and attention-based BiLSTMRHATNet: residual and hybrid attention-based transformer network for hyperspectral image classification

ArabEmoNet: A Lightweight Hybrid 2D CNN-BiLSTM Model with Attention for Robust Arabic Speech Emotion Recognition

Speech emotion recognition is vital for human-computer interaction, particularly for low-resource la

A Lightweight Landmark-Based Model for Bahasa Lip-Reading Using Attention-BiLSTM

Background: Most lip-reading studies primarily utilize image-based representations of lip movements,

Direct English-to-Yoruba speech Translation model using Transformer with Augmented Attention Mechanism

Mode Decomposition Bi-Directional Long Short-Term Memory (BiLSTM) Attention Mechanism and Transformer (AMT) Model for Ozone (O3) Prediction in Johannesburg, South Africa

This paper presents a model that combines mode decomposition approaches with a bi-directional long s

Multimodal based Amharic fake news detection using CNN and attention-based BiLSTM

RHATNet: residual and hybrid attention-based transformer network for hyperspectral image classification

Abstract Hyperspectral images comprise many continuous bands in narrow wavelengt