Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : JOIV : International Journal on Informatics Visualization

Few-Shot-BERT-RNN Narrative Structure Analysis for Andersen's Stories Daniati, Erna; Wibawa, Aji Prasetya; Irianto, Wahyu Sakti Gunawan; Hernandez, Leonel
JOIV : International Journal on Informatics Visualization Vol 9, No 4 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.4.3932

Abstract

Event Extraction (EE) is a pivotal task for NLP, where important events in the narrative text need to be detected and recognized. We present an alternative method for extracting events from Hans Christian Andersen's fairy tales, utilizing Few-Shot Learning with BERT (Bidirectional Encoder Representations from Transformers) and RNN (Recurrent Neural Network) in this paper. We selected Andersen's fairy tales because they are characterized by rich narratives and symbolic language, which also often prevents automatic event extraction. To reduce reliance on labeled samples, we utilize the Few-Shot Learning method, which enables the model to learn from a small number of labeled event examples trivially. The BERT model is used to generate deep representations by modeling the context between words and sentences. RNN is essential to capture the sequence of events in the story, which determines the structure of the narrative. The findings demonstrate that the proposed framework significantly improves event extraction, with high values of evaluation metrics such as in accuracy, precision, recall, and F1-score. The proposed method is also effective in extracting non-explicit events while keeping the narrative context. Despite the challenges posed by metaphorical language and subjective events, this work demonstrates that Few-Shot Learning, BERT, and RNNs offer a promising solution to the task of event extraction from complex narratives.
Attention-Enhanced Convolutional Neural Network for Context Extraction in Andersen's Fairy Tales Daniati, Erna; Wibawa, Aji Prasetya; Irianto, Wahyu Sakti Gunawan; Nafalski, Andrew
JOIV : International Journal on Informatics Visualization Vol 9, No 6 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.6.4056

Abstract

Event extraction in classic literature and fairy tales remains highly challenging due to their non-linear plot structures, archaic linguistic expressions, and intricate character interactions, while advances in modern NLP still show limitations in capturing subtle narrative cues in historical texts. This study aims to address these gaps by developing an event extraction model tailored to the narrative characteristics of Hans Christian Andersen’s fairy tales. We propose a BERT-enhanced Context-aware Convolutional Neural Network (CNN) that integrates an attention mechanism to overcome the limited contextual range of traditional CNNs. The model leverages BERT’s contextual embeddings enriched with an attention layer to detect event triggers, character relations, and narrative transitions across nonlinear storylines. A hybrid dataset was constructed through system-generated annotations refined via manual verification and combined with AN/an cartoon-based representations for model training and final testing. Experimental results show that the proposed model surpasses both the CNN-only baseline and a rule-based approach, achieving precision of 0.92, recall of 0.89, F1-score of 0.90, and accuracy of 0.91, outperforming the CNN baseline (0.85/0.82/0.83/0.84) and rule-based system (0.78/0.75/0.76/0.77). These findings highlight the effectiveness of context-aware representations for processing literary narratives and demonstrate interdisciplinary relevance to digital humanities and AI-based storytelling, with future extensions envisioned for multilingual settings and genre-specific adaptations.