Multilabel Hate Speech Classification in Indonesian Political Discourse on X using Combined Deep Learning Models with Considering Sentence Length
Open Access
- 5 February 2025
- journal article
- Published by Faculty of Computer Science, Universitas Indonesia in Jurnal Ilmu Komputer dan Informasi
- Vol. 18 (1) , 113-125
Abstract
Hate speech, as public expression of hatred or offensive discourse targeting race, religion, gender, or sexual orientation, is widespread on social media. This study assesses BERT-based models for multi-label hate speech detection, emphasizing how text length impacts model performance. Models tested include BERT, BERT-CNN, BERT-LSTM, BERT-BiLSTM, and BERT with two LSTM layers. Overall, BERT-BiLSTM achieved the highest (82.00%) and best performance on longer texts (83.20% ) with high and , highlighting its ability to capture nuanced context. BERT-CNN excelled in shorter texts, achieving the highest (79.80%) and an of 79.10%, indicating its effectiveness in extracting features in brief content. BERT-LSTM showed balanced and across text lengths, while BERT-BiLSTM, although high in r, had slightly lower on short texts due to its reliance on broader context. These results highlight the importance of model selection based on text characteristics: BERT-BiLSTM is ideal for nuanced analysis in longer texts, while BERT-CNN better captures key features in shorter content.Keywords
This publication has 23 references indexed in Scilit:
- Deep Learning Model for Identification and Classification of Web based Toxic Comments2023
- A systematic review of hate speech automatic detection using natural language processingNeurocomputing, 2023
- BERT-based Ensemble Approaches for Hate Speech Detection2022
- Twitter’s Hate Speech Multi-label Classification Using Bidirectional Long Short-term Memory (BiLSTM) Method2021
- Multi-label classification with weighted classifier selection and stacked ensembleInformation Sciences, 2021
- A Short Text Classification Method Based on N ‐Gram and CNNChinese Journal of Electronics, 2020
- Emotion Classification on Indonesian Twitter Dataset2018
- A Dataset and Preliminaries Study for Abusive Language Detection in Indonesian Social MediaProcedia Computer Science, 2018
- Hate speech detection in the Indonesian language: A dataset and preliminary study2017
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997