Enhancing Depressive Post Detection in Bangla: A Comparative Study of TF-IDF, BERT and FastText Embeddings

TL;DR

This paper compares TF-IDF, BERT, and FastText embeddings within a CNN-BiLSTM model to detect depressive posts in Bangla social media data, demonstrating BERT's superior performance with an 84% F1-score.

Contribution

It introduces a novel approach combining advanced NLP techniques and deep learning for depressive post detection in Bangla, with a comprehensive comparison of embedding methods.

Findings

BERT embedding outperforms TF-IDF and FastText in detection accuracy.

Oversampling improves model performance on imbalanced data.

The proposed method achieves an 84% F1-score, surpassing existing techniques.

Abstract

Due to massive adoption of social media, detection of users' depression through social media analytics bears significant importance, particularly for underrepresented languages, such as Bangla. This study introduces a well-grounded approach to identify depressive social media posts in Bangla, by employing advanced natural language processing techniques. The dataset used in this work, annotated by domain experts, includes both depressive and non-depressive posts, ensuring high-quality data for model training and evaluation. To address the prevalent issue of class imbalance, we utilised random oversampling for the minority class, thereby enhancing the model's ability to accurately detect depressive posts. We explored various numerical representation techniques, including Term Frequency-Inverse Document Frequency (TF-IDF), Bidirectional Encoder Representations from Transformers (BERT) embedding and FastText embedding, by integrating them with a deep learning-based Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) model. The results obtained through extensive experimentation, indicate that the BERT approach performed better the others, achieving a F1-score of 84%. This indicates that BERT, in combination with the CNN-BiLSTM architecture, effectively recognises the nuances of Bangla texts relevant to depressive contents. Comparative analysis with the existing state-of-the-art methods demonstrates that our approach with BERT embedding performs better than others in terms of evaluation metrics and the reliability of dataset annotations. Our research significantly contribution to the development of reliable tools for detecting depressive posts in the Bangla language. By highlighting the efficacy of different embedding techniques and deep learning models, this study paves the way for improved mental health monitoring through social media platforms.