Hindi/Bengali Sentiment Analysis Using Transfer Learning and Joint Dual Input Learning with Self Attention

TL;DR

This paper presents a transfer learning and joint dual input learning approach with self-attention for sentiment analysis and hate speech detection in Hindi and Bengali, leveraging deep neural networks and shared embeddings.

Contribution

It introduces a novel joint dual input learning framework with self-attention for multilingual sentiment analysis and hate speech detection in Hindi and Bengali.

Findings

Transfer learning improves Bengali sentiment classification accuracy.

Joint dual input learning enhances cross-language sentiment detection.

Self-attention mechanism improves model interpretability and performance.

Abstract

Sentiment Analysis typically refers to using natural language processing, text analysis and computational linguistics to extract affect and emotion based information from text data. Our work explores how we can effectively use deep neural networks in transfer learning and joint dual input learning settings to effectively classify sentiments and detect hate speech in Hindi and Bengali data. We start by training Word2Vec word embeddings for Hindi \textbf{HASOC dataset} and Bengali hate speech and then train LSTM and subsequently, employ parameter sharing based transfer learning to Bengali sentiment classifiers by reusing and fine-tuning the trained weights of Hindi classifiers with both classifier being used as baseline in our study. Finally, we use BiLSTM with self attention in joint dual input learning setting where we train a single neural network on Hindi and Bengali dataset simultaneously using their respective embeddings.