What question did this study set out to answer?

The aim is to develop a sentiment classification system utilizing deep learning models while enhancing explainability.

March 27, 2026Open Access

Sentiment Analysis of Social Media Using Deep Learning and Explainable AI

HGHarsh GuptaBarkatullah University JCJyoti ChauhanBarkatullah University

Key Points

The aim is to develop a sentiment classification system utilizing deep learning models while enhancing explainability.
Utilized models including VADER, LSTM, BERT, and RoBERTa for sentiment analysis.
Fine-tuned the RoBERTa model to improve accuracy.
Integrated Explainable AI using DeepSeek for interpretability.
Evaluated model performance based on accuracy metrics.
The proposed model achieved an accuracy of approximately 95-96%.
Outperformed baseline models in sentiment classification.
DeepSeek integration provided human-readable explanations for model predictions.

Abstract

Sentiment analysis has become a fundamental task in Natural Language Processing (NLP), especially with the exponential growth of social media data. This paper presents a comprehensive approach for sentiment classification using multiple models including VADER, LSTM, BERT, and RoBERTa. The proposed system focuses on fine-tuning RoBERTa to achieve high accuracy and integrates Explainable Artificial Intelligence (XAI) using DeepSeek to enhance interpretability. Experimental results show that the proposed model achieves an accuracy of approximately 95–96%, outperforming baseline models. The integration of DeepSeek provides human-readable explanations, improving model transparency and usability.

Ask AI

Helpful

Bookmark

View Full Paper