Optimized Deep Neural Architectures for Domain-Adaptive and Noise Resilient Sentiment Analysis in Social Media

Lekhpal Singh , Dr. Nidhi Mishra

Optimized Deep Neural Architectures for Domain-Adaptive and Noise Resilient Sentiment Analysis in Social Media

Authors

Lekhpal Singh , Dr. Nidhi Mishra

Keywords:

Sentiment Analysis; Deep Neural Networks; BERT; XLNet; BiLSTM Optimization; Domain Adaptation; Multilingual Social Media

Abstract

Background: With the exponential rise of social media platforms such as Twitter, Facebook, andYouTube, sentiment analysis has become a crucial tool for understanding public opinion, consumerbehaviour, and social trends. However, the diversity of languages, informal expressions, and noisy textual data pose significant challenges for accurate sentiment detection

References

1. Park, J., Lee, H.J. and Cho, S. (2021) Automatic construction of context-aware sentiment lexicon in the financial domain using direction-dependent words. arXiv preprint arXiv:2106.05723.

Downloads

Published

2024-04-20

How to Cite

Lekhpal Singh , Dr. Nidhi Mishra. (2024). Optimized Deep Neural Architectures for Domain-Adaptive and Noise Resilient Sentiment Analysis in Social Media . Journal of Computational Analysis and Applications (JoCAAA), 33(1A), 910–927. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/5671