This project aims to enhance the detection and curb the spread of hate speech using machine learning pipelines, creating a safer online community.
This project aims to understand emerging Science and Technology (S&T) areas and their regional and national impacts on society and the economy.
This paper investigates the ability of Large Language Models (LLMs) to detect implicit hate speech and assess their confidence in responses.
This paper explores the use of multimodal methodologies for stock volatility prediction, addressing overfitting and gender bias through adversarial training to enhance fairness and robustness.
This paper introduced a novel deep learning model for long-term citation forecasting in scientific patents and publications.