Qihan Wang

Master's

Data Science

University of Southern California Information Sciences Institute

- Dec 2023 - Now - Developed a violence classification model and investigated violence radicalization in online communities using NLP by - Python, resulting in increased user retention, reduced content moderation costs, and improved regulatory compliance - Fine-tuned deep learning-based NLP models (such as BERT and Roberta) for violence detection using transformer - Utilized embeddings and recommendations - Boosted 20% accuracy by bootstrapping, over-sampling methods for data imbalance problems