Online Conversation
Online conversation analysis focuses on understanding the dynamics of human interaction in digital spaces, aiming to improve online communication and mitigate harmful behaviors. Current research employs machine learning models, including BERT and LLMs, to classify conversation types, detect toxicity and hate speech (both explicit and implicit), and predict conversation branching and derailment, often leveraging graph convolutional networks to capture contextual information. These advancements have significant implications for social science research, enabling better understanding of online behavior and informing the development of more ethical and effective online platforms and AI systems for moderation and support.
Papers
OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA)
Fujian Jia, Xin Liu, Lixi Deng, Jiwen Gu, Chunchao Pu, Tunan Bai, Mengjiang Huang, Yuanzhi Lu, Kang Liu
CFRet-DVQA: Coarse-to-Fine Retrieval and Efficient Tuning for Document Visual Question Answering
Jinxu Zhang, Yongqi Yu, Yu Zhang