Temporaily Available Slides for Recent Talks
Talk, Anywhere, Anywhere
NCCU
Selected talks and presentations
Detection of Content Incivility and its Causal Effects using Machine Learning
Talk, SICSS 2022@NUS, Singapore
Using political incivility as an example, this talk presents a dictionary-based classification method, by leveraging word embeddings, could outperform supervised machine learning methods to detect uncivil content in online comments. Furthermore, this talk shows that machine learning models could help identify the causal effects of political incivility on engagement and contagions, by controlling for textual confounders.
The Structures and Consequences of Online Political Discussion
Talk, CSSLab@CUHK, Hong Kong
This talk summarizes a series of computational studies using large-scale social media data to examine the structures and consequences of political discussions online.
Tutorial on Weird Statistics Questions
Tutorial, CUHK, Hong Kong
This is a tutorial for the PhD students in the school of journalism and communication at CUHK.
Information Diffusion in Communication Networks
Talk, SICSS 2021@Hong Kong, HKUST, Hong Kong
This talk summarized the popular empirical models including user-centric models, cascade-centric models, and a newly developed model by combining the two.