Transfer Learning for Human & AI

Since March 2020, companies nationwide have started work from home (WFH) dueto the rapid increase of COVID-19 confirmed cases in an attempt to help prevent the coronavirus from spreading and rescue the economy from the pandemic . We perform an ordinary least square regression to investigate therelationship between the sentiment about WFH and user characteristics including gender, age, ethnicity, median household income, and population density . We use latent Dirichlet allocation to extracttopics and discover how tweet contents relate to people’s attitude . Thesefindings provide evidence that sentiment about . WFH varies across usercharacteristics. Furthermore, content analysis sheds light on the nuanceddifferences of sentiment and reveal disparities relate to WFH . Furthermore, Content Analysis sheds light

Author(s) : Ziyu Xiong, Pin Li, Hanjia Lyu, Jiebo Luo

Links : PDF - Abstract

Code :

https://github.com/nhynes/abc

Keywords : wfh - sentiment - pandemic - relate - content -

• Mathematics for Machine Learning by Marc Peter Deisenroth, A. Aldo Faisal and Cheng Soon Ong
• Khan Academy Matrices
• Kaggle Learning
• Practical Deep Learning for Coders – Part 1
• fast.ai Machine Learning
• Complete Python Bootcamp
• Learning How to Learn on Coursera
• The Hundred-Page Machine Learning Book