Wenshu is specializing in data science and quantitative analysis, proficient in Python for data analysis, machine learning, and statistical modelling, as well as with experience in numerical analysis tools R, SPSS, MATLAB, data visualization techniques Qlik, Tableau, Origin Lab, and database SQL.
Her current work includes problem-solving and insights gaining through writing codes to implement statistical models and machine learning methods over the large corpus and varied datasets(i.e. clustering, regression, classification, MLP, ANOVA, etc.). The sentiment and narrative analysis is based on the NOW corpus from dozens of countries as well as COHA corpus with different genres (i.e. fiction, news, magazine, nonfiction) over hundreds of years. Through statistical analysis and models, different variables (such as risk index, cultural indicators, and demographic variables, etc.) are studied to explore the interaction and relationship among them. So far, she has worked on projects related to some topics about ageism, racism, healthcare, COVID, etc., where various methods and pathways based on machine learning and statistical analysis have been adopted and applied.