This article was developed based on the final project for a Social Media Analytics Course in the University of Hong Kong’s Master of Science in Business Analytics programme. The project is a result of a team effort and everybody worked hard to deliver all analysis that are going to be presented in this document. I would like to say thank you to all my team mates: August Hjorth, Maria Raquel Gomez Lopez, Martina de Luca, Xiaoyen Chen and Mawuli Adjei.
Introduction
This is the second article about South China Morning Post (SCMP) Social Network Analysis, and in this post it is going to be cover the step by step of our approach to the Topic Modeling, including data treatment, basic analysis and visualizations and the model development. Hope you find this article useful and please let me know your feedbacks!
Data
To develop our topic model, we used the Twitter data extracted using the Twitter API and rtweet package in R.
Rmarkdown is a super useful package in R! It enables the creation of reports in different formats like word, pdf, html, and others; all of them very neat and professional. I also like to use it in small projects, since it is possible to comment all steps in a very organized way, besides that you can even develop your own theme and the results are awesome!
I decided to make this tutorial to help those who are new to Rmarkdown, making it very straightforward to the features that I use most, so one can start using all the awesome options of this package that makes our lives much easier right away!
