Project Overview#

Computational scientists across disciplines have reported accounts failed attempts to reproduce scientific outcomes even when replication packages were available, which limits advancing research and threatens the validity of existing works. This has led to the reproducibility crisis. Social networks are essential for today’s world, and Twitter has grown as a medium for informal scientific discussions.

This project aims to analyse if reproducibility and open-science is discussed in Twitter, how it is discussed, and which sentiments it generates among those involved in the discussions.

This tutorial is a great example of what to expect (but you’ll work with far more complex data).

Requirements#

  • Python programming, including scikit-learn, numpy, pandas, Jupyter notebooks.
  • Basics of NLP in Python, including nltk, textblob, and LDA.
  • Basics of plotting (seaborn, ggplot, etc).

Info#

bars search times arrow-up