About us

Anthropocene Principles






Overview – The Social Media Data Processing Pipeline

  May 1, 2016
  The SAGE Handbook of Social Media Research Methods
h  Book Chapter
  data cleaning, data modelling, data transformation, research methods, social media, Twitter

Publication Authors

Post Author


This chapter provides a broad introduction to the modelling, cleaning, and transformation techniques that must be applied to social media data before it can be imported into storage and analysis software. While each of the above topics in itself encompasses a wide range of issues, they are also inextricably related in that each relies in some way upon the others. In order to discuss these processes as a group, we employ the term data processing to describe the preparatory phase between data collection and data analysis. The sections that follow demonstrate how data processing can be broken down into a pipeline of three phases: modelling, cleaning and transformation.

<< Go back to publications