Discussing the planning and testing phase of data analysis tools upgrades.

This is the findings from running three analysis on a same data set - one manual, one rule-based and one machine-learning based to summarize unstructured research data.

I discuss an example of a project where I used semantic analysis to humanize data during research analysis.

We discuss three challenges in reconciling structured and unstructured data in research analysis.

We discuss the process of building custom dictionaries for research and three limitations of commercial dictionaries.

What might be an interesting construct for automating the processing of some of your participant research? We look at semantic automation.

What should we think about when paying for participants? How can payment skew the research work?

This is a ten minutes segment from a one-hour interview with guest Charlie Beckett, past senior producer and programme editor at BBC News and Current affairs, current founding director of Polis, the think-tank for research and debate around international journalism and society (London School of Economics). You can find the original podcast episode here: Different by Design.

UPDATED - This is Part of the Data Stories Series

Written by Corina Paraschiv.

A special thank you to Kenneth D. Bailey’s work on typologies and taxonomies, for having inspired this Data Story.

A reflection on the value of self-referential coding in informing your research - when handled cautiously.