Machine learning and meta-ethnography: Seven steps to synthesising 578 evaluations into four themes

This paper documents a case study of using machine learning and meta-ethnography techniques to synthesise and draw lessons from 578 evaluations. This paper is part of the BetterEvaluation Innovation Working Paper series.

About this resource

What would you do if you were asked to rapidly identify practical insights on a development issue based on a potentially vast number of evaluation documents?

An Independent Evaluation Group (IEG) team faced with reviewing 578 project evaluations combined evaluation and data science techniques to rapidly analyse and report on four themes related to improving interventions in contexts of migration. 

This paper presents a worked example of how the team undertook this task.

Authors and their affiliation

This paper was written by Stephen Porter, Harsh Anuj, Yingjia Liu, Kristin Strohecker (The Independent Evaluation Group, The World Bank Group).


Porter, S., Anuj, H., Liu, Y., Strohecker, K. (2021). ‘Machine learning and meta-ethnography: Seven steps to synthesising 578 evaluations into four themes’. BetterEvaluation Innovation Working Paper series. 

No votes yet
Rate this Resource:
A special thanks to this page's contributors
Resource Suggested By
Evaluation Strategy Advisor, World Bank.
Washington DC, United States of America.


There are currently no comments. Be the first to comment on this page!

Add new comment

Login Login and comment as BetterEvaluation member or simply fill out the fields below.