# QRMine: A python package for triangulation in Grounded Theory

**Authors:** Bell Raj Eapen, Norm Archer, Kamran Sartipi  
**arXiv:** [2003.13519](https://arxiv.org/abs/2003.13519)  
**Date:** 2020-03-30  
**Summary page:** https://www.summarizepaper.com/en/paper/2003.13519v1/

## Key points

- QRMine is a python package that supports Grounded Theory (GT) in qualitative research
- GT is a method for building theory based on data, using both textual and numeric information
- The process involves various stages of coding or tagging data for sense-making, such as open coding and selective coding
- Machine Learning (ML) techniques, including natural language processing (NLP), can assist researchers in this process by automating some aspects of the coding process
- Triangulation is the process of combining various types of data to strengthen findings and conclusions
- ML can facilitate deriving insights from numerical data that corroborate findings from textual interview transcripts
- The QRMine package encapsulates various ML and NLP libraries to support coding and triangulation in GT
- Researchers can install QRMine from the Python Package Index (PyPI) with minimal effort, enabling them to use these methods on their own data
- The package is open-source, allowing for contributions to its development
- Computational triangulation will make GT relevant in the realm of big data where traditional manual analysis methods may be insufficient due to the sheer volume of information available.
- By leveraging ML techniques through packages like QRMine, researchers can more efficiently analyze large datasets while maintaining the rigor and validity associated with GT methodology.
- Overall, QRMine represents a valuable tool for qualitative researchers seeking to incorporate ML techniques into their work while maintaining a grounded approach to theory-building based on empirical evidence.

## Summary

The QRMine python package has been developed to support the use of Grounded Theory (GT) in qualitative research. GT is a method for building theory based on data, using both textual and numeric information. The process involves various stages of coding or tagging data for sense-making, such as open coding and selective coding. Machine Learning (ML) techniques, including natural language processing (NLP), can assist researchers in this process by automating some aspects of the coding process. Triangulation is the process of combining various types of data to strengthen findings and conclusions. ML can facilitate deriving insights from numerical data that corroborate findings from textual interview transcripts. The QRMine package encapsulates various ML and NLP libraries to support coding and triangulation in GT. Researchers can install QRMine from the Python Package Index (PyPI) with minimal effort, enabling them to use these methods on their own data. The package is open-source, allowing for contributions to its development. The authors believe that computational triangulation will make GT relevant in the realm of big data, where traditional manual analysis methods may be insufficient due to the sheer volume of information available. By leveraging ML techniques through packages like QRMine, researchers can more efficiently analyze large datasets while maintaining the rigor and validity associated with GT methodology. Overall, QRMine represents a valuable tool for qualitative researchers seeking to incorporate ML techniques into their work while maintaining a grounded approach to theory-building based on empirical evidence. This package provides an effective way for researchers to utilize modern computational methods while still adhering to rigorous qualitative research standards.