Abstract

We attempt to develop a research method that incorporates Machine Learning and Grounded Theory (GT) Research to analyze massive text data. Traditional GT is limited by human cognitive limitations wherein processing massive text data is nearly impossible to interpret and analyze. On the other hand, Machine Learning techniques are suitable for massive text analysis but lacks human judgement, intuition and interpretive capacities. By combining GT with Machine Learning, we attempt to extend traditional GT with Machine Learning so that researchers are able to analyze massive text to develop novel and interesting theories. However, ontologically and epistemologically GT and Machine Learning have different origins. We propose to incorporate Machine Learning with GT using ‘Emergence” as central to Grounded Theory research. We argue that Machine Learning Model serves in place of human computational nodes where teams of researchers are used in large scale GT research projects.

COinS
 

Integrating Machine Learning and Grounded Theory Research

We attempt to develop a research method that incorporates Machine Learning and Grounded Theory (GT) Research to analyze massive text data. Traditional GT is limited by human cognitive limitations wherein processing massive text data is nearly impossible to interpret and analyze. On the other hand, Machine Learning techniques are suitable for massive text analysis but lacks human judgement, intuition and interpretive capacities. By combining GT with Machine Learning, we attempt to extend traditional GT with Machine Learning so that researchers are able to analyze massive text to develop novel and interesting theories. However, ontologically and epistemologically GT and Machine Learning have different origins. We propose to incorporate Machine Learning with GT using ‘Emergence” as central to Grounded Theory research. We argue that Machine Learning Model serves in place of human computational nodes where teams of researchers are used in large scale GT research projects.