[We’re pleased to welcome authors Dr. Stefan Mol, Vladimer B. Kobayashi, Hannah A. Berkers, Gabor Kismihok, and Deanne N. Den Hartog of the University of Amsterdam. They recently published an article in Organizational Research Methods entitled “Text Mining in Organizational Research,” which is currently free to read for a limited time. Below, Dr. Mol recounts the events that led to the research and the significance it has to the field:]
Were there any specific external events that influence your decision to pursue this research?
One critical on-going event that lead us to pursue this research is the revolution and promise brought by the rise of big data to understand and enhance organizational processes. A large proportion of these data are comprised of texts that are generated every day at rates that imply that manual analysis of all of this data is no longer possible. The abundance of untapped text data suggest the existence of information with the promise of generating new knowledge that may be used to enhance both individual and organizational level outcomes.
Although, organizations already collect and store text data, many do not fully take advantage of the knowledge that can be gleaned from analyzing text. This may be due to a lack of expertise in conducting automatic text analysis or text mining. The mission of our work here is to empower organizational researchers by raising awareness of the possibilities afforded by text mining, helping them see how text mining might help them answer their research questions, and helping them to understand and use the text mining process and tools.
In what ways is your research innovative, and how do you think it will impact the field?
With this article we hope to contribute by facilitating dialogue between data scientists and organizational researchers about the opportunities afforded by text mining. As an example, we illustrate the role that text mining of vacancies might play in job analysis. Previous approaches to job analysis rely on time consuming collection and analysis of survey and observation based data the results of which soon become outdated due to the fast changing nature of jobs. Using text mining we demonstrate how one can take advantage of other data sources such as online job vacancies to understand the requirements and skill demands of different types of jobs. Our goal is to not only apply text mining to the field of job analysis but more importantly to inform organizational researchers about the wide-ranging uses text mining could have in organizational research. We hope that this will spark an increase in the use of text data and machine learning in organizational research.
What advice would you give to new scholars and incoming researchers in this particular field of study?
Existing text mining solutions are technique and tool-oriented because most techniques and Big Data tools are currently primarily shaped by technical fields, such as statistics and computer science, that put greater emphasis on the computational and technological aspects. However, applying these in the field of organizational research holds great promise. Organizational researchers bring with them a repertoire of organizational theories. These theories provide domain specific information and requirements that can influence the selection of techniques and analytical strategy, and the way to evaluate the success of the particular application. Our advice for incoming organizational researchers wanting to explore text mining is to draw on their own theoretical expertise and from there start selecting the appropriate techniques and approaches to text mining. Also, as with using other analytical tools, we do need to pay careful attention to rigor in evaluation and validation of text mining based results.