When most people think of Big Data, they think of vast amounts of numbers and statistics but while quantitative data informs research and provides meaningful analysis, it is a mere portion of Big Data’s potential.
New research published in the Journal of Supply Chain Management by Tima Bansal, Jury Gualandris, and Nahyun Kim from the Ivey Business School identifies the opportunity of incorporating quantitative Big Data in supply chain theory and research.
Qualitative Big Data offers rich, contextualized information about organizations and their complex connections. Types of qualitative Big Data can include text, video, audio, images, networks, and graphics. Despite its richness, finding ways to analyze and interpret quantitative Big Data can be overwhelming. To make sense of it, the authors propose the use of topic modeling.
Topic modeling is a method that identifies themes, relationships among topics, and changing topical patterns in qualitative textual data. It helps synthesize qualitative data in a way that can reveal a hidden distribution of topics, something that can be missed by simply reading the text. Topic modeling can also mitigate some of the systematic biases that may creep in with traditional research techniques that rely heavily on interpretation of text by researchers.
The use of qualitative Big Data and topic modeling is not yet widespread but a few instances of its application in organizational theory may help inform future applications in supply chain theory. For example, one organizational theory study in 2019 looked at radical environmental groups and used qualitative Big Data and topic modeling to identify the tactics activists deployed to mobilize social change. Instead of looking at environmental groups, supply chain researchers could apply the same logic to understand the connections between supply chain members and why some supply chains succeed while others do not.
The possibilities for using qualitative Big Data in supply chain research are plentiful but currently unexplored. One important potential opportunity is exploring the emergence of the circular economy within complex supply systems. For example, Big Data techniques may be able to capture changes within the agrifood system (e.g. a retailer that recirculate food waste and food packaging waste for alternative uses in other industries, or a farmer upcycling crop waste for bioplastics) that could indicate wider systems change towards circularity.
Read the full article here.