PurposeThe study primarily aims to examine an emerging fashion technology, direct-to-garment (DTG) printing, using data mining-driven social network analysis (SNA). Simultaneously, the study also demonstrates application of a group novel computational technique to capture, analyze and visually depict data for strategic insight into the fashion industry.Design/methodology/approachA total of 5,060 tweets related to DTG were captured using Crimson Hexagon. Python and Gephi were applied to convert, calculate and visualize the yearly networks for 2016–2019. Based on graph theory, degree centrality and betweenness centrality indices guide interpretation of the outcome networks.FindingsThe findings reveal insights into DTG printing technology networks through identification of interrelated indicators (i.e. nodes, edges and communities) over time. Deeper interpretation of the dominant indicators and the unique changes within each of the DTG communities were investigated and discussed.Practical implicationsThree SNA models suggest directions including the dominant apparel categories for DTG application, competing alternatives for apparel decorating approaches to DTG and growing market niches for DTG. Interpretation of the yearly networks suggests evolution of this domain over the investigation period.Originality/valueThe social media based, data mining-driven SNA method provides a novel path and a powerful technique for scholars and practitioners to investigate information among complex, abstract or novel topics such as DTG. Context specific findings provide initial insight into the evolving competitive structures driving DTG in the fashion market.