Abstract
The study illustrates an application of evidence data for performing Total Interpretive Structural Modeling (TISM). TISM is widely used to analyze the critical success factors or inhibitors and their interlinkages. This study uses learning from evidence data, specifically social media analytics, to identify the relationship between the elements. Thus, it leads to the advancement of the TISM-P methodology with evidence-based TISM (TISM-E). This study uses Twitter as a source of evidence data. Further, 2,60,297 tweets were used to illustrate the process of TISM-E. The paper demonstrates the application of TISM-E for the success of the COVID-19 vaccination drive. The pandemic effects are long-term; therefore, the hierarchical model developed shows a sustainable approach for vaccinating maximum population. Further, the framework developed will ensure the distribution efficacy of vaccines. In addition, it will aid practitioners in developing future vaccination policies. The enhanced model provides evidence for polarity (positive/negative) of relationships and can help to build propositions for theory development. The study contributes to healthcare, modeling research, and graph-theoretic literature.