The big data analytical approach is used in this paper to analyze how leadership in corporate culture contributes to engaging the employees. Organizations are increasingly becoming aware of the magnitude of cultural alignment in driving greater performance and retention of their talent throughout their stay in the organisation, therefore, it is important to have an idea of the slight interaction between the behaviour of leadership and the feeling of the employees. The research leverages sentiment analysis via natural language processing (NLP) to process and analyze a large volume of employee-generated textual data collected from company feedback forms, review platforms such as Glassdoor, and publicly available social media accounts including LinkedIn and Twitter. Support Vector Machine (SVM) is a supervised machine learning algorithm that is applied to categorise the levels of engagement with respect to the textual features/attributes that have been extrapolated. The model has been cognitive-conditioned to recognize the cues of engagement since it has learned the lingual patterns, due to cultural traits such as openness, collaboration, innovation and trust. Organizations with a transformational leadership that had been a central part of an inclusive and transparent culture have been found to have significantly higher ratings with regard to employee engagement. The classification accuracy was sufficiently high to confirm that the model effectively distinguishes between high and low employee engagement instances. The current study provides an empirical validation of the fact that the combination of the big-data practices and cultural insights enables the organization to diagnose and enhance the engagement strategy.