A text mining approach to strategy research

Text mining is valuable to analyze big quantities of textual data corpora without effort and with hight consistency. In particular, topic modelling with the latent Dirichlet allocation (LDA) algorithm enables retrieving the most recurrent topic from a textual database. On the other hand, Demand-side perspective is a novel strategy theory that complete the traditional one by remarking the consumer role in the development of the strategy. In this book, a text mining approach is applied using KNIME Analytics Platform and is employed to investigate the Automotive landscape. The results of the method are used to provide to automotive practitioners demand-side coherent strategy ideas.In the literature review, I introduce the relevant business theories and position Priem's demand-side strategy. Then, I present several business analytics techniques and their applications and implications for businesses. The empirical chapter introduces KNIME and describes the implementation of the LDA algorithm. Finally, in the last chapter, I discuss the results of the analysis and suggest implication for automotive practitioners.

Autorentext

Tiziano Volpentesta is an Italian master student of Business at the University of Calabria, Italy. He graduated in Management and Finance at the University of Calabria in April 2019 and he has been a visiting student at the York University in Toronto, Canada. His interests are at the intersection of Marketing and Strategy research.