Topic modelling is a prominent task for automatic topic extraction in many applications such as sentiment analysis and recommendation systems. The approach is vital for service industries to monitor their customer discussions. The use of traditional approaches such as Latent Dirichlet Allocation (LDA) for topic discovery has shown great performances, however, they are not consistent in their results as these approaches suffer from data sparseness and inability to model the word order in a document. Thus, this study presents the use of Kernel Principal Component Analysis (KernelPCA) and K-means Clustering in the BERTopic architecture. We have prepared a new dataset using tweets from customers of Nigerian banks and we use this to compare the topic modelling approaches. Our findings showed KernelPCA and K-means in the BERTopic architecture-produced coherent topics with a coherence score of 0.8463.
The term Knowledge Exchange (KE) is commonly used to describe university-industry collaborations that frequently foster innovation. Understanding such collaborations and their potential value is a difficult activity. The means of supporting collaboration vary significantly and potential for successful innovation is hard to asses. In this paper, we describe work aimed at developing an improved understanding of knowledge exchange within a digital context-both within digital sectors and also in non-digital sectors where the adoption of digital technologies can lead to new and challenging opportunities. Our work focuses upon digital innovation for Small to Medium Enterprises (SMEs) aiming to support effective Knowledge Exchange based innovation; a specific driver being the difficulty of understanding the potential for successful and productive collaborations with individual SMEs. From a number of existing digital innovation models and instruments, factors for characterizing digital innovation potential have identified. However, based on our experience and expert feedback, such characterizations appear to be inappropriate for SMEs. In response to this, an instrument has been developed to identify potential for quality digital innovation based on collaborative KE between SMEs and universities. The instrument is introduced, and its development and refinement discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.