Parallel Session 3, MICE Track: Toward Unsupervised Machine Learning Technique to Discover the Key Topics Influence Exhibition Visitor Engagement in Social Media: A Case Study from Taiwan

Classroom 209

Unsupervised machine learning of text mining in social media has become a new research area in the past decade. Topic modelling is a probabilistic generative model that has been used in the field of computer science and bioinformatics. This pioneer study utilized topic modelling in unsupervised machine learning technic to analyze the contemporary exhibition visitor engagement in social media Facebook fan page. Latent Dirichlet Allocation (LDA) result supported that the visitors were highly concerned with gamification activities for an incentive prize both to create involvement and to enhance exhibition experience. The results visualization provide a professional exhibition organizer (PEO) with accurate information in developing successful E-WOM marketing strategies in social media or an exhibition management design for promoting successful exhibition visitor engagements in real time.