Title: Adversarial learning of Poisson factorisation models for gauging brand sentiment in user reviews
Authors: Runcong Zhao - University of Warwick (United Kingdom) [presenting]
Abstract: The Brand-Topic Model, a probabilistic model which is able to generate polarity-bearing topics of commercial brands, is presented. Compared to other topic models, BMT infers real-valued brand-associated sentiment scores and extracts fine-grained sentiment-topics which vary smoothly in a continuous range of polarity scores. It builds on the Poisson factorisation model, combining it with an adversarial learning mechanism to induce better-separated polarity-bearing topics. Experimental evaluation on Amazon reviews against several baselines shows an overall improvement of topic quality in terms of coherence, uniqueness and separation of polarised topics.