Elisabetta Fersini is currently assistant professor at the University of Milano-Bicocca (Computer Science Dept.). Her research activity is mainly focused on propositional and relational machine learning for natural language processing.
Machine learning for the analysis of customer reviews
Nowadays the number of people consulting product reviews on the web before making any purchase has increased. If most reviews are positive the probability of buying a given product increases, while if most reviews are negative almost certainly customers will choose another product. This gives strong incentives for opinion spamming, which refers to the writing fake reviews to intentionally mislead readers. In this talk, we will give an overview of the current methodologies for fake review detection, extending a markov random field model with some concepts about “burstiness of reviews”.