Jester 2.0 (demonstration abstract): collaborative filtering to retrieve jokes

1. INRODUCTION Jester 2.0 is a WWW-based system that allows users to retrieve jokes baaed on their ratings of sample jokes. It predicts the humor preferences of a user and presents a set of jokes that the user might find “funny”. The heart of the recommendation scheme is a new principal component analysis (PCA) and clustering-based linear time collaborative filtering algorithm for efficient and effective personalized information retrieval. The inputs to the algorithm are the userS ratings for jokes in a set of jokes called the “predictor set”.