Extracting Information from Informal Communication

toward methods which are particularly applicable to informal communication. We also consider a type of information which is somewhat unique to informal communication: preferences and opinions. Individuals often expression their opinions on products and services in such communication. Others' may read these "reviews" to try to predict their own experiences. However, humans do a poor job of aggregating and generalizing large sets of data. We develop techniques that can perform the job of predicting unobserved opinions. We address both the single-user case where information about the items is known, and the multi-user case where we can generalize opinions without external information. Experiments on large- scale rating data sets validate our approach.