Symmetrization and Overfittingin Probabilistic Latent Semantic Analysis

摘要

An algorithm is proposed for revealing latent user's interests from the observable protocol of usersbehavior, e.g., site visits. The algorithm combines the ideas of customer environment analysis and probabilis-tic latent semantic analysis. A quality criterion based on the classification of preliminarily labeled sites isintroduced to optimize the algorithm parameters and compare algorithms. The experiments show that thequality has an optimum by the essential parameters of the algorithm, however the attempt of too precise opti-mization can lead to overfitting.