Handling Item Similarity in Behavioral Patterns through General Pattern Mining

Modeling human behavior on the Web is an essential goal of Web usage mining and is often performed by sequential pattern mining (SPM). The similarity between data elements and the variability of human behavior often result in the decrease of the support value of some patterns and thus limit the number of patterns mined. This is often associated with a loss of information. As the data can take the form of multiple data sources that represent multiple views of the area of interest, they can be used to handle this similarity and variability. Traditional approaches form a unique dataset from these data. However, the associated mining task is complex and generates a large and redundant set of sequential patterns. This work proposes G_SPM, a pattern mining algorithm designed for behavioral pattern mining that takes advantage of multi-source data to handle the similarity, while adopting a selective mining strategy to limit the complexity of the mining process and the increase in the number of patterns. It considers the behavioral data source as the main source, and exploits complementary sources only when similarity is suspected. It forms frequent general patterns that represent sets of similar behavioral patterns with a limited frequency, while controlling the level of generality. Experimental results confirm that G_SPM succeeds in mining general patterns and thus in handling the problem of item similarity. In addition G_SPM outperforms traditional approaches in terms of runtime and redundancy of the resulting set of patterns.