Mapping Product Taxonomies in E-commerce
Steven S. Aanen, Lennart J. Nederstigt, Damir Vandić, Flavius Frăsincar · EUR Research Repository (Erasmus University Rotterdam) · 2012
In this paper we propose SCHEMA, an algorithm that automatically maps heterogeneous product taxonomies in the domain of e-commerce. SCHEMA employs a custom word sense disambiguation technique, based on the Lesk algorithm, in combination with the semantic lexicon WordNet. For finding candidate target categories and determining the path-similarity we propose a semantic category matching algorithm that takes into account the disambiguation process of a category. The mapping quality score is calculated using the Damerau-Levenshtein distance and a node-dissimilarity penalty. The performance of SCHEMA was tested on three real-life datasets and compared to PROMPT and the algorithm proposed by Park & Kim. The comparison shows that SCHEMA improves considerably recall and F1-score, while maintaining similar precision.