A Trail Based Internet-Domain Recommender System using Artificial Neural Networks.
Tobias Berka, Wernher Behrendt, Erich Gams, Siegfried Reich (2002): A Trail Based Internet-Domain Recommender System using Artificial Neural Networks. In: Proceedings of the Int. Conf. on Adaptive Hypermedia and Adaptive Web Based Systems, AH2002
This paper discusses the use of artificial neural networks, trained with patterns extracted from trail data, as recommender systems. More specifically, feed-forward Multilayer Perceptrons trained with the Backpropagation Algorithm were used to assign a rating to pairs of domains, based on the number of people that have traversed between them.
This rating, applied to the hyper-graph neighborhood of an HTML document, can be used to suggest related domains to the user. The artificial neural network constructed in this project was capable of learning, and thus reproducing, the training set to a great extent. Outside of the training set, several experiments indicated that the artificial neural network becomes both capable of finding domains that are related, and an expert for domains that are relevant for the user community that produced the trail data.