On the role of time and sessions in diversifying recommendation results

On the role of time and sessions in diversifying recommendation results

Proceedings of the 8th Italian Information Retrieval Workshop - -2017

Authors

Anelli Vito Walter, Bellini Vito, Di Noia Tommaso, La Bruna Wanda, Tomeo Paolo, Di Sciascio Eugenio

Abstract

Intent-aware approaches to diversification have been proposed in the last years to provide the user with a list of recommendations covering different aspects of her behavior. In this paper, we present two diversification methods taking into account temporal aspects of the user profile: in the first one, in order to emphasize the importance of more recent items, we adopt a temporal decay function while in the second one we take into account temporal sessions. The two proposed methods have been implemented as temporal variants of the well-known xQuAD framework and tested against the Netflix 100M dataset.

Download: 2017_Anelli_IIR2017.pdf

DOI

https://doi.org/10.1145/3125486.3125496

BibTex references

@InProceedings{ABDLTD17a,
  author       = "Anelli, Vito Walter and Bellini, Vito and Di Noia, Tommaso and La Bruna, Wanda and Tomeo, Paolo and Di Sciascio, Eugenio",
  title        = "On the role of time and sessions in diversifying recommendation results",
  booktitle    = "Proceedings of the 8th Italian Information Retrieval Workshop",
  volume       = "1911",
  pages        = "92--95",
  year         = "2017",
  publisher    = "CEUR-WS",
  url          = "http://sisinflab.poliba.it/Publications/2017/ABDLTD17a"

}