Regularize and Explicit Collaborative Filtering With Textual Attention - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Regularize and Explicit Collaborative Filtering With Textual Attention

Abstract

Recommendation can be seen as tantamount to blind sentiment analysis, i.e. a sentiment prediction without text data. In that sense, we aim at encoding priors on users and items while reading their reviews, using a deep architecture with personalized attention modeling. Following this idea, we build an hybrid hierarchical sentiment classifier which is then used as a recommender system in inference.
No file

Dates and versions

hal-02503475 , version 1 (10-03-2020)

Identifiers

  • HAL Id : hal-02503475 , version 1

Cite

Charles-Emmanuel Dias, Vincent Guigue, Patrick Gallinari. Regularize and Explicit Collaborative Filtering With Textual Attention. ESANN 2018 - European Symposium on Artificial Neural Networks, Apr 2018, Bruges, Belgium. ⟨hal-02503475⟩
37 View
0 Download

Share

Gmail Facebook X LinkedIn More