6533b854fe1ef96bd12afbeb

RESEARCH PRODUCT

Convolutional Matrix Factorization for Recommendation Explanation

Yichao LuRuihai DongBarry Smyth

subject

Recommendation modelComputer science020204 information systemsCustomer reviews0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processing02 engineering and technologyData miningcomputer.software_genreTransparency (behavior)Convolutional neural networkcomputerMatrix decomposition

description

In this paper, we introduce a novel recommendation model, which harnesses a convolutional neural network to mine meaningful information from customer reviews, and integrates it with matrix factorization algorithm seamlessly. It is a valid method to improve the transparency of CF algorithms.

yearjournalcountryeditionlanguage
2018-03-05Proceedings of the 23rd International Conference on Intelligent User Interfaces Companion
https://doi.org/10.1145/3180308.3180343