Collaborative multi-level embedding learning from reviews for rating prediction

Zhang Wei, Quan Yuan, Jiawei Han, Wang Jianyong

Research output: Contribution to journalConference article

Abstract

We investigate the problem of personalized reviewbased rating prediction which aims at predicting users' ratings for items that they have not evaluated by using their historical reviews and ratings. Most of existing methods solve this problem by integrating topic model and latent factor model to learn interpretable user and items factors. However, these methods cannot utilize word local context information of reviews. Moreover, it simply restricts user and item representations equivalent to their review representations, which may bring some irrelevant information in review text and harm the accuracy of rating prediction. In this paper, we propose a novel Collaborative Multi-Level Embedding (CMLE) model to address these limitations. The main technical contribution of CMLE is to integrate word embedding model with standard matrix factorization model through a projection level. This allows CMLE to inherit the ability of capturing word local context information from word embedding model and relax the strict equivalence requirement by projecting review embedding to user and item embeddings. A joint optimization problem is formulated and solved through an efficient stochastic gradient ascent algorithm. Empirical evaluations on real datasets show CMLE outperforms several competitive methods and can solve the two limitations well.

Original languageEnglish (US)
Pages (from-to)2986-2992
Number of pages7
JournalIJCAI International Joint Conference on Artificial Intelligence
Volume2016-January
StatePublished - Jan 1 2016
Event25th International Joint Conference on Artificial Intelligence, IJCAI 2016 - New York, United States
Duration: Jul 9 2016Jul 15 2016

Fingerprint

Factorization

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Collaborative multi-level embedding learning from reviews for rating prediction. / Wei, Zhang; Yuan, Quan; Han, Jiawei; Jianyong, Wang.

In: IJCAI International Joint Conference on Artificial Intelligence, Vol. 2016-January, 01.01.2016, p. 2986-2992.

Research output: Contribution to journalConference article

@article{c7fbc80f5d304e6b8a82a7d5d1fa8f21,
title = "Collaborative multi-level embedding learning from reviews for rating prediction",
abstract = "We investigate the problem of personalized reviewbased rating prediction which aims at predicting users' ratings for items that they have not evaluated by using their historical reviews and ratings. Most of existing methods solve this problem by integrating topic model and latent factor model to learn interpretable user and items factors. However, these methods cannot utilize word local context information of reviews. Moreover, it simply restricts user and item representations equivalent to their review representations, which may bring some irrelevant information in review text and harm the accuracy of rating prediction. In this paper, we propose a novel Collaborative Multi-Level Embedding (CMLE) model to address these limitations. The main technical contribution of CMLE is to integrate word embedding model with standard matrix factorization model through a projection level. This allows CMLE to inherit the ability of capturing word local context information from word embedding model and relax the strict equivalence requirement by projecting review embedding to user and item embeddings. A joint optimization problem is formulated and solved through an efficient stochastic gradient ascent algorithm. Empirical evaluations on real datasets show CMLE outperforms several competitive methods and can solve the two limitations well.",
author = "Zhang Wei and Quan Yuan and Jiawei Han and Wang Jianyong",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
volume = "2016-January",
pages = "2986--2992",
journal = "IJCAI International Joint Conference on Artificial Intelligence",
issn = "1045-0823",

}

TY - JOUR

T1 - Collaborative multi-level embedding learning from reviews for rating prediction

AU - Wei, Zhang

AU - Yuan, Quan

AU - Han, Jiawei

AU - Jianyong, Wang

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We investigate the problem of personalized reviewbased rating prediction which aims at predicting users' ratings for items that they have not evaluated by using their historical reviews and ratings. Most of existing methods solve this problem by integrating topic model and latent factor model to learn interpretable user and items factors. However, these methods cannot utilize word local context information of reviews. Moreover, it simply restricts user and item representations equivalent to their review representations, which may bring some irrelevant information in review text and harm the accuracy of rating prediction. In this paper, we propose a novel Collaborative Multi-Level Embedding (CMLE) model to address these limitations. The main technical contribution of CMLE is to integrate word embedding model with standard matrix factorization model through a projection level. This allows CMLE to inherit the ability of capturing word local context information from word embedding model and relax the strict equivalence requirement by projecting review embedding to user and item embeddings. A joint optimization problem is formulated and solved through an efficient stochastic gradient ascent algorithm. Empirical evaluations on real datasets show CMLE outperforms several competitive methods and can solve the two limitations well.

AB - We investigate the problem of personalized reviewbased rating prediction which aims at predicting users' ratings for items that they have not evaluated by using their historical reviews and ratings. Most of existing methods solve this problem by integrating topic model and latent factor model to learn interpretable user and items factors. However, these methods cannot utilize word local context information of reviews. Moreover, it simply restricts user and item representations equivalent to their review representations, which may bring some irrelevant information in review text and harm the accuracy of rating prediction. In this paper, we propose a novel Collaborative Multi-Level Embedding (CMLE) model to address these limitations. The main technical contribution of CMLE is to integrate word embedding model with standard matrix factorization model through a projection level. This allows CMLE to inherit the ability of capturing word local context information from word embedding model and relax the strict equivalence requirement by projecting review embedding to user and item embeddings. A joint optimization problem is formulated and solved through an efficient stochastic gradient ascent algorithm. Empirical evaluations on real datasets show CMLE outperforms several competitive methods and can solve the two limitations well.

UR - http://www.scopus.com/inward/record.url?scp=85006165297&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006165297&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85006165297

VL - 2016-January

SP - 2986

EP - 2992

JO - IJCAI International Joint Conference on Artificial Intelligence

JF - IJCAI International Joint Conference on Artificial Intelligence

SN - 1045-0823

ER -