Recommendation in a changingworld: Exploiting temporal dynamics in ratings and reviews

Yining Liu, Yong Liu, Yanming Shen, Keqiu Li

Research output: Contribution to journalArticle

Abstract

Users' preferences, and consequently their ratings and reviews to items, change over time. Likewise, characteristics of items are also time-varying. By dividing data into time periods, temporal Recommender Systems (RSs) improve recommendation accuracy by exploring the temporal dynamics in user rating data. However, temporal RSs have to cope with rating sparsity in each time period. Meanwhile, reviews generated by users contain rich information about their preferences, which can be exploited to address rating sparsity and further improve the performance of temporal RSs. In this article, we develop a temporal rating model with topics that jointly mines the temporal dynamics of both user-item ratings and reviews. Studying temporal drifts in reviews helps us understand item rating evolutions and user interest changes over time. Our model also automatically splits the review text in each time period into interim words and intrinsic words. By linking interim words and intrinsic words to short-term and long-term item features, respectively, we jointly mine the temporal changes in user and item latent features together with the associated review text in a single learning stage. Through experiments on 28 real-world datasets collected from Amazon, we show that the rating prediction accuracy of our model significantly outperforms the existing state-of-art RS models. And our model can automatically identify representative interim words in each time period as well as intrinsic words across all time periods. This can be very useful in understanding the time evolution of users' preferences and items' characteristics.

Original languageEnglish (US)
Article number3
JournalACM Transactions on the Web
Volume12
Issue number1
DOIs
StatePublished - Aug 1 2017

Fingerprint

Recommender systems
Experiments

Keywords

  • Recommender Systems
  • Temporal dynamics
  • Topic models

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Recommendation in a changingworld : Exploiting temporal dynamics in ratings and reviews. / Liu, Yining; Liu, Yong; Shen, Yanming; Li, Keqiu.

In: ACM Transactions on the Web, Vol. 12, No. 1, 3, 01.08.2017.

Research output: Contribution to journalArticle

@article{169b61841727401786b146b0a6d5e5c9,
title = "Recommendation in a changingworld: Exploiting temporal dynamics in ratings and reviews",
abstract = "Users' preferences, and consequently their ratings and reviews to items, change over time. Likewise, characteristics of items are also time-varying. By dividing data into time periods, temporal Recommender Systems (RSs) improve recommendation accuracy by exploring the temporal dynamics in user rating data. However, temporal RSs have to cope with rating sparsity in each time period. Meanwhile, reviews generated by users contain rich information about their preferences, which can be exploited to address rating sparsity and further improve the performance of temporal RSs. In this article, we develop a temporal rating model with topics that jointly mines the temporal dynamics of both user-item ratings and reviews. Studying temporal drifts in reviews helps us understand item rating evolutions and user interest changes over time. Our model also automatically splits the review text in each time period into interim words and intrinsic words. By linking interim words and intrinsic words to short-term and long-term item features, respectively, we jointly mine the temporal changes in user and item latent features together with the associated review text in a single learning stage. Through experiments on 28 real-world datasets collected from Amazon, we show that the rating prediction accuracy of our model significantly outperforms the existing state-of-art RS models. And our model can automatically identify representative interim words in each time period as well as intrinsic words across all time periods. This can be very useful in understanding the time evolution of users' preferences and items' characteristics.",
keywords = "Recommender Systems, Temporal dynamics, Topic models",
author = "Yining Liu and Yong Liu and Yanming Shen and Keqiu Li",
year = "2017",
month = "8",
day = "1",
doi = "10.1145/3108238",
language = "English (US)",
volume = "12",
journal = "ACM Transactions on the Web",
issn = "1559-1131",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - Recommendation in a changingworld

T2 - Exploiting temporal dynamics in ratings and reviews

AU - Liu, Yining

AU - Liu, Yong

AU - Shen, Yanming

AU - Li, Keqiu

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Users' preferences, and consequently their ratings and reviews to items, change over time. Likewise, characteristics of items are also time-varying. By dividing data into time periods, temporal Recommender Systems (RSs) improve recommendation accuracy by exploring the temporal dynamics in user rating data. However, temporal RSs have to cope with rating sparsity in each time period. Meanwhile, reviews generated by users contain rich information about their preferences, which can be exploited to address rating sparsity and further improve the performance of temporal RSs. In this article, we develop a temporal rating model with topics that jointly mines the temporal dynamics of both user-item ratings and reviews. Studying temporal drifts in reviews helps us understand item rating evolutions and user interest changes over time. Our model also automatically splits the review text in each time period into interim words and intrinsic words. By linking interim words and intrinsic words to short-term and long-term item features, respectively, we jointly mine the temporal changes in user and item latent features together with the associated review text in a single learning stage. Through experiments on 28 real-world datasets collected from Amazon, we show that the rating prediction accuracy of our model significantly outperforms the existing state-of-art RS models. And our model can automatically identify representative interim words in each time period as well as intrinsic words across all time periods. This can be very useful in understanding the time evolution of users' preferences and items' characteristics.

AB - Users' preferences, and consequently their ratings and reviews to items, change over time. Likewise, characteristics of items are also time-varying. By dividing data into time periods, temporal Recommender Systems (RSs) improve recommendation accuracy by exploring the temporal dynamics in user rating data. However, temporal RSs have to cope with rating sparsity in each time period. Meanwhile, reviews generated by users contain rich information about their preferences, which can be exploited to address rating sparsity and further improve the performance of temporal RSs. In this article, we develop a temporal rating model with topics that jointly mines the temporal dynamics of both user-item ratings and reviews. Studying temporal drifts in reviews helps us understand item rating evolutions and user interest changes over time. Our model also automatically splits the review text in each time period into interim words and intrinsic words. By linking interim words and intrinsic words to short-term and long-term item features, respectively, we jointly mine the temporal changes in user and item latent features together with the associated review text in a single learning stage. Through experiments on 28 real-world datasets collected from Amazon, we show that the rating prediction accuracy of our model significantly outperforms the existing state-of-art RS models. And our model can automatically identify representative interim words in each time period as well as intrinsic words across all time periods. This can be very useful in understanding the time evolution of users' preferences and items' characteristics.

KW - Recommender Systems

KW - Temporal dynamics

KW - Topic models

UR - http://www.scopus.com/inward/record.url?scp=85028550636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028550636&partnerID=8YFLogxK

U2 - 10.1145/3108238

DO - 10.1145/3108238

M3 - Article

AN - SCOPUS:85028550636

VL - 12

JO - ACM Transactions on the Web

JF - ACM Transactions on the Web

SN - 1559-1131

IS - 1

M1 - 3

ER -