Author topic model-based collaborative filtering for personalized POI recommendations

Shuhui Jiang, Xueming Qian, Jialie Shen, Yun Fu, Tao Mei

Research output: Contribution to journalArticleResearchpeer-review

Abstract

From social media has emerged continuous needs for automatic travel recommendations. Collaborative filtering (CF) is the most well-known approach. However, existing approaches generally suffer from various weaknesses. For example , sparsity can significantly degrade the performance of traditional CF. If a user only visits very few locations, accurate similar user identification becomes very challenging due to lack of sufficient information for effective inference. Moreover, existing recommendation approaches often ignore rich user information like textual descriptions of photos which can reflect users' travel preferences. The topic model (TM) method is an effective way to solve the 'sparsity problem,' but is still far from satisfactory. In this paper, an author topic model-based collaborative filtering (ATCF) method is proposed to facilitate comprehensive points of interest (POIs) recommendations for social users. In our approach, user preference topics, such as cultural, cityscape, or landmark, are extracted from the geo-tag constrained textual description of photos via the author topic model instead of only from the geo-tags (GPS locations). Advantages and superior performance of our approach are demonstrated by extensive experiments on a large collection of data.

Original languageEnglish
Article number15125522
Pages (from-to)907-918
Number of pages12
JournalIEEE Transactions on Multimedia
Volume17
Issue number6
Early online date26 Mar 2015
DOIs
Publication statusPublished - 1 Jun 2015
Externally publishedYes

Fingerprint

Collaborative filtering
Global positioning system
Experiments

Cite this

Jiang, Shuhui ; Qian, Xueming ; Shen, Jialie ; Fu, Yun ; Mei, Tao. / Author topic model-based collaborative filtering for personalized POI recommendations. In: IEEE Transactions on Multimedia. 2015 ; Vol. 17, No. 6. pp. 907-918.
@article{19b6a7402052454cac0416af87f76957,
title = "Author topic model-based collaborative filtering for personalized POI recommendations",
abstract = "From social media has emerged continuous needs for automatic travel recommendations. Collaborative filtering (CF) is the most well-known approach. However, existing approaches generally suffer from various weaknesses. For example , sparsity can significantly degrade the performance of traditional CF. If a user only visits very few locations, accurate similar user identification becomes very challenging due to lack of sufficient information for effective inference. Moreover, existing recommendation approaches often ignore rich user information like textual descriptions of photos which can reflect users' travel preferences. The topic model (TM) method is an effective way to solve the 'sparsity problem,' but is still far from satisfactory. In this paper, an author topic model-based collaborative filtering (ATCF) method is proposed to facilitate comprehensive points of interest (POIs) recommendations for social users. In our approach, user preference topics, such as cultural, cityscape, or landmark, are extracted from the geo-tag constrained textual description of photos via the author topic model instead of only from the geo-tags (GPS locations). Advantages and superior performance of our approach are demonstrated by extensive experiments on a large collection of data.",
keywords = "Data mining, recommendation system, text mining, travel recommendation",
author = "Shuhui Jiang and Xueming Qian and Jialie Shen and Yun Fu and Tao Mei",
year = "2015",
month = "6",
day = "1",
doi = "10.1109/TMM.2015.2417506",
language = "English",
volume = "17",
pages = "907--918",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
number = "6",

}

Author topic model-based collaborative filtering for personalized POI recommendations. / Jiang, Shuhui; Qian, Xueming; Shen, Jialie; Fu, Yun; Mei, Tao.

In: IEEE Transactions on Multimedia, Vol. 17, No. 6, 15125522 , 01.06.2015, p. 907-918.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Author topic model-based collaborative filtering for personalized POI recommendations

AU - Jiang, Shuhui

AU - Qian, Xueming

AU - Shen, Jialie

AU - Fu, Yun

AU - Mei, Tao

PY - 2015/6/1

Y1 - 2015/6/1

N2 - From social media has emerged continuous needs for automatic travel recommendations. Collaborative filtering (CF) is the most well-known approach. However, existing approaches generally suffer from various weaknesses. For example , sparsity can significantly degrade the performance of traditional CF. If a user only visits very few locations, accurate similar user identification becomes very challenging due to lack of sufficient information for effective inference. Moreover, existing recommendation approaches often ignore rich user information like textual descriptions of photos which can reflect users' travel preferences. The topic model (TM) method is an effective way to solve the 'sparsity problem,' but is still far from satisfactory. In this paper, an author topic model-based collaborative filtering (ATCF) method is proposed to facilitate comprehensive points of interest (POIs) recommendations for social users. In our approach, user preference topics, such as cultural, cityscape, or landmark, are extracted from the geo-tag constrained textual description of photos via the author topic model instead of only from the geo-tags (GPS locations). Advantages and superior performance of our approach are demonstrated by extensive experiments on a large collection of data.

AB - From social media has emerged continuous needs for automatic travel recommendations. Collaborative filtering (CF) is the most well-known approach. However, existing approaches generally suffer from various weaknesses. For example , sparsity can significantly degrade the performance of traditional CF. If a user only visits very few locations, accurate similar user identification becomes very challenging due to lack of sufficient information for effective inference. Moreover, existing recommendation approaches often ignore rich user information like textual descriptions of photos which can reflect users' travel preferences. The topic model (TM) method is an effective way to solve the 'sparsity problem,' but is still far from satisfactory. In this paper, an author topic model-based collaborative filtering (ATCF) method is proposed to facilitate comprehensive points of interest (POIs) recommendations for social users. In our approach, user preference topics, such as cultural, cityscape, or landmark, are extracted from the geo-tag constrained textual description of photos via the author topic model instead of only from the geo-tags (GPS locations). Advantages and superior performance of our approach are demonstrated by extensive experiments on a large collection of data.

KW - Data mining

KW - recommendation system

KW - text mining

KW - travel recommendation

UR - http://www.scopus.com/inward/record.url?scp=84929353602&partnerID=8YFLogxK

U2 - 10.1109/TMM.2015.2417506

DO - 10.1109/TMM.2015.2417506

M3 - Article

VL - 17

SP - 907

EP - 918

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 6

M1 - 15125522

ER -