VideoTopic: Content-based video recommendation using a topic model

Qiusha Zhu, Mei-Ling Shyu, Haohong Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Citations (Scopus)

Abstract

Most video recommender systems limit the content to the metadata associated with the videos, which could lead to poor results since metadata is not always available or correct. Meanwhile, the visual information of videos is typically not fully explored, which is especially important for recommending new items with limited metadata information. In this paper, a novel content-based video recommendation framework, called Video Topic, that utilizes a topic model is proposed. It decomposes the recommendation process into video representation and recommendation generation. It aims to capture user interests in videos by using a topic model to represent the videos, and then generates recommendations by finding those videos that most fit to the topic distribution of the user interests. Experimental results on the Movie Lens dataset validate the effectiveness of Video Topic by evaluating each of its components and the whole framework.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013
Pages219-222
Number of pages4
DOIs
StatePublished - Dec 1 2013
Event15th IEEE International Symposium on Multimedia, ISM 2013 - Anaheim, CA, United States
Duration: Dec 9 2013Dec 11 2013

Other

Other15th IEEE International Symposium on Multimedia, ISM 2013
CountryUnited States
CityAnaheim, CA
Period12/9/1312/11/13

Fingerprint

Metadata
Recommender systems
Lenses

Keywords

  • content-based video recommendation
  • topic model
  • video presentation
  • VideoTopic

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Zhu, Q., Shyu, M-L., & Wang, H. (2013). VideoTopic: Content-based video recommendation using a topic model. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013 (pp. 219-222). [6746793] https://doi.org/10.1109/ISM.2013.41

VideoTopic : Content-based video recommendation using a topic model. / Zhu, Qiusha; Shyu, Mei-Ling; Wang, Haohong.

Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. p. 219-222 6746793.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhu, Q, Shyu, M-L & Wang, H 2013, VideoTopic: Content-based video recommendation using a topic model. in Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013., 6746793, pp. 219-222, 15th IEEE International Symposium on Multimedia, ISM 2013, Anaheim, CA, United States, 12/9/13. https://doi.org/10.1109/ISM.2013.41
Zhu Q, Shyu M-L, Wang H. VideoTopic: Content-based video recommendation using a topic model. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. p. 219-222. 6746793 https://doi.org/10.1109/ISM.2013.41
Zhu, Qiusha ; Shyu, Mei-Ling ; Wang, Haohong. / VideoTopic : Content-based video recommendation using a topic model. Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. pp. 219-222
@inproceedings{a4d920f5a04b4abd8768d9c7db7b8a18,
title = "VideoTopic: Content-based video recommendation using a topic model",
abstract = "Most video recommender systems limit the content to the metadata associated with the videos, which could lead to poor results since metadata is not always available or correct. Meanwhile, the visual information of videos is typically not fully explored, which is especially important for recommending new items with limited metadata information. In this paper, a novel content-based video recommendation framework, called Video Topic, that utilizes a topic model is proposed. It decomposes the recommendation process into video representation and recommendation generation. It aims to capture user interests in videos by using a topic model to represent the videos, and then generates recommendations by finding those videos that most fit to the topic distribution of the user interests. Experimental results on the Movie Lens dataset validate the effectiveness of Video Topic by evaluating each of its components and the whole framework.",
keywords = "content-based video recommendation, topic model, video presentation, VideoTopic",
author = "Qiusha Zhu and Mei-Ling Shyu and Haohong Wang",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ISM.2013.41",
language = "English",
isbn = "9780769551401",
pages = "219--222",
booktitle = "Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013",

}

TY - GEN

T1 - VideoTopic

T2 - Content-based video recommendation using a topic model

AU - Zhu, Qiusha

AU - Shyu, Mei-Ling

AU - Wang, Haohong

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Most video recommender systems limit the content to the metadata associated with the videos, which could lead to poor results since metadata is not always available or correct. Meanwhile, the visual information of videos is typically not fully explored, which is especially important for recommending new items with limited metadata information. In this paper, a novel content-based video recommendation framework, called Video Topic, that utilizes a topic model is proposed. It decomposes the recommendation process into video representation and recommendation generation. It aims to capture user interests in videos by using a topic model to represent the videos, and then generates recommendations by finding those videos that most fit to the topic distribution of the user interests. Experimental results on the Movie Lens dataset validate the effectiveness of Video Topic by evaluating each of its components and the whole framework.

AB - Most video recommender systems limit the content to the metadata associated with the videos, which could lead to poor results since metadata is not always available or correct. Meanwhile, the visual information of videos is typically not fully explored, which is especially important for recommending new items with limited metadata information. In this paper, a novel content-based video recommendation framework, called Video Topic, that utilizes a topic model is proposed. It decomposes the recommendation process into video representation and recommendation generation. It aims to capture user interests in videos by using a topic model to represent the videos, and then generates recommendations by finding those videos that most fit to the topic distribution of the user interests. Experimental results on the Movie Lens dataset validate the effectiveness of Video Topic by evaluating each of its components and the whole framework.

KW - content-based video recommendation

KW - topic model

KW - video presentation

KW - VideoTopic

UR - http://www.scopus.com/inward/record.url?scp=84900590255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900590255&partnerID=8YFLogxK

U2 - 10.1109/ISM.2013.41

DO - 10.1109/ISM.2013.41

M3 - Conference contribution

AN - SCOPUS:84900590255

SN - 9780769551401

SP - 219

EP - 222

BT - Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013

ER -