Predicting image popularity in an incomplete social media community by a weighted bi-partite graph

Xiang Niu, Lusong Li, Tao Mei, Jialie Shen, Ke Xu

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

Abstract

Popularity prediction is a key problem in networks to analyze the information diffusion, especially in social media communities. Recently, there have been some custom-build prediction models in Digg and YouTube. However, these models are hardly transplant to an incomplete social network site (e.g., Flickr) by their unique parameters. In addition, because of the large scale of the network in Flickr, it is difficult to get all of the photos and the whole network. Thus, we are seeking for a method which can be used in such incomplete network. Inspired by a collaborative filtering method - Network-based Inference (NBI), we devise a weighted bipartite graph with undetected users and items to represent the resource allocation process in an incomplete network. Instead of image analysis, we propose a modified interdisciplinary models, called Incomplete Network-based Inference (INI). Using the data from 30 months in Flickr, we show the proposed INI is able to increase prediction accuracy by over 58.1%, compared with traditional NBI. We apply our proposed INI approach to personalized advertising application and show that it is more attractive than traditional Flickr advertising.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Multimedia and Expo
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages735-740
Number of pages6
ISBN (Electronic)978-0-7695-4711-4
ISBN (Print)978-1-4673-1659-0
DOIs
Publication statusPublished - 5 Nov 2012
Externally publishedYes
Event2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012 - Melbourne, VIC, Australia
Duration: 9 Jul 201213 Jul 2012

Conference

Conference2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012
CountryAustralia
CityMelbourne, VIC
Period9/07/1213/07/12

Fingerprint

Marketing
Transplants
Collaborative filtering
Image analysis
Resource allocation

Cite this

Niu, X., Li, L., Mei, T., Shen, J., & Xu, K. (2012). Predicting image popularity in an incomplete social media community by a weighted bi-partite graph. In 2012 IEEE International Conference on Multimedia and Expo (pp. 735-740). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICME.2012.43
Niu, Xiang ; Li, Lusong ; Mei, Tao ; Shen, Jialie ; Xu, Ke. / Predicting image popularity in an incomplete social media community by a weighted bi-partite graph. 2012 IEEE International Conference on Multimedia and Expo. IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 735-740
@inproceedings{5c2b16c9e7804620908603c6022ba719,
title = "Predicting image popularity in an incomplete social media community by a weighted bi-partite graph",
abstract = "Popularity prediction is a key problem in networks to analyze the information diffusion, especially in social media communities. Recently, there have been some custom-build prediction models in Digg and YouTube. However, these models are hardly transplant to an incomplete social network site (e.g., Flickr) by their unique parameters. In addition, because of the large scale of the network in Flickr, it is difficult to get all of the photos and the whole network. Thus, we are seeking for a method which can be used in such incomplete network. Inspired by a collaborative filtering method - Network-based Inference (NBI), we devise a weighted bipartite graph with undetected users and items to represent the resource allocation process in an incomplete network. Instead of image analysis, we propose a modified interdisciplinary models, called Incomplete Network-based Inference (INI). Using the data from 30 months in Flickr, we show the proposed INI is able to increase prediction accuracy by over 58.1{\%}, compared with traditional NBI. We apply our proposed INI approach to personalized advertising application and show that it is more attractive than traditional Flickr advertising.",
keywords = "Bipartite graph, incomplete network inference, personalized advertising, popularity prediction, social media",
author = "Xiang Niu and Lusong Li and Tao Mei and Jialie Shen and Ke Xu",
year = "2012",
month = "11",
day = "5",
doi = "10.1109/ICME.2012.43",
language = "English",
isbn = "978-1-4673-1659-0",
pages = "735--740",
booktitle = "2012 IEEE International Conference on Multimedia and Expo",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Niu, X, Li, L, Mei, T, Shen, J & Xu, K 2012, Predicting image popularity in an incomplete social media community by a weighted bi-partite graph. in 2012 IEEE International Conference on Multimedia and Expo. IEEE, Institute of Electrical and Electronics Engineers, pp. 735-740, 2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012, Melbourne, VIC, Australia, 9/07/12. https://doi.org/10.1109/ICME.2012.43

Predicting image popularity in an incomplete social media community by a weighted bi-partite graph. / Niu, Xiang; Li, Lusong; Mei, Tao; Shen, Jialie; Xu, Ke.

2012 IEEE International Conference on Multimedia and Expo. IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 735-740.

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

TY - GEN

T1 - Predicting image popularity in an incomplete social media community by a weighted bi-partite graph

AU - Niu, Xiang

AU - Li, Lusong

AU - Mei, Tao

AU - Shen, Jialie

AU - Xu, Ke

PY - 2012/11/5

Y1 - 2012/11/5

N2 - Popularity prediction is a key problem in networks to analyze the information diffusion, especially in social media communities. Recently, there have been some custom-build prediction models in Digg and YouTube. However, these models are hardly transplant to an incomplete social network site (e.g., Flickr) by their unique parameters. In addition, because of the large scale of the network in Flickr, it is difficult to get all of the photos and the whole network. Thus, we are seeking for a method which can be used in such incomplete network. Inspired by a collaborative filtering method - Network-based Inference (NBI), we devise a weighted bipartite graph with undetected users and items to represent the resource allocation process in an incomplete network. Instead of image analysis, we propose a modified interdisciplinary models, called Incomplete Network-based Inference (INI). Using the data from 30 months in Flickr, we show the proposed INI is able to increase prediction accuracy by over 58.1%, compared with traditional NBI. We apply our proposed INI approach to personalized advertising application and show that it is more attractive than traditional Flickr advertising.

AB - Popularity prediction is a key problem in networks to analyze the information diffusion, especially in social media communities. Recently, there have been some custom-build prediction models in Digg and YouTube. However, these models are hardly transplant to an incomplete social network site (e.g., Flickr) by their unique parameters. In addition, because of the large scale of the network in Flickr, it is difficult to get all of the photos and the whole network. Thus, we are seeking for a method which can be used in such incomplete network. Inspired by a collaborative filtering method - Network-based Inference (NBI), we devise a weighted bipartite graph with undetected users and items to represent the resource allocation process in an incomplete network. Instead of image analysis, we propose a modified interdisciplinary models, called Incomplete Network-based Inference (INI). Using the data from 30 months in Flickr, we show the proposed INI is able to increase prediction accuracy by over 58.1%, compared with traditional NBI. We apply our proposed INI approach to personalized advertising application and show that it is more attractive than traditional Flickr advertising.

KW - Bipartite graph

KW - incomplete network inference

KW - personalized advertising

KW - popularity prediction

KW - social media

UR - http://www.scopus.com/inward/record.url?scp=84868098787&partnerID=8YFLogxK

U2 - 10.1109/ICME.2012.43

DO - 10.1109/ICME.2012.43

M3 - Conference Paper published in Proceedings

SN - 978-1-4673-1659-0

SP - 735

EP - 740

BT - 2012 IEEE International Conference on Multimedia and Expo

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Niu X, Li L, Mei T, Shen J, Xu K. Predicting image popularity in an incomplete social media community by a weighted bi-partite graph. In 2012 IEEE International Conference on Multimedia and Expo. IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 735-740 https://doi.org/10.1109/ICME.2012.43