2012 IEEE International Conference on Multimedia and Expo 2012
DOI: 10.1109/icme.2012.43
|View full text |Cite
|
Sign up to set email alerts
|

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 us… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
12
0

Year Published

2014
2014
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 17 publications
(12 citation statements)
references
References 11 publications
0
12
0
Order By: Relevance
“…Niu et al [16] introduce a weighted bipartite graph model, called Incomplete Network-based Inference (INI), to predict image popularity based on network relationships. Cha et al [4] study how the popularity of pictures evolves over time, showing that even popular photos propagate slowly and that they do not spread widely.…”
Section: Popularity Prediction On Social Networkmentioning
confidence: 99%
See 1 more Smart Citation
“…Niu et al [16] introduce a weighted bipartite graph model, called Incomplete Network-based Inference (INI), to predict image popularity based on network relationships. Cha et al [4] study how the popularity of pictures evolves over time, showing that even popular photos propagate slowly and that they do not spread widely.…”
Section: Popularity Prediction On Social Networkmentioning
confidence: 99%
“…More recently, work has attempted to predict the popularity of images on Flickr 2 [16]. However, this approach, as well as the others mentioned, rely on the interactions of users (e.g.…”
Section: Introductionmentioning
confidence: 97%
“…Previous work on analyzing engagement on Instagram [5,13,17,18,24,26,27] treated images posted on different time periods the same way. However, as an account gets older and gathers more followers, the average number of likes for new photos posted goes up.…”
Section: Definition Of Engagement On Instagrammentioning
confidence: 99%
“…Zhu et al [2], show that photos using filters are more likely to be viewed and commented on, while Bakhshi et al [1], show that photos with faces attract more likes and comments. Several works have attempted to predict engagement using various combinations of text-based, network-based, and user-based features [5,6,10,13,17,18,24,26,27]. However, all of these works use a large dataset, containing many users.…”
Section: Introductionmentioning
confidence: 99%
“…Totti et al [42] predicted the popularity of images using aesthetics and users' information on Pinterest; they measured popularity using the number of repins. Niu et al [43] predicted the popularity of images on Flickr using network-based features, such as centrality analysis; the number of views was used as a popularity measurement. Gelli [44] used visual sentiments, and users' information to predict the normalized number of views of images on Flickr.…”
Section: Related Work For Image Popularity Predictionmentioning
confidence: 99%