A Bayesian Approach to Identify Photos Likely to Be More Popular in Social Media

DOI: 10.4236/jcc.2015.311031   PDF   HTML   XML   3,495 Downloads   3,909 Views   Citations

Abstract

With cameras becoming ubiquitous in Smartphones, it has become a very common trend to capture and share moments with friends and family in social media. Arguably, the 2 most relevant factors that contribute to the popularity are: the user’s social aspect and the content of the image (image quality, objects in the image etc.). In recent years, due to various security concerns, it has been increasingly difficult to derive social attributes from social media. Due to this limitation, in this paper we study what make images popular in social media based on the image content alone. We use Bayesian learning approach with variable likelihood function in order to predict image popularity. Our finding shows that a mapping between image content to image popularity can be achieved with a significant recall and precision. We then use our model to predict images that are likely to be more popular from a set of user images which eventually facilitate easy share.

Share and Cite:

Choudhury, A. and Nagaswamy, S. (2015) A Bayesian Approach to Identify Photos Likely to Be More Popular in Social Media. Journal of Computer and Communications, 3, 198-204. doi: 10.4236/jcc.2015.311031.

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1] Petrovic, S., Osborne, M. and Lavrenko, V. (2011) Rt to Win! Predicting Message Propagation in Twitter. ICWSM.
[2] Hong, L., Dan, O. and Davison, B.D. (2011) Predicting Popular Messages in Twitter. WWW (Companion Volume), 57-58. http://dx.doi.org/10.1145/1963192.1963222
[3] Pinto, H., Almeida, J.M. and Goncalves, M.A. (2013) Using Early View Patterns to Predict the Popularity of Youtube Videos. WSDM, 365-374.
[4] Shamma, D.A., Yew, J., Kennedy, L. and Churchill, E.F. (2011) Viral Actions: Predicting Video View Counts Using Synchronous Sharing Behaviors. ICWSM.
[5] Nwana, A.O., Avestimehr, S. and Chen, T. (2013) A Latent Social Approach to Youtube Popularity Prediction. CoRR.
[6] Khosla, A., Sarma, A.D. and Hamid, R. (2014) What Makes an Image Popular? IW3C2.
[7] Figueiredo, F. (2013) On the Prediction of Popularity of Trends and Hits for User Generated Videos. Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, 741-746. http://dx.doi.org/10.1145/2433396.2433489
[8] Figueiredo, F., Benevenuto, F. and Almeida, J.M. (2011) The Tube over Time: Characterizing Popularity Growth of YouTube Videos. Proceedings of the Fourth ACM International Con-ference on Web Search and Data Mining, 745- 754. http://dx.doi.org/10.1145/1935826.1935925
[9] Vanwinckelen, G. and Meert, W. (2014) Predicting the Popularity of Online Articles with Random Forests. ECML/ PKDD Discovery Challenge on Predictive Web Analytics, Nancy, September 2014.
[10] Yu, B., Chen, M. and Kwok, L. (2011) Toward Predicting Popularity of Social Marketing Messages. Salerno, J., et al., Eds., SBP 2011, LNCS 6589, 317-324. http://dx.doi.org/10.1007/978-3-642-19656-0_44
[11] He, X., et al. (2014) Practical Lessons from Predicting Clicks on Ads at Facebook. ADKDD’14, 24-27 August 2014. http://dx.doi.org/10.1145/2648584.2648589
[12] Cheng, J., Adamic, L.A., Dow, P.A., Kleinberg, J. and Leskovec, J. Can Cascades Be Predicted? WWW’14, Seoul, Republic of Korea.
[13] Daume III, H. A Course in Machine Learning. Chapter 5.1, 69.

  
comments powered by Disqus

Copyright © 2020 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.