Social and Content Hybrid Image Recommender System for Mobile Social Networks

Abstract

One of the advantages of social networks is the possibility to socialize and personalize the content created or shared by the users. In mobile social networks, where the devices have limited capabilities in terms of screen size and computing power, Multimedia Recommender Systems help to present the most relevant content to the users, depending on their tastes, relationships and profile. Previous recommender systems are not able to cope with the uncertainty of automated tagging and are knowledge domain dependant. In addition, the instantiation of a recommender in this domain should cope with problems arising from the collaborative filtering inherent nature (cold start, banana problem, large number of users to run, etc.). The solution presented in this paper addresses the abovementioned problems by proposing a hybrid image recommender system, which combines collaborative filtering (social techniques) with content-based techniques, leaving the user the liberty to give these processes a personal weight. It takes into account aesthetics and the formal characteristics of the images to overcome the problems of current techniques, improving the performance of existing systems to create a mobile social networks recommender with a high degree of adaptation to any kind of user.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Roberts M, Ducheneaut N, Begole B, Partridge K, Price B, Bellotti V, Walendowski A, Rasmussen P (2008) Scalable architecture for context-aware activity-detecting mobile recommendation systems. International Symposium on a World of Wireless, Mobile and Multimedia Networks, pp 1–6, 23–26 June 2008

  2. 2.

    Gombrich EH (2002) Art and illusion: a study in the psychology of pictorial representation. Phaidon Press, London

    Google Scholar 

  3. 3.

    Itten J (2002) The art of color: the subjective experience and objective rationale of color. Wiley, New York

    Google Scholar 

  4. 4.

    Davis S (ed) (2000) Color perception: philosophical, psychological, artistic, and computational perspectives. Oxford University Press, New York

    Google Scholar 

  5. 5.

    Ren T, Wu G (2010) Automatic image retargeting evaluation based on user perception. Image Processing (ICIP), 2010 17th IEEE International Conference on, vol., no., pp 1569–1572, 26–29 Sept. 2010

  6. 6.

    Adomavicius G, Tuzhilin A (2006) Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng 17(6):734–742

    Article  Google Scholar 

  7. 7.

    Veltkamp RC, Tanase M (2000) Content-based image retrieval systems: a survey. Technical Report UU-CS-2000-34, Dept. of Computing Science, Utrecht University

  8. 8.

    Boutemedjet S, Ziou D (2008) A graphical model for context-aware visual content recommendation. IEEE Trans Multimed 10(1):52–62

    Article  Google Scholar 

  9. 9.

    Gudivada VN, Raghavan VV (1995) Content based image retrieval systems. Computer 28(9):18–22

    Article  Google Scholar 

  10. 10.

    Godoy D, Amandi A (2008) Hybrid content and tag-based profiles for recommendation in collaborative tagging systems. Proceedings of the 6th Latin American web congress. IEEE Computer Society Vila Velha, Brazil, Pages 58–65

  11. 11.

    Hyvönen E, Styrman A, Saarela S (2002) Ontology-based image retrieval. Towards the semantic web and web services. Proceedings of the XML Finland 2002 Conference, Helsinki, Finland, 2002, Pages 15–27

  12. 12.

    Sheth B, Maes P (1993) Evolving agents for personalized information filtering. Proceedings to the Ninth Conference on Artificial Intelligence for Applications, March 1993, Pages 345–352

  13. 13.

    Balabanovic M, Shoham Y (1997) Fab: content-based, collaborative recommendation. Communications of ACM 40, March 1997, Pages 66–72

  14. 14.

    Tkalčič M, Burnik U, Košir A. Using affective parameters in a content-based recommender system for images. User Model User-Adap 20(4):279–311

  15. 15.

    Benitez AB, Beigi M, Shih-Fu C (1998) Using relevance feedback in content-based image metasearch. IEEE Internet Comput 2(4):59–69

    Article  Google Scholar 

  16. 16.

    Candillier L, Meyer F, Boullé M (2007) Comparing state-of-the-art collaborative filtering systems. Proceedings of the 5th international conference on machine learning and data mining in pattern recognition, July 18–20, 2007, Leipzig, Germany

  17. 17.

    Gao Y, Luo H, Fan J (2009) Personalized image recommendation. 15th International Multimedia Modeling Conference, MMM 2009, volume 5371 LNCS, pp 217–219, Sophia-Antipolis, France, 7–9 Jan 2009

    Article  Google Scholar 

  18. 18.

    Milicevic AK, Nanopoulos A, Ivanovic M (2010) Social tagging in recommender systems: a survey of the state-of-the-art and possible extensions. Artificial Intelligence Review, Springer Netherlands, Pages 187–209

  19. 19.

    Burke R (2002) Hybrid recommender systems: survey and experiments. User modeling and user-adapted interaction, Springer Netherlands, issue 4, vol. 12, Nov. 2002, pp 331–370

  20. 20.

    Sang Hyun C, Young-Seon J, Jeong MK (2010) A hybrid recommendation method with reduced data for large-scale application. IEEE Trans Syst Man Cybern C Appl Rev 40(5):557–566

    Article  Google Scholar 

  21. 21.

    Kazienko P, Musiał K and Kajdanowicz T (2011) Multidimensional social network in the social recommender system. IEEE Trans Syst Man Cybern Syst Hum Vol. 41, Nº 4, Julio 2011

  22. 22.

    Arazy O, Kumar N, Shapira B (2009) Improving social recommender systems. Social computing. IEEE Computer Society Julio/Agosto

  23. 23.

    Granovetter MS (1983) The strength of the weak tie: revisited [PDF]. Socio Theor 1:201–233

    Article  Google Scholar 

  24. 24.

    Krackhardt D (1992) The strength of strong ties: the importance of philos in organizations. In: Nohria N, Eccles R (eds) Networks and organizations: structure, form, and action. Harvard Business School Press, Boston, pp 216–239

    Google Scholar 

  25. 25.

    Herlocker JL, Constant JA, Terveen LG, Riedl JT (2004) Evaluating collaborative filtering recommender systems. ACM Trans Inf Syst 22(1):5–53

    Article  Google Scholar 

  26. 26.

    O’Donovan J, Smyth B (2005) Trust in recommender systems. IUI’05, January 9–12, 2005, San Diego, California, USA

  27. 27.

    Manjunath BS, Salembier P and Sikora T (2002) Introduction to MPEG-7: multimedia content description interface. Ed. John Wiley & Sons, Ltd

  28. 28.

    Bastan M, Cam H, Gudukbay U, Ulusoy O (2009) An MPEG-7 compatible video retrieval system with integrated support for complex multimodal queries. IEEE MultiMedia

  29. 29.

    Barrilero M, Uribe S, Alduan M, Sanchez F, Alvarez F (2011) Innetwork content based image recommendation system for Contentaware Networks. IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), April 2011, Pages 115–120

  30. 30.

    Shan Z, Hai-tao W (2008) Image retrieval based on bit-plane distribution entropy. 2008 International Conference on Computer Science and Software Engineering.

  31. 31.

    Ye F, Shi Z, Shi Z (2009) A comparative study of PCA, LDA and kernel LDA for image classification. Ubiquitous virtual reality, 2009, ISUVR ‘09. International Symposium on, vol., no., pp 51–54, 8–11 July 2009

  32. 32.

    Feng-Cheng C, Hsueh-Ming H (2008) An improved presentation method for relevance feedback in a content-based image retrieval system. Intelligent Information Hiding and Multimedia Signal Processing, 2008. IIHMSP ‘08 International Conference on, vol., no., pp 91–94, 15–17 Aug. 2008

  33. 33.

    Hadjahmadi AH, Homayounpour MM, Ahadi SM (2008) Robust weighted fuzzy c-means clustering. Fuzzy Systems, 2008, FUZZ-IEEE 2008, (IEEE World Congress on Computational Intelligence), IEEE International Conference on, vol., no., pp 305–311, 1–6 June 2008

  34. 34.

    Sledge IJ, Bezdek JC, Havens TC, Keller JM (2010) Relational generalizations of cluster validity indices. IEEE Trans Fuzzy Syst 18(4):771–786

    Article  Google Scholar 

  35. 35.

    Xie XL, Beni G (1991) A validity measure for fuzzy clustering. IEEE Trans Pattern Anal Mach Intell 13(8):841–847

    Article  Google Scholar 

  36. 36.

    Jones BC, Wilkes DM (2001) A new analysis framework for relevance feedback-driven similarity measure refinement in content-based image retrieval. Computer vision and pattern recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, vol.1, no., pp I-920- I-925 vol. 1, 2001

  37. 37.

    Sugimoto O, Naito S, Sakazawa S, Koike A (2009) Objective perceptual video quality measurement method based on hybrid no reference framework. Image Processing (ICIP), 2009 16th IEEE International Conference on, vol., no., pp 2237–2240, 7–10 Nov. 2009

  38. 38.

    Cho JH, Kwon K, Park Y (2007) Collaborative filtering using dual information sources. IEEE Intell Syst 22(3):30–38

    Article  Google Scholar 

  39. 39.

    Breese JS, Heckerman D and Kadie C (1998) Empirical analysis of predictive algorithms for collaborative filtering. In Proc. 14th Conf. Uncertainty Artificial Intell., 1998, pp 43–52

  40. 40.

    Woerndl W, Groh G (2007) Utilizing physical and social context to improve recommender systems. Web Intelligence and Intelligent Agent Technology Workshops, 2007 IEEE/WIC/ACM International Conferences on, vol., no., pp 123–128, 5–12 Nov. 2007

  41. 41.

    Widisinghe A, Ranasinghe D, Kulathilaka K, Kaluarachchi R, Wimalawarne KADNK (2010) picSEEK: collaborative filtering for context-based image recommendation. Information and Automation for Sustainability (ICIAFs), 2010 5th International Conference on, vol., no., pp 225–232, 17–19 Dec. 2010

  42. 42.

    Sanchez F, Barrilero M, Alvarez F, Cisneros G (2011) Embedded audiovisual recommender system for user terminals based on user social and implicit information. Consumer Electronics (ICCE), 2011 IEEE International Conference on, vol., no., pp 773–774, 9–12 Jan. 2011

Download references

Acknowledgments

This work was supported in part by the Spanish Ministry of Science and Innovation - CDTI under the contract of the CENIT Program, project “BUSCAMEDIA” (CEN- 20091026) (www.cenit-buscamedia.es). The authors of this paper would like to thank the people who helped to the completion of this paper by providing their ratings of the selected images to test and validate our algorithms. Moreover, the authors thank Álvaro Martínez and Iago Fernández-Cedrón for the help with the implementation of the Android application, and Javier Arróspide for the English language review.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Faustino Sanchez.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Sanchez, F., Barrilero, M., Uribe, S. et al. Social and Content Hybrid Image Recommender System for Mobile Social Networks. Mobile Netw Appl 17, 782–795 (2012). https://doi.org/10.1007/s11036-012-0399-6

Download citation

Keywords

  • aesthetics
  • social recommendation
  • content-based recommendation
  • hybrid recommender
  • image classification
  • user modeling