Utilizing Online Social Network and Location-Based Data to Recommend Products and Categories in Online Marketplaces

  • Emanuel LacicEmail author
  • Dominik Kowald
  • Lukas Eberhard
  • Christoph Trattner
  • Denis Parra
  • Leandro Balby Marinho
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8940)


Recent research has unveiled the importance of online social networks for improving the quality of recommender systems and encouraged the research community to investigate better ways of exploiting the social information for recommendations. To contribute to this sparse field of research, in this paper we exploit users’ interactions along three data sources (marketplace, social network and location-based) to assess their performance in a barely studied domain: recommending products and domains of interests (i.e., product categories) to people in an online marketplace environment. To that end we defined sets of content- and network-based user similarity features for each data source and studied them isolated using an user-based Collaborative Filtering (CF) approach and in combination via a hybrid recommender algorithm, to assess which one provides the best recommendation performance. Interestingly, in our experiments conducted on a rich dataset collected from SecondLife, a popular online virtual world, we found that recommenders relying on user similarity features obtained from the social network data clearly yielded the best results in terms of accuracy in case of predicting products, whereas the features obtained from the marketplace and location-based data sources also obtained very good results in case of predicting categories. This finding indicates that all three types of data sources are important and should be taken into account depending on the level of specialization of the recommendation task.


Recommender systems Online marketplaces SNA Social data Location-based data SecondLife Collaborative filtering Item recommendations Product recommendations Category prediction 



This work is supported by the Know-Center and the EU funded project Learning Layers (Grant Agreement 318209). Moreover, parts of this work were carried out during the tenure of an ERCIM “Alain Bensoussan” fellowship programme. The Learning Layers project is supported by the European Commission within the 7th Framework Program, under the DG Information society and Media (E3), unit of Cultural heritage and technology-enhanced learning. The Know-Center is funded within the Austrian COMET Program - Competence Centers for Excellent Technologies - under the auspices of the Austrian Ministry of Transport, Innovation and Technology, the Austrian Ministry of Economics and Labor and by the State of Styria. COMET is managed by the Austrian Research Promotion Agency (FFG).


  1. 1.
    Zhang, Y., Pennacchiotti, M.: Predicting purchase behaviors from social media. In: Proceedings of WWW ’13, pp. 1521–1532 (2013)Google Scholar
  2. 2.
    Guo, S., Wang, M., Leskovec, J.: The role of social networks in online shopping: Information passing, price of trust, and consumer choice. In: Proceedings of EC ’11, pp. 157–166. ACM (2011)Google Scholar
  3. 3.
    Trattner, C., Parra, D., Eberhard, L., Wen, X.: Who will trade with whom? Predicting buyer-seller interactions in online trading platforms through social networks. In: Proceedings of WWW ’14, pp. 387–388. ACM (2014)Google Scholar
  4. 4.
    Ma, H., Zhou, D., Liu, C., Lyu, M.R., King, I.: Recommender systems with social regularization. In: Proceedings of WSDM ’11, pp. 287–296. ACM (2011)Google Scholar
  5. 5.
    Jamali, M., Ester, M.: A matrix factorization technique with trust propagation for recommendation in social networks. In: Proceedings of RecSys ’10, pp. 135–142. ACM, New York (2010)Google Scholar
  6. 6.
    Bischoff, K.: We love rock’n’roll: analyzing and predicting friendship links in In: Proceedings of WebSci ’12, pp. 47–56. ACM (2012)Google Scholar
  7. 7.
    Feng, W., Wang, J.: Incorporating heterogeneous information for personalized tag recommendation in social tagging systems. In: Proceedings of KDD ’12, pp. 1276–1284. ACM (2012)Google Scholar
  8. 8.
    Delporte, J., Karatzoglou, A., Matuszczyk, T., Canu, S.: Socially enabled preference learning from implicit feedback data. In: Blockeel, H., Kersting, K., Nijssen, S., Železný, F. (eds.) ECML PKDD 2013, Part II. LNCS, vol. 8189, pp. 145–160. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  9. 9.
    Lacic, E., Kowald, D., Parra, D., Kahr, M., Trattner, C.: Towards a scalable social recommender engine for online marketplaces: The case of apache solr. In: Proceedings of WWW ’14, pp. 817–822. ACM (2014)Google Scholar
  10. 10.
    Steurer, M., Trattner, C.: Acquaintance or partner? Predicting partnership in online and location-based social networks. In: Proceedings of ASONAM’13. IEEE/ACM (2013)Google Scholar
  11. 11.
    Adamic, L., Adar, E.: Friends and neighbors on the web. Soci. Netw. 25, 211–230 (2003)CrossRefGoogle Scholar
  12. 12.
    Cranshaw, J., Toch, E., Hong, J., Kittur, A., Sadeh, N.: Bridging the gap between physical location and online social networks. In: Proceedings of the 12th ACM International Conference on Ubiquitous Computing, pp. 119–128. ACM (2010)Google Scholar
  13. 13.
    Barabási, A., Albert, R.: Emergence of scaling in random networks. Science 286, 509–512 (1999)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Lacic, E., Kowald, D., Trattner, C.: Socrecm: A scalable social recommender engine for online marketplaces. In: Proceedings of HT ’14, pp. 308–310 (2014)Google Scholar
  15. 15.
    Schafer, J.B., Frankowski, D., Herlocker, J., Sen, S.: Collaborative filtering recommender systems. In: The adaptive web. Springer (2007) 291–324.Google Scholar
  16. 16.
    Bostandjiev, S., O’Donovan, J., Höllerer, T.: Tasteweights: a visual interactive hybrid recommender system. In: Proceedings of RecSys ’12, pp. 35–42. ACM (2012)Google Scholar
  17. 17.
    Smyth, B., McClave, P.: Similarity vs. Diversity. In: Aha, D.W., Watson, I. (eds.) ICCBR 2001. LNCS (LNAI), vol. 2080, pp. 347–361. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  18. 18.
    Herlocker, J.L., Konstan, J.A., Terveen, L.G., Riedl, J.T.: Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. (TOIS) 22, 5–53 (2004)CrossRefGoogle Scholar
  19. 19.
    Van Rijsbergen, C.J.: Foundation of evaluation. J. Doc. 30, 365–373 (1974)CrossRefGoogle Scholar
  20. 20.
    Parra, D., Sahebi, S.: Recommender systems: sources of knowledge and evaluation metrics. In: Velásquez, J.D., Palade, V., Jain, L.C. (eds.) Advanced Techniques in Web Intelligence-2. SCI, vol. 452, pp. 149–176. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  21. 21.
    Ge, M., Delgado-Battenfeld, C., Jannach, D.: Beyond accuracy: evaluating recommender systems by coverage and serendipity. In: Proceedings of the Fourth ACM Conference on Recommender Systems, pp. 257–260. ACM (2010)Google Scholar
  22. 22.
    Steurer, M., Trattner, C.: Predicting interactions in online social networks: an experiment in second life. In: Proceedings of the 4th International Workshop on Modeling Social Media, p. 5. ACM (2013)Google Scholar
  23. 23.
    Szell, M., Sinatra, R., Petri, G., Thurner, S., Latora, V.: Understanding mobility in a social petri dish. Scientific Reports 2 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Emanuel Lacic
    • 1
    Email author
  • Dominik Kowald
    • 1
  • Lukas Eberhard
    • 2
  • Christoph Trattner
    • 3
  • Denis Parra
    • 4
  • Leandro Balby Marinho
    • 5
  1. 1.Know-CenterGraz University of TechnologyGrazAustria
  2. 2.IICMGraz University of TechnologyGrazAustria
  3. 3.Norwegian University of Science and TechnologyTrondheimNorway
  4. 4.Pontificia Universidad Catlica de ChileSantiagoChile
  5. 5.UFCGCampina GrandeBrazil

Personalised recommendations