Feeding a Hybrid Recommendation Framework with Linked Open Data and Graph-Based Features

  • Cataldo MustoEmail author
  • Pasquale Lops
  • Marco de Gemmis
  • Giovanni Semeraro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10640)


In this article we propose a hybrid recommendation framework based on classification algorithms such as Random Forests and Naive Bayes, which are fed with several heterogeneous groups of features. We split our features into two classes: classic features, as popularity-based, collaborative and content-based ones, and extended features gathered from the LOD cloud, as basic ones (i.e. genre of a movie or the writer of a book) and graph-based features calculated on the ground of the different topological characteristics of the tripartite representation connecting users, items and properties in the LOD cloud.

In the experimental session we evaluate the effectiveness of our framework on varying of different groups of features, and results show that both LOD-based and graph-based features positively affect the overall performance of the algorithm, especially in highly sparse recommendation scenarios. Our approach also outperforms several state-of-the-art recommendation techniques, thus confirming the insights behind this research.


Recommender systems Machine learning Linked open data 


  1. 1.
    Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC/ISWC -2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). CrossRefGoogle Scholar
  2. 2.
    Burke, R.: Hybrid recommender systems: survey and experiments. User Model. User-Adap. Inter. 12(4), 331–370 (2002)CrossRefzbMATHGoogle Scholar
  3. 3.
    Esposito, F., Malerba, D., Semeraro, G.: Flexible matching for noisy structural descriptions. In: IJCAI, pp. 658–664 (1991)Google Scholar
  4. 4.
    Gantner, Z., Drumond, L., Freudenthaler, C., Rendle, S., Schmidt-Thieme, L.: Learning attribute-to-feature mappings for cold-start recommendations. In: ICDM 2010, pp. 176–185. IEEE Computer Society (2010)Google Scholar
  5. 5.
    de Gemmis, M., Lops, P., Musto, C., Narducci, F., Semeraro, G.: Semantics-aware content-based recommender systems. In: Ricci, F., Rokach, L., Shapira, B. (eds.) Recommender Systems Handbook, pp. 119–159. Springer, Boston, MA (2015). CrossRefGoogle Scholar
  6. 6.
    Lops, P., de Gemmis, M., Semeraro, G.: Content-based recommender systems: state of the art and trends. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds.) Recommender Systems Handbook, pp. 73–105. Springer, Boston (2011). CrossRefGoogle Scholar
  7. 7.
    Lops, P., de Gemmis, M., Semeraro, G., Musto, C., Narducci, F., Bux, M.: A semantic content-based recommender system integrating folksonomies for personalized access. In: Castellano, G., Jain, L.C., Fanelli, A.M. (eds.) Web Personalization in Intelligent Environments. Studies in Computational Intelligence, vol. 229, pp. 27–47. Springer, Heidelberg (2009). CrossRefGoogle Scholar
  8. 8.
    Mak, H., Koprinska, I., Poon, J.: Intimate: a web-based movie recommender using text categorization. In: WI 2003, pp. 602–605. IEEE (2003)Google Scholar
  9. 9.
    Musto, C., Basile, P., Lops, P., de Gemmis, M., Semeraro, G.: Linked open data-enabled strategies for top-n recommendations. In: CEUR Workshop Proceedings CBRecSys 2014, vol. 1245, pp. 49–56 (2014).
  10. 10.
    Musto, C., Basile, P., Lops, P., de Gemmis, M., Semeraro, G.: Introducing linked open data in graph-based recommender systems. Inf. Process. Manag. 53(2), 405–435 (2017)CrossRefGoogle Scholar
  11. 11.
    Musto, C., Lops, P., Basile, P., de Gemmis, M., Semeraro, G.: Semantics-aware graph-based recommender systems exploiting linked open data. In: Proceedings of UMAP 2016, pp. 229–237. ACM (2016).
  12. 12.
    Musto, C., Semeraro, G., de Gemmis, M., Lops, P.: Learning word embeddings from wikipedia for content-based recommender systems. In: Ferro, N., Crestani, F., Moens, M.-F., Mothe, J., Silvestri, F., Di Nunzio, G.M., Hauff, C., Silvello, G. (eds.) ECIR 2016. LNCS, vol. 9626, pp. 729–734. Springer, Cham (2016). CrossRefGoogle Scholar
  13. 13.
    Musto, C., Semeraro, G., Lops, P., de Gemmis, M.: Random indexing and negative user preferences for enhancing content-based recommender systems. In: Huemer, C., Setzer, T. (eds.) EC-Web 2011. LNBIP, vol. 85, pp. 270–281. Springer, Heidelberg (2011). CrossRefGoogle Scholar
  14. 14.
    Musto, C., Semeraro, G., Lops, P., de Gemmis, M., Narducci, F.: Leveraging social media sources to generate personalized music playlists. In: Huemer, C., Lops, P. (eds.) EC-Web 2012. LNBIP, vol. 123, pp. 112–123. Springer, Heidelberg (2012). CrossRefGoogle Scholar
  15. 15.
    Ostuni, V., Di Noia, T., Di Sciascio, E., Oramas, S., Serra, X.: A semantic hybrid approach for sound recommendation. In: WWW 2015, pp. 85–86. ACM (2015)Google Scholar
  16. 16.
    Pazzani, M., Muramatsu, J., Billsus, D.: Syskill & webert: identifying interesting web sites. In: AAAI/IAAI, vol. 1, pp. 54–61 (1996)Google Scholar
  17. 17.
    Semeraro, G., Lops, P., de Gemmis, M., Musto, C., Narducci, F.: A folksonomy-based recommender system for personalized access to digital artworks. J. Comput. Cult. Herit. (JOCCH) 5(3), 11 (2012)Google Scholar
  18. 18.
    Tiroshi, A., Berkovsky, S., Kâafar, M.A., Vallet, D., Chen, T., Kuflik, T.: Improving business rating predictions using graph based features. In: IUI 2014, pp. 17–26 (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Cataldo Musto
    • 1
    Email author
  • Pasquale Lops
    • 1
  • Marco de Gemmis
    • 1
  • Giovanni Semeraro
    • 1
  1. 1.Department of Computer ScienceUniversity of Bari Aldo MoroBariItaly

Personalised recommendations