A Novel Semantic Clustering Approach for Reasonable Diversity in News Recommendations

  • Punam Bedi
  • Shikha Agarwa
  • Archana Singhal
  • Ena Jain
  • Gunjan Gupta
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 31)


Experienced users expect the recommendations to be accurate as well as diverse. Unconditional diversity looses user’s trust. Therefore a novel soft hierarchical semantic clustering approach is proposed to group users based on their semantic profiles, to bring reasonable diversity in news recommendations. To find ranked membership of user in a cluster, interest score along with rank of that category in profile is considered. Users are compared semantically using hierarchical structure of ontology, to bring positive serendipity along with reasonable diversity. New items are recommended with semantic ranking. Transparency helps user to understand and logically accept new unexpected recommendations. Clusters are formed by making variations in standard Jaccard similarity metric and are compared for homogeneity using Semi-Partial R-Squared (SPRS) metric. Result shows that formed clusters are better in terms of homogeneity and distribution of concepts per cluster. The approach is scalable, as number of users and items increases.


Collaborative filtering Hierarchical semantic clustering Soft clustering Semantic user profile Transparency 


  1. 1.
    Burke, R.: Knowledge-based recommender systems. In: Kent, A., Hall, C.M. (eds.) Encyclopedia of Library and Information Science, vol. 69, pp. 180–200. Marcel Dekker, New York (2000) Google Scholar
  2. 2.
    Su, X.Y., Khoshgoftaar, T.M.: A survey of collaborative filtering techniques. Adv. Artif. Intell. 2009, p. 19 (2009). Article ID 421425 Google Scholar
  3. 3.
    Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans. Know. Data Eng 17(6), 734–749 (2005)CrossRefGoogle Scholar
  4. 4.
    Herlocker, J., Konstan, J., Terveen, L., Riedl, J.: Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. 22(1), 5–53 (2004)CrossRefGoogle Scholar
  5. 5.
    Vargas, S., Castells, P.: Rank and relevance in novelty and diversity metrics for recommender systems. In: Recsys 11. ACM 2011 987-1-4503-0683-6/11/10 (2011)Google Scholar
  6. 6.
    Belem, F., Martins, E., Almeida, J., et al.: Exploiting novelty and diversity in tag recommendation. In: ECIR 2013. LNCS, vol. 7814, pp. 380–391. Springer (2013)Google Scholar
  7. 7.
    Agarwal, S., Singhal, A.: Handling skewed results in news recommendations by focused analysis of semantic user profiles. In: International Conference on Reliability Optimization and Information Technology ICROIT 2014 IEEE Delhi Section (2014)Google Scholar
  8. 8.
    Halkidi, M., Batistakis, Y., Vazirgiannis, M.: Clustering validity checking methods: part II in ACM. SIGMOD Rec. 31(3), 19–27 (2002)CrossRefGoogle Scholar
  9. 9.
    McNee, S.M., Riedl, J., Konstan, J.A.: Being accurate is not enough: how accuracy metrics have hurt recommender systems. In: Conference on Human Factors in Computing Systems (CHI 2006), pp. 997–1001. ACM, Montreal (2006)Google Scholar
  10. 10.
    Johnson, J., Johnson, P.: Explanation facilities and interactive systems. Proc. Intell. User Interfaces 93, 159–166 (1993)Google Scholar
  11. 11.
    Gupta, D., Bhatia, K.K., Sharma, A.K.: A novel indexing technique for web documents using hierarchical clustering. Int. J. Comput. Sci. Netw. Secur. 9(9), 168–175 (2009)Google Scholar
  12. 12.
    Ju, C., Xu, C.: A new collaborative recommendation approach based on users clustering using artificial bee colony algorithm. Sci. World J. 2013, 9 (2013). Article ID 869658Google Scholar
  13. 13.
    Anastasakos, T., Hillard, D., Kshetramade, S., Raghavan, H.: A collaborative filtering approach to sponsored search. In Yahoo! Labs, Technical Report No. YL-2009-006 (2009)Google Scholar
  14. 14.
    Garcin, F., Zhou, K., Faltings, B., Schickel, V.: Personalized news recommendation based on collaborative filtering. In: Proceedings of the 2012 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology, vol. 01, pp. 437–441 (2012)Google Scholar
  15. 15.
    Li, L., Wang, D., Li, T. et al.: SCENE: A scalable two-stage personalized news recommendation system. In: ACM 978-1-4503-0757-4/11/07, SIGIR’11. Beijing, China. Copyright 2011 (2011)Google Scholar
  16. 16.
    Castellano, G., Fanelli, A.M., Mencar, C. et al.: Similarity-based fuzzy clustering for user profiling. In: 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology—Workshops (2007)Google Scholar
  17. 17.
    Das, A., Datar, M., Garg, A.: Google news personalization: scalable online collaborative filtering. In: WWW 2007/Track: Industrial Practice and Experience, Alberta, Canada, 8–12 May 2007Google Scholar
  18. 18.
    Billsus, D., Pazzani, M.J.: A personal news agent that talks, learns and explains. In: Proceedings of the 3rd International Conference on Autonomous Agents, pp. 268–275. ACM Press, New York (1999)Google Scholar
  19. 19.
    Schafer, J.B. et al.: Collaborative filtering recommender systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds.) The Adaptive Web. LNCS, vol. 4321, pp. 291–324 (2007)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • Punam Bedi
    • 1
  • Shikha Agarwa
    • 1
  • Archana Singhal
    • 1
  • Ena Jain
    • 1
  • Gunjan Gupta
    • 1
  1. 1.Department of Computer ScienceUniversity of DelhiDelhiIndia

Personalised recommendations