Collective Intelligence Based Algorithm for Ranking Book Reviews

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 215)

Abstract

IIR (Internet Information Retrieval) system searches important documents on the internet by measuring the importance of these documents. For this purpose, various ranking techniques are proposed and adopted. In this paper, we propose ReviewRank, a ranking technique for finding book reviews. With an increasing number of people buying books online, reviews of books written by other people have become more important. General ranking techniques measure the importance of documents based on references or quotations between documents through hyperlinks. However, they are not suitable for book reviews. In this paper, we analyze characteristics of the importance of book reviews based on voluntary participation or evaluation of people called as collective intelligence, and proposes measures for considering the importance. We also suggest a ranking algorithm which adopts ReviewRank for finding book reviews. Experimental results show that ReviewRank outperforms previous ranking techniques for both general IIR system and searching book reviews.

Keywords

Book review Information retrieval Ranking technique Collective intelligence 

Notes

Acknowledgments

This research was supported by the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (NRF No. 2012-0003740 and 2012-0000478).

References

  1. 1.
    Aizawa AN (2003) An information-theoretic perspective of Tf-idf measures. J Inf Process Manag 39(1):45–65MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Alyguliev RM (2007) Analysis of hyperlinks and the ant algorithm for calculating the ranks of web pages. ACCS 41(1):44–53Google Scholar
  3. 3.
    Dou Z, Song R, Nie JY, Wen JR (2009) Using anchor texts with their hyperlink structure for web search. SIGIR, New York, pp 227–234Google Scholar
  4. 4.
    Duan Y, Jiang L, Qin T, Zhou M, Shum HY (2010) An empirical study on learning to rank of tweets. In: COLING pp 295–303Google Scholar
  5. 5.
    Egghe L, Leydesdorff L (2009) The relation between Pearson’s correlation coefficient r and Salton’s cosine measure. CoRRGoogle Scholar
  6. 6.
    Gayo-Avello D (2010) Nepotistic relationships in Twitter and their impact on rank prestige algorithms. CoRRGoogle Scholar
  7. 7.
    Huang JJS, Yang SJH, Chen JYL, Li I, Hsiao IYT (2010) A social bookmarking-based people search service building communities of practice with collective intelligence. IJOCI 1(2):83–95Google Scholar
  8. 8.
    Krol D, Lopes HS (2012) Nature-inspired collective intelligence in theory and practice. Inf Sci 182(1):243–263Google Scholar
  9. 9.
    Page L, Brin S, Motwani R, Winograd T (1999) The pagerank citation ranking: bringing order to the web. Technical Report, Stanford InfoLabGoogle Scholar
  10. 10.
    Ryang H, Yun U (2011) Effective ranking techniques for book review retrieval based on the structural feature. Lecture Note in Computer Science, ICHIT, CheJu Island, pp 360–367Google Scholar
  11. 11.
    Teevan J, Ramage D, Morris MR (2011) #TwitterSearch: a comparison of microblog search and web search. WSDM, pp 35–44Google Scholar
  12. 12.
    Tumer D, Wolpert D (2011) Collective intelligence, data routing and Braess’ paradox. CoRRGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  1. 1.Department of Computer ScienceChungbuk National UniversityHeungdeok-guRepublic of Korea

Personalised recommendations