Advertisement

Entity Ranking by Learning and Inferring Pairwise Preferences from User Reviews

  • Shinryo Uchida
  • Takehiro YamamotoEmail author
  • Makoto P. Kato
  • Hiroaki Ohshima
  • Katsumi Tanaka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10648)

Abstract

In this paper, we propose a method of ranking entities (e.g. products) based on pairwise preferences learned and inferred from user reviews. Our proposed method finds expressions from user reviews that indicate pairwise preferences of entities in terms of a certain attribute, and learns a function that determines the relative degree of the attribute to rank entities. Since there are a limited number of such expressions in reviews, we further propose a method of inferring pairwise preferences based on attribute dependencies obtained from reviews. As some pairwise preferences are less confident, we also propose a modified version of a learning to rank method, Fuzzy Ranking SVM, which can take into account the uncertainty of pairwise preferences. The experiment was carried out with three categories of products and several attributes specific to each category. The experimental results showed that our approach could learn more accurate pairwise preferences than baseline methods, and inference based on the attribute dependency could improve the performances.

Keywords

Entity ranking Learning to rank Review mining 

Notes

Acknowledgments

This work was supported by JSPS KAKENHI Grant Numbers JP15H01718, JP26700009, JP16H02906, JP16K16156, and JP25240050.

References

  1. 1.
    Bailey, P., De Vries, A.P., Craswell, N., Soboroff, I.: Overview of the TREC 2007 enterprise track. In: TREC (2007)Google Scholar
  2. 2.
    Balog, K., Thomas, P., Craswell, N., Soboroff, I., Bailey, P., De Vries, A.P.: Overview of the TREC 2008 enterprise track. In: TREC (2008)Google Scholar
  3. 3.
    Carenini, G., Ng, R.T., Zwart, E.: Extracting knowledge from evaluative text. In: K-CAP, pp. 11–18 (2005)Google Scholar
  4. 4.
    Chen, X., Bennett, P.N., Collins-Thompson, K., Horvitz, E.: Pairwise ranking aggregation in a crowdsourced setting. In: WSDM, pp. 193–202 (2013)Google Scholar
  5. 5.
    Cheng, W., Rademaker, M., De Baets, B., Hüllermeier, E.: Predicting partial orders: ranking with abstention. In: ECML-PKDD, pp. 215–230 (2010)Google Scholar
  6. 6.
    Choi, J., Kim, D., Kim, S., Lee, J., Lim, S., Lee, S., Kang, J.: Consento: a new framework for opinion based entity search and summarization. In: CIKM, pp. 1935–1939 (2012)Google Scholar
  7. 7.
    Craswell, N., de Vries, A.P., Soboroff, I.: Overview of the TREC 2005 enterprise track. In: TREC (2005)Google Scholar
  8. 8.
    de Vries, A.P., Vercoustre, A.-M., Thom, J.A., Craswell, N., Lalmas, M.: Overview of the INEX 2007 entity ranking track. In: Fuhr, N., Kamps, J., Lalmas, M., Trotman, A. (eds.) INEX 2007. LNCS, vol. 4862, pp. 245–251. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-85902-4_22 CrossRefGoogle Scholar
  9. 9.
    Demartini, G., Iofciu, T., de Vries, A.P.: Overview of the INEX 2009 entity ranking track. In: Geva, S., Kamps, J., Trotman, A. (eds.) INEX 2009. LNCS, vol. 6203, pp. 254–264. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-14556-8_26 CrossRefGoogle Scholar
  10. 10.
    Demartini, G., de Vries, A.P., Iofciu, T., Zhu, J.: Overview of the INEX 2008 entity ranking track. In: Geva, S., Kamps, J., Trotman, A. (eds.) INEX 2008. LNCS, vol. 5631, pp. 243–252. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-03761-0_25 CrossRefGoogle Scholar
  11. 11.
    Ganesan, K., Zhai, C.: Opinion-based entity ranking. Inf. Retrieval 15(2), 116–150 (2012)CrossRefGoogle Scholar
  12. 12.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD, pp. 168–177 (2004)Google Scholar
  13. 13.
    Iwanari, T., Yoshinaga, N., Kaji, N., Nishina, T., Toyoda, M., Kitsuregawa, M.: Ordering concepts based on common attribute intensity. In: IJCAI, pp. 3747–3753 (2016)Google Scholar
  14. 14.
    Jindal, N., Liu, B.: Identifying comparative sentences in text documents. In: SIGIR, pp. 244–251 (2006)Google Scholar
  15. 15.
    Joachims, T.: Optimizing search engines using click through data. In: KDD, pp. 133–142 (2002)Google Scholar
  16. 16.
    Kim, Y., Kim, W., Shim, K.: Latent ranking analysis using pairwise comparisons. In: ICDM, pp. 869–874 (2014)Google Scholar
  17. 17.
    Li, S., Lin, C.Y., Song, Y.I., Li, Z.: Comparable entity mining from comparative questions. IEEE Trans. Knowl. Data Eng. 25(7), 1498–1509 (2013)CrossRefGoogle Scholar
  18. 18.
    Lin, C.F., Wang, S.D.: Fuzzy support vector machines. IEEE Trans. Neural Networks 13(2), 464–471 (2002)CrossRefGoogle Scholar
  19. 19.
    Liu, B., Hu, M., Cheng, J.: Opinion observer: analyzing and comparing opinions on the web. In: WWW, pp. 342–351 (2005)Google Scholar
  20. 20.
    Nelson, P.: Information and consumer behavior. J. Polit. Econ. 78(2), 311–329 (1970)CrossRefGoogle Scholar
  21. 21.
    Soboroff, I., de Vries, A.P., Craswell, N.: Overview of the TREC 2006 enterprise track. In: TREC (2006)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Shinryo Uchida
    • 1
  • Takehiro Yamamoto
    • 1
    Email author
  • Makoto P. Kato
    • 1
  • Hiroaki Ohshima
    • 2
  • Katsumi Tanaka
    • 1
  1. 1.Graduate School of InformaticsKyoto UniversityKyotoJapan
  2. 2.Graduate School of Applied InformaticsUniversity of HyogoKobeJapan

Personalised recommendations