Personalizing recommendation diversity based on user personality


In recent years, diversity has attracted increasing attention in the field of recommender systems because of its ability of catching users’ various interests by providing a set of dissimilar items. There are few endeavors to personalize the recommendation diversity being tailored to individual users’ diversity needs. However, they mainly depend on users’ behavior history such as ratings to customize diversity, which has two limitations: (1) They neglect taking into account a user’s needs that are inherently caused by some personal factors such as personality; (2) they fail to work well for new users who have little behavior history. In order to address these issues, this paper proposes a generalized, dynamic personality-based greedy re-ranking approach to generating the recommendation list. On one hand, personality is used to estimate each user’s diversity preference. On the other hand, personality is leveraged to alleviate the cold-start problem of collaborative filtering recommendations. The experimental results demonstrate that our approach significantly outperforms related methods (including both non-diversity-oriented and diversity-oriented methods) in terms of metrics measuring recommendation accuracy and personalized diversity degree, especially in the cold-start setting.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. 1.

  2. 2.

    High C means that the user has high score on the personality trait “Conscientiousness”, which is also applied to the other abbreviations (i.e., O for “Openness to Experience”, E for “Extroversion”, A for “Agreeableness”, and N for “Neuroticism”).

  3. 3.

  4. 4.

  5. 5.

    The type classification is determined by Douban, and each group belongs to one type.

  6. 6.

    Active user refers to the user who has at least one behavior record during the year 2015 (from Jan. 1 to Dec. 31), e.g., creating a group/topic, joining a group, leaving a comment, recommending or liking a group/topic.

  7. 7.

    To clean the data, we first excluded 118 incomplete answers (5.7%). We then analyzed users’ answers to the personality questionnaire and filtered out all of the contradictory records [e.g., a user rated 5 (out of 5) on two opposite statements “I think I am cold and aloof” and “I think I am considerate and kind to almost everyone”], by which we further removed 252 invalid answers.

  8. 8.

    A POMP score is a linear transformation of any raw metric into a 0–100 scale, where 0 represents the minimum possible score and 100 represents the maximum possible score (Cohen et al. 1999). In this case, \({ Score}_{{ POMP}}=({ Score}_{{ ORI}}-1) \times 25\), where \({ Score}_{{ ORI}}\) ranges from 1 to 5.

  9. 9.

    Similar to other work that often uses genres of movies, cuisine types in restaurants, or topic categories of news stories, to calculate items’ diversity (Eskandanian et al. 2017), we mainly considered the types of groups users have joined.

  10. 10.

    The reason we did not use Cosine similarity measure (Qian et al. 2004) is because it may produce the deviation when two compared vectors are along with the same direction. For example, given three users’ personality vectors (\(ps_a=(1,1,1,1,1)^T\), \(ps_b=(2,2,2,2,2)^T\), and \(ps_c=(5,5,5,5,5)^T\)), we can obtain the Cosine similarity results: \(Sim_{Cosine}(ps_a,ps_b)=Sim_{Cosine}(ps_a,ps_c)=1\), but in fact, user b should be more similar to user a than user c, which can be more accurately identified by the Euclidean distance measure.

  11. 11.

    Users vary in their use of a rating scale (Schafer et al. 2007). For instance, one optimistic user may consistently rate items 4 out of 5 stars, while a pessimistic user may often give 3 starts even though s/he likes the item.

  12. 12.

  13. 13.

    \(Improvement percentage (IP)=\frac{Value_{testmodel}-Value_{Baseline}}{Value_{Baseline}}\), where \(Value_{Baseline}\) and \(Value_{testmodel}\) respectively denote the performance of the baseline RB approach and the test model such as PB Greedy.

  14. 14.

    Average improvement percentage (Average IP)=\(\frac{\sum _{n \in N} IP_{Num=n}}{|N|}\), where N refers to the set of training data size (\(N=\{1,3,5,7,10,15,20\}\)).


  1. Adomavicius, G., Kwon, Y.: Toward more diverse recommendations: item re-ranking methods for recommender systems. In: Workshop on Information Technologies and Systems (WITS 2009), pp. 417–440. Citeseer (2009)

  2. Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans. Knowl. Data Eng. 17(6), 734–749 (2005)

    Article  Google Scholar 

  3. Ajzen, I.: Attitudes, Personality, and Behavior. McGraw-Hill Education, London (2005)

    Google Scholar 

  4. Armstrong, R.A.: When to use the bonferroni correction. Ophthalmic Physiol. Opt. 34(5), 502–508 (2014)

    Article  Google Scholar 

  5. Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2–3), 235–256 (2002)

    Article  MATH  Google Scholar 

  6. Bradley, K., Smyth, B.: Improving recommendation diversity. In: Proceedings of the 12th Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2001), pp. 85–94 (2001)

  7. Breese, J.S., Heckerman, D., Kadie, C.: Empirical analysis of predictive algorithms for collaborative filtering. In: Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence (UAI 1998), pp. 43–52. Morgan Kaufmann Publishers Inc. (1998)

  8. Carbonell, J., Goldstein, J.: The use of mmr, diversity-based reranking for reordering documents and producing summaries. In: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 1998), pp. 335–336. ACM (1998)

  9. Celli, F., Pianesi, F., Stillwell, D., Kosinski, M.: Workshop on computational personality recognition (shared task). In: Proceedings of the Workshop on Computational Personality Recognition (2013)

  10. Chen, D., Plemmons, R.J.: Nonnegativity constraints in numerical analysis. Birth Numer. Anal. 10, 109–140 (2009)

    Article  MATH  Google Scholar 

  11. Chen, L., Pu, P.: Preference-based organization interfaces: aiding user critiques in recommender systems. User Model. 2007, 77–86 (2007)

    Google Scholar 

  12. Chen, L., Wu, W., He, L.: How personality influences users’ needs for recommendation diversity? In: Proceedings of the 31st ACM Conference on Human Factors in Computing Systems (CHI 2013 Extended Abstracts), pp. 829–834. ACM (2013)

  13. Chen, L., Wu, W., He, L.: Personality and recommendation diversity. In: Emotions and Personality in Personalized Services, vol. 3, pp. pp–201. Springer International Publishing (2016)

  14. Clarke, C.L., Kolla, M., Cormack, G.V., Vechtomova, O., Ashkan, A., Büttcher, S., MacKinnon, I.: Novelty and diversity in information retrieval evaluation. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2008), pp. 659–666. ACM (2008)

  15. Cohen, P., Cohen, J., Aiken, L.S., West, S.G.: The problem of units and the circumstance for pomp. Multivar. Behav. Res. 34(3), 315–346 (1999)

    Article  Google Scholar 

  16. Cronbach, L.J.: Theory of generalizability for scores and profiles. The Dependability of Behavioral Measurements pp. 161–188 (1972)

  17. De Vries, L., Gensler, S., Leeflang, P.S.: Popularity of brand posts on brand fan pages: an investigation of the effects of social media marketing. J. Interact. Mark. 26(2), 83–91 (2012)

    Article  Google Scholar 

  18. Desrosiers, C., Karypis, G.: A comprehensive survey of neighborhood-based recommendation methods. In: Recommender Systems Handbook, pp. 107–144. Springer, Berlin (2011)

  19. Di Noia, T., Ostuni, V.C., Rosati, J., Tomeo, P., Di Sciascio, E.: An analysis of users’ propensity toward diversity in recommendations. In: Proceedings of the 8th ACM Conference on Recommender Systems (RecSys 2014), pp. 285–288. ACM (2014)

  20. Digman, J.M.: Personality structure: emergence of the five-factor model. Annu. Rev. Psychol. 41(1), 417–440 (1990)

    Article  Google Scholar 

  21. Eskandanian, F., Mobasher, B., Burke, R.: A clustering approach for personalizing diversity in collaborative recommender systems. In: Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (UMAP 2017), pp. 280–284. ACM (2017)

  22. Ge, M., Delgado-Battenfeld, C., Jannach, D.: Beyond accuracy: evaluating recommender systems by coverage and serendipity. In: Proceedings of the 4th ACM Conference on Recommender Systems (RecSys 2010), pp. 257–260. ACM (2010)

  23. Helson, R., Soto, C.J.: Up and down in middle age: monotonic and nonmonotonic changes in roles, status, and personality. J. Pers. Soc. Psychol. 89(2), 194 (2005)

    Article  Google Scholar 

  24. Herlocker, J.L., Konstan, J.A., Terveen, L.G., Riedl, J.T.: Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. 22(1), 5–53 (2004)

    Article  Google Scholar 

  25. Hofmann, T.: Latent semantic models for collaborative filtering. ACM Trans. Inf. Syst. 22(1), 89–115 (2004)

    Article  Google Scholar 

  26. Hu, R., Pu, P.: Acceptance issues of personality-based recommender systems. In: Proceedings of the 3rd ACM Conference on Recommender Systems (RecSys 2009), pp. 221–224. ACM (2009)

  27. Hu, R., Pu, P.: A study on user perception of personality-based recommender systems. User Modeling, Adaptation, and Personalization (UMAP 2010), pp. 291–302 (2010)

  28. Hu, R., Pu, P.: Enhancing collaborative filtering systems with personality information. In: Proceedings of the 5th ACM Conference on Recommender Systems (RecSys 2011), pp. 197–204. ACM (2011)

  29. Hu, R., Pu, P.: Helping users perceive recommendation diversity. In: DiveRS@ RecSys, pp. 43–50 (2011)

  30. Hu, Y., Koren, Y., Volinsky, C.: Collaborative filtering for implicit feedback datasets. In: Proceedings of the 8th International Conference on Data Mining (ICDM 2008), pp. 263–272. IEEE (2008)

  31. Järvelin, K., Kekäläinen, J.: Cumulated gain-based evaluation of ir techniques. ACM Trans. Inf. Syst. 20(4), 422–446 (2002)

    Article  Google Scholar 

  32. John, O.P., Srivastava, S.: The big five trait taxonomy: history, measurement, and theoretical perspectives. Handb. Pers. Theory Res. 2(1999), 102–138 (1999)

    Google Scholar 

  33. Kaiseler, M., Polman, R.C., Nicholls, A.R.: Effects of the big five personality dimensions on appraisal coping, and coping effectiveness in sport. Eur. J. Sport Sci. 12(1), 62–72 (2012)

    Article  Google Scholar 

  34. Kaminskas, M., Bridge, D.: Diversity, serendipity, novelty, and coverage: a survey and empirical analysis of beyond-accuracy objectives in recommender systems. ACM Trans. Interact. Intell. Syst. 7(1), 2 (2016)

    Article  Google Scholar 

  35. Karumur, R.P., Nguyen, T.T., Konstan, J.A.: Personality, user preferences and behavior in recommender systems. Inf. Syst. Front. 6, 1–25 (2017)

    Google Scholar 

  36. Kaufman, L., Rousseeuw, P.: Clustering by Means of Medoids. North-Holland, Amsterdam (1987)

    Google Scholar 

  37. Knijnenburg, B.P., Willemsen, M.C., Gantner, Z., Soncu, H., Newell, C.: Explaining the user experience of recommender systems. User Model. User-Adap. Interact. 22(4–5), 441–504 (2012)

    Article  Google Scholar 

  38. Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)

    Article  Google Scholar 

  39. Lawson, C.L., Hanson, R.J.: Solving Least Squares Problems. SIAM, Philadelphia (1995)

    Google Scholar 

  40. McCrae, R.R., Terracciano, A.: Personality profiles of cultures: aggregate personality traits. J. Pers. Soc. Psychol. 89(3), 407 (2005)

    Article  Google Scholar 

  41. McNee, S.M., Riedl, J., Konstan, J.A.: Being accurate is not enough: how accuracy metrics have hurt recommender systems. In: Proceedings of the 24th ACM Conference on Human Factors in Computing Systems (CHI 2006 Extended Abstracts), pp. 1097–1101. ACM (2006)

  42. Mourão, F., Fonseca, C., Araujo, C.S., Meira Jr, W.: The oblivion problem: exploiting forgotten items to improve recommendation diversity. In: DiveRS@ RecSys, pp. 27–34 (2011)

  43. Nadkarni, A., Hofmann, S.G.: Why do people use facebook? Pers. Individ. Differ. 52(3), 243–249 (2012)

    Article  Google Scholar 

  44. Nguyen, T.T., Hui, P.M., Harper, F.M., Terveen, L., Konstan, J.A.: Exploring the filter bubble: the effect of using recommender systems on content diversity. In: Proceedings of the 23rd International Conference on World Wide Web (WWW 2014), pp. 677–686. ACM (2014)

  45. Nunes, M.A.S., Hu, R.: Personality-based recommender systems: an overview. In: Proceedings of the 6th ACM Conference on Recommender Systems (RecSys 2012), pp. 5–6. ACM (2012)

  46. Nunnally, J.C., Bernstein, I.H., Berge, J.M.T.: Psychometric Theory, vol. 226. McGraw-Hill, New York (1967)

    Google Scholar 

  47. Perrett, D., Schaffer, J., Piccone, A., Roozeboom, M., et al.: Bonferroni adjustments in tests for regression coefficients. Mult. Linear Regres. Viewp. 32, 1–6 (2006)

    Google Scholar 

  48. Powers, D.M.: Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. J. Mach. Learn. Technol. 2, 37–63 (2011)

    Google Scholar 

  49. Qian, G., Sural, S., Gu, Y., Pramanik, S.: Similarity between euclidean and cosine angle distance for nearest neighbor queries. In: Proceedings of the 19th ACM Symposium on Applied Computing (SAC 2004), pp. 1232–1237. ACM (2004)

  50. Rentfrow, P.J., Gosling, S.D.: The do re mi’s of everyday life: the structure and personality correlates of music preferences. J. Pers. Soc. Psychol. 84(6), 1236 (2003)

    Article  Google Scholar 

  51. Rényi, A., et al.: On measures of entropy and information. In: Proceedings of the 4th Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Contributions to the Theory of Statistics. The Regents of the University of California (1961)

  52. Roberts, B.W.: Back to the future: personality and assessment and personality development. J. Res. Pers. 43(2), 137–145 (2009)

    Article  Google Scholar 

  53. Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web (WWW 2001), pp. 285–295. ACM (2001)

  54. Schafer, J.B., Frankowski, D., Herlocker, J., Sen, S.: Collaborative filtering recommender systems. In: The Aaptive Web, pp. 291–324. Springer, Berlin (2007)

  55. Seber, G.A., Lee, A.J.: Linear Regression Analysis, vol. 329. Wiley, New York (2012)

    Google Scholar 

  56. Sha, C., Wu, X., Niu, J.: A framework for recommending relevant and diverse items. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI 2016), pp. 3868–3874 (2016)

  57. Shani, G., Gunawardana, A.: Evaluating recommendation systems. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds.) Recommender Systems Handbook, pp. 257–297. Springer, Boston (2011)

    Google Scholar 

  58. Shi, Y., Larson, M., Hanjalic, A.: List-wise learning to rank with matrix factorization for collaborative filtering. In: Proceedings of the 4th ACM Conference on Recommender Systems (RecSys 2010), pp. 269–272. ACM (2010)

  59. Shi, Y., Zhao, X., Wang, J., Larson, M., Hanjalic, A.: Adaptive diversification of recommendation results via latent factor portfolio. In: Proceedings of the 35th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2012), pp. 175–184. ACM (2012)

  60. Smyth, B., McClave, P.: Similarity vs. diversity. In: Aha, D.W., Watson, I. (eds.) Case-Based Reasoning Research and Development, pp. 347–361. Springer, Berlin (2001)

    Google Scholar 

  61. Srivastava, S., John, O.P., Gosling, S.D., Potter, J.: Development of personality in early and middle adulthood: set like plaster or persistent change? J. Pers. Soc. Psychol. 84(5), 1041 (2003)

    Article  Google Scholar 

  62. Su, X., Khoshgoftaar, T.M.: A survey of collaborative filtering techniques. Adv. Artif. Intell. 2009, 4 (2009)

    Article  Google Scholar 

  63. Thackeray, R., Neiger, B.L., Smith, A.K., Van Wagenen, S.B.: Adoption and use of social media among public health departments. BMC Pub. Health 12(1), 242 (2012)

    Article  Google Scholar 

  64. Tintarev, N., Dennis, M., Masthoff, J.: Adapting recommendation diversity to openness to experience: a study of human behaviour. In: International Conference on User Modeling, Adaptation, and Personalization (UMAP 2013), pp. 190–202. Springer, Berlin (2013)

  65. Tkalcic, M., Kunaver, M., Tasic, J., Košir, A.: Personality based user similarity measure for a collaborative recommender system. In: Proceedings of the 5th Workshop on Emotion in Human-Computer Interaction-Real World Challenges, pp. 30–37 (2009)

  66. Tkalcic, M., Quercia, D., Graf, S.: Preface to the special issue on personality in personalized systems. User Model. User-Adap. Interact. 26(2–3), 103 (2016)

    Article  Google Scholar 

  67. Tobias, I.F., Braunhofer, M., Elahi, M., Ricci, F., Ivan, C.: Alleviating the new user problem in collaborative filtering by exploiting personality information. User Model. User-Adapt. Interact. 26, 221–255 (2016)

    Article  Google Scholar 

  68. Vargas, S., Castells, P.: Exploiting the diversity of user preferences for recommendation. In: Proceedings of the 10th Conference on Open Research Areas in Information Retrieval (OAIR 2013), pp. 129–136. LE CENTRE DE HAUTES ETUDES INTERNATIONALES D’INFORMATIQUE DOCUMENTAIRE (2013)

  69. Wang, J., Zhu, J.: Portfolio theory of information retrieval. In: Proceedings of the 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2009), pp. 115–122. ACM (2009)

  70. Willemsen, M.C., Graus, M.P., Knijnenburg, B.P.: Understanding the role of latent feature diversification on choice difficulty and satisfaction. User Model. User-Adap. Interact. 26(4), 347–389 (2016)

    Article  Google Scholar 

  71. Wood, D., Wortman, J.: Trait means and desirabilities as artifactual and real sources of differential stability of personality traits. J. Pers. 80(3), 665–701 (2012)

    Article  Google Scholar 

  72. Wu, W., Chen, L.: Implicit acquisition of user personality for augmenting movie recommendations. In: International Conference on User Modeling, Adaptation, and Personalization (UMAP 2015), pp. 302–314. Springer, Berlin (2015)

  73. Wu, W., Chen, L., He, L.: Using personality to adjust diversity in recommender systems. In: Proceedings of the 24th ACM Conference on Hypertext and Social Media (HT 2013), pp. 225–229. ACM (2013)

  74. Wu, W., He, L., Yang, J.: Evaluating recommender systems. In: Proceedings of the 7th International Conference on Digital Information Management (ICDIM 2012), pp. 56–61. IEEE (2012)

  75. Zeng, W., Shang, M.S., Zhang, Q.M., Lü, L., Zhou, T.: Can dissimilar users contribute to accuracy and diversity of personalized recommendation? Int. J. Mod. Phys. C 21(10), 1217–1227 (2010)

    Article  Google Scholar 

  76. Zhang, M., Hurley, N.: Avoiding monotony: improving the diversity of recommendation lists. In: Proceedings of the 2nd ACM Conference on Recommender Systems (RecSys 2008), pp. 123–130. ACM (2008)

  77. Ziegler, C.N., McNee, S.M., Konstan, J.A., Lausen, G.: Improving recommendation lists through topic diversification. In: Proceedings of the 14th International Conference on World Wide Web (WWW 2005), pp. 22–32. ACM (2005)

Download references


We thank all participants who took part in our user survey. We also thank reviewers for their suggestions and comments. In addition, we thank Hong Kong Research Grants Council (RGC) for sponsoring the research work (under Project RGC/HKBU12200415).

Author information



Corresponding author

Correspondence to Wen Wu.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Wu, W., Chen, L. & Zhao, Y. Personalizing recommendation diversity based on user personality. User Model User-Adap Inter 28, 237–276 (2018).

Download citation


  • Recommender system
  • Diversity
  • Personality traits
  • User survey
  • Greedy re-ranking