Advertisement

Learning What to Share in Online Social Networks Using Deep Reinforcement Learning

  • Shatha JaradatEmail author
  • Nima Dokoohaki
  • Mihhail Matskin
  • Elena Ferrari
Chapter
Part of the Lecture Notes in Social Networks book series (LNSN)

Abstract

Online networking sites tried their best to have right privacy mechanisms in place for users, enabling them to share the right content with the right audience. With all these efforts, privacy customizations remain hard for users across the sites. Existing research that addresses this problem mainly focuses on semi-supervised strategies that introduce extra complexity by requiring the user to manually specify initial privacy preferences for their friends. In this work, we suggest a deep reinforcement learning framework that can dynamically generate privacy labels for users in OSNs. We evaluated our framework on a 1 year crawl of Twitter data, using different types of recurrent units in recurrent neural networks (RNN): Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Simple RNN. Our experiments revealed that LSTM performed better than GRU in terms of top users detection accuracy and the ranked dependence between the generated privacy labels and estimated user trust values.

References

  1. 1.
    Madejski, M., Johnson, M., Bellovin, S.M.: A study of privacy settings errors in an online social network. In: Proceedings of 4th IEEE International Workshop on Security and Social Networking, SESOC ’12, Lugano (2012)Google Scholar
  2. 2.
    Wang, X., Liu, Y., Sun, C., Wang, B., Wang, X.: Predicting polarities of tweets by composing word embeddings with long short-term memory. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, pp. 1343–1353 (2014)Google Scholar
  3. 3.
    Vilares, D., Doval, Y., Alonso, M.A.: Deep learning experiments for sentiment analysis on Spanish tweets. In: TASS 2015 Workshop on Sentiment Analysis at SEPLN. CEUR Workshop Proceedings, Alicante, vol. 1397, pp. 47–52 (2015)Google Scholar
  4. 4.
    Li, X., Du, N., Li, H., Li, K., Gao, J., Zhang, A.: A deep learning approach to link prediction in dynamic networks. In: Proceedings of SIAM International Conference on Data Mining (SDM’14) (2014)CrossRefGoogle Scholar
  5. 5.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. J. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  6. 6.
    Cho, K., Van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches, pp. 1409–1259 (2014). Preprint. arXivGoogle Scholar
  7. 7.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Proceedings NIPS Deep Learn Workshop (2014)Google Scholar
  8. 8.
    Greff, K., Srivastava, R.K., Kout, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. In: International Conference on Machine Learning (2015)Google Scholar
  9. 9.
    Jaradat, S., Dokoohaki, D., Matskin, M., Ferrari, E.: Trust and privacy correlations in social networks: a deep learning framework. In: Advances in Social Network Analysis and Mining, pp. 203–206 (2016)Google Scholar
  10. 10.
    Carminati, B., Ferrari, E., Viviani, M. (eds.): Security and Trust in Online Social Networks. Synthesis Lectures on Information Security, Privacy, and Trust, vol. 4, pp. 1–120. Morgan & Claypool Publishers, San Rafael (2013)Google Scholar
  11. 11.
    Sherchan, W., Nepal, S., Paris, C.: A survey of trust in social networks. J. ACM Comput. Surv. 45, 47:1–47:33 (2013)CrossRefGoogle Scholar
  12. 12.
    Buskens, V.: The social structure of trust. J. Soc. Netw. 20, 265–298 (1998)CrossRefGoogle Scholar
  13. 13.
    Guha, R., Kumar, R., Raghavan, P., Tomkins, A.: Propagation of trust and distrust. In: Proceedings of the 13th International Conference on World Wide Web, New York, pp. 403–412 (2004)Google Scholar
  14. 14.
    Maheswaran, M., Tang, H.C., Ghunaim, A.: Towards a gravity-based trust model for social networking systems. In: Proceedings of the 27th International Conference on Distributed Computing Systems Workshops, p. 24 (2007)Google Scholar
  15. 15.
    Verbiest, N., Cornelis, C., Victor, P., Herrera-Viedma, E.: Trust and distrust aggregation enhanced with path length incorporation. J. Fuzzy Sets Syst. 202, 61–74 (2012)CrossRefGoogle Scholar
  16. 16.
    Liu, G., Wang, Y., Orgun, M.A.: Finding k optimal social trust paths for the selection of trustworthy service providers in complex social networks. J. IEEE Trans. Serv. Comput. 6, 41–48 (2011)Google Scholar
  17. 17.
    Adali, S., Escriva, R., Goldberg, M.K., Hayvanovych, M., Magdon-Ismail, M., Szymanski, B.K., Wallace, W.A., Williams, G.: Measuring behavioral trust in social networks. In: Proceedings of the IEEE International Conference on Intelligence and Security Informatics (ISI’10), Vancouver, BC, pp. 150–152 (2010)Google Scholar
  18. 18.
    Liu, H., Lim, E., Lauw, H.W., Le, M., Sun, A., Srivastava, J., Ae Kim, Y.: Predicting trusts among users of online communities: an epinions case study. In: Proceedings of the 9th ACM Conference on Electronic Commerce, Chicago, IL, pp. 310–319 (2008)Google Scholar
  19. 19.
    Yang, S., Smola, A.J., Long, B., Zha, H., Chang, Y.: Friend or frenemy? Predicting signed ties in social networks. In: Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval, Portland, OR, pp. 555–564 (2012)Google Scholar
  20. 20.
    Carminati, B., Ferrari, E., Viviani, M.: A multi-dimensional and event-based model for trust computation in the social web. In: International Conference on Social Informatics, pp.323–336. Springer, Lausanne (2012)Google Scholar
  21. 21.
    Li, M., Bonti, A.: T-OSN: a trust evaluation model in online social networks. In: 2011 IFIP 9th International Conference on Embedded and Ubiquitous Computing, Melbourne, pp. 469–473 (2011)Google Scholar
  22. 22.
    Squicciarini, A.C., Paci, F., Sundareswaran, S.: Prima: a comprehensive approach to privacy protection in social network sites. J. Ann. Telecommun. - annales des Télécommunications 69, 21–36 (2014)CrossRefGoogle Scholar
  23. 23.
    Fang, L., LeFevre, K.: Privacy wizards for social networking sites. In: Proceedings of the 19th International Conference on World Wide Web, Raleigh, NC, pp. 351–360 (2010)Google Scholar
  24. 24.
    Dokoohaki, N., Kaleli, C., Polat, H., Matskin, M.: Achieving optimal privacy in trust-aware social recommender systems. In: Proceedings of the Second International Conference on Social Informatics, Laxenburg, pp.62–79 (2010)Google Scholar
  25. 25.
    Konstan, J.A., Riedl, J.: Recommender systems: from algorithms to user experience. J. User Model. User-Adap. Inter. 22, 101–123 (2012)CrossRefGoogle Scholar
  26. 26.
    Bunea, R., Mokarizadeh, S., Dokoohaki, N., Matskin, M.: Exploiting dynamic privacy in socially regularized recommenders. In: Data Mining Workshops (ICDMW), 2012 IEEE 12th International Conference on Data Mining Workshops, Brussels, pp. 539–546 (2012)Google Scholar
  27. 27.
    Dwyer, C., Hiltz, S.R., Passerini, K.: Trust and privacy concern within social networking sites: a comparison of Facebook and Myspace. In: Proceedings of the 13th Americas Conference on Information Systems (AMCIS), Keystone, CO (2007)Google Scholar
  28. 28.
    Bakker, B.: The state of mind: reinforcement learning with recurrent neural networks. Ph.D. dissertation, Leiden University (2004)Google Scholar
  29. 29.
    Watkins, C., Dayan, P.: Technical note: Q-learning. J. Mach. Learn. 8, 279–292 (1992)CrossRefGoogle Scholar
  30. 30.
    Harmon, M.E., Baird, L.C.: Multi-player residual advantage learning with general function approximation. Technical report, Wright-Patterson Air Force Base (1996)Google Scholar
  31. 31.
    Riedmiller, M.: Neural fitted Q iteration first experiences with a data efficient neural reinforcement learning method. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) Machine Learning: ECML 2005. ECML 2005. Lecture Notes in Computer Science, vol. 3720, pp. 317–328. Springer, Berlin (2005)CrossRefGoogle Scholar
  32. 32.
    Akcora, C., Carminati, B., Ferrari E.: Network and profile based measures for user similarities on social networks. In: Information Reuse and Integration (IRI), IEEE International Conference on Information Reuse & Integration, pp. 292–298. IEEE, Las Vegas (2011)Google Scholar
  33. 33.
    Dokoohaki, N., Zikou, F.,Gillblad, D., Matskin, M.: Predicting swedish elections using Twitter: a case for stochastic link structure analysis. In: The 5th workshop on Social Network Analysis in Applications (SNAA2015), Collocated with IEEE/ACM ASONAM, Paris, pp. 1269–1276 (2015)Google Scholar
  34. 34.
    Steckelmacher, D., Vancx, P.: An empirical comparison of neural architectures for reinforcement learning in partially observable environments. In: 27th Benelux Conference on Artificial Intelligence, Hasselt (2015)Google Scholar
  35. 35.
    Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. J. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRefGoogle Scholar
  36. 36.
    Singla, P., Richardson, M.: Yes, there is a correlation: - from social networks to personal behavior on the web. In: Proceedings of the 17th International Conference on World Wide Web, Beijing, pp. 655–664 (2008)Google Scholar
  37. 37.
    Anagnostopoulos, A., Kumar, R., Mahdian, M.: Influence and correlation in social networks. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, pp. 7–15 (2008)Google Scholar
  38. 38.
    Zafarani, R., Liu, H.: Evaluation without ground truth in social media. Commun. ACM 58(6), 54–60 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Shatha Jaradat
    • 1
    Email author
  • Nima Dokoohaki
    • 1
  • Mihhail Matskin
    • 1
  • Elena Ferrari
    • 2
  1. 1.KTH Royal Institute of TechnologyStockholmSweden
  2. 2.University of InsubriaVareseItaly

Personalised recommendations