Abstract
We address the problem of modeling trust network evolution through social communications among users in a social media site. In particular, we focus on a social trust-link created between two users having mediating-objects such as mediating-users and mediating-items, and analyze the time-decay effects of mediating-objects on social trust-link creation. To this end, we first introduce the basic TCM model that can be regarded as a conventional link prediction method based on mediating-objects, and propose the TCM model with time-decay by incorporating an appropriate time-decay function into it. We present an efficient learning method of the proposed model, and apply it to an analysis of social trust-link creation for two real item-review sites. We show that the proposed model significantly outperforms the basic TCM model in terms of prediction performance, and clarify several properties of user behavior for social trust-link creation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
We also evaluated its prediction capability in terms of the area under the ROC curve (AUC) for trust-link prediction, and confirmed that the results for AUC were similar to those for PLR.
References
Barabási, A.L.: The origin of bursts and heavy tails in human dynamics. Nature 435, 207–211 (2005)
Barbieri, N., Bonchi, F., Manco, G.: Who to follow and why: link prediction with explanations. In: Proceedings of KDD 2014, pp. 1266–1275 (2014)
Chen, W., Lakshmanan, L., Castillo, C.: Information and influence propagation in social networks. Synth. Lect. Data Manag. 5, 1–177 (2013)
Crandall, D., Cosley, D., Huttenlocher, D., Kleinberg, J., Suri, S.: Feedback effects between similarity and social influence in online communities. In: Proceedings of KDD 2008, pp. 160–168 (2008)
Gomez-Rodriguez, M., Leskovec, J., Krause, A.: Inferring networks of diffusion and influence. In: Proceedings of KDD 2010, pp. 1019–1028 (2010)
Guha, R., Kumar, R., Raghavan, P., Tomkins, A.: Propagation of trust and distrust. In: Proceedings of WWW 2004, pp. 403–412 (2004)
Kempe, D., Kleinberg, J., Tardos, E.: Maximizing the spread of influence through a social network. In: Proceedings of KDD 2003, pp. 137–146 (2003)
Kimura, M., Saito, K., Nakano, R., Motoda, H.: Extracting influential nodes on a social network for information diffusion. Data Min. Knowl. Disc. 20, 70–97 (2010)
Koren, Y.: Collaborative filtering with temporal dynamics. In: Proceedings of KDD 2009, pp. 447–456 (2009)
Leskovec, J., Backstrom, I., Kumar, K., Tomkins, A.: Microscopic evolution of social networks. In: Proceedings of KDD 2008, pp. 462–470 (2008)
Leskovec, J., Huttenlocher, D., Kleinberg, J.: Predicting positive and negative links in online social networks. In: Proceedings of WWW 2010, pp. 641–650 (2010)
Liben-Nowell, D., Kleinberg, J.: The link-prediction problem for social networks. J. Am. Soc. Inf. Sci. Technol. 58, 1019–1031 (2007)
Liu, H., Lim, E., Lauw, H., Le, M., Sun, A., Srivastava, J., Kim, Y.: Predicting trusts among users of online communities: an epinion case study. In: Proceedings of EC 2008, pp. 310–319 (2008)
Nguyen, V., Lim, E., Jiang, J., Sun, A.: To trust or not to trust? Predicting online trusts using trust antecedent framework. In: Proceedings of ICDM 2009, pp. 896–901 (2009)
Oliveira, J.G., Barabási, A.L.: Dawin and Einstein correspondence patterns. Nature 437, 1251 (2005)
Tang, J., Chang, S., Aggarwal, C., Liu, F.: Negative link prediction in social media. In: Proceedings of WSDM 2015, pp. 87–96 (2015)
Tang, J., Gao, H., Hu, X., Liu, H.: Exploiting homophily effect for trust prediction. In: Proceedings of WSDM 2013, pp. 53–62 (2013)
Tang, J., Gao, H., Liu, H., Sarma, A.D.: eTrust: understanding trust evolution in an online world. In: Proceedings of KDD 2012, pp. 253–261 (2012)
Weng, L., Ratkiewicz, J., Perra, N., Goncalves, B., Castillo, C., Bonchi, F., Schifanella, R., Menczer, F., Flammini, A.: The role of information diffusion in the evolution of social networks. In: Proceedings of KDD 2013, pp. 356–364 (2013)
Zhang, J., Yu, P.S., Zhou, Z.: Meta-path based multi-network collective link prediction. In: Proceedings of KDD 2014, pp. 1286–1295 (2014)
Acknowledgements
This work was partly supported by JSPS Grant-in-Aid for Scientific Research (C) (No. 26330352), Japan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Learning Algorithm
Appendix: Learning Algorithm
We consider learning the TCM model with time-decay from the observed data \(D_*\). We derive an iterative algorithm for estimating the values of and by maximizing the objective function (see Eq. (5)). Let and be the current estimates of and , respectively. By Jensen’s inequality, we have
for any \((u,v,t) \in D_*\), where
for \(k = 1, \dots , K\) and \(\alpha \in \mathcal{M}_{k,t} (u,v)\). Note that \( \sum _{k=1}^K \sum _{\alpha \in \mathcal{M}^k_{u,v,t}} {\bar{q}}_{k, \alpha } (u,v,t) \ = \ 1. \) Thus, by Eqs. (2), (5) and (7), we have where
Here, for \((u,v,t) \in D_*\), \(w \in V_t(u) \cup \{v \}\), \(k = 1, \dots , K\) and \(\alpha \in \mathcal{M}_{k,t} (u,w)\), \(g_{\alpha } (u, w, t)\) is defined as follows: \(g_{\alpha } (u, w, t) = t - \tau _\alpha (u, w)\) if \(f(s; \lambda _k) = f_{ex} (s; \lambda _k)\) and \(g_{\alpha } (u, w, t) = \log (t - \tau _\alpha (u, w))\) if \(f(s; \lambda _k) = f_{pl} (s; \lambda _k)\) (see Eqs. (3) and (4)). Also, const indicates such a constant term that does not depend on and . Note that . Thus, we consider increasing the value of by maximizing . We define by
for \((u,v,t) \in D\), \(k = 1, \dots , K\) and \(\alpha \in \mathcal{M}_{k,t} (u,v)\). From Eqs.(9) and (10), we have
for \(k = 1, \dots , K\). Also, from Eqs.(10), (11) and (12), we have
for \(k, \ell = 1, \dots , K\), where \(\delta _{k, \ell }\) is the Kronecker delta. We consider a quadratic form
for , , where \(\langle z_{k, \alpha } (w) \rangle \) stands for
for \((u,v,t) \in D_*\), \(k = 1, \dots , K\), \(w \in V_t (u)\) and \(\alpha \in \mathcal{M}_{k,t} (u,w)\). From Eq. (10), note that
Thus, by Eq. (16), we have
for , . This implies that the Hessian matrix of function is negative definite. Hence, we can find the point at which function attains the maximum by solving , for \(k = 1, \dots , K\). We employ Newton’s method and obtain an update formula for and (see Eqs. (11), (12), (13), (14) and (15)).
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Takahashi, H., Kimura, M. (2017). Analyzing Time-Decay Effects of Mediating-Objects in Creating Trust-Links. In: Appice, A., Ceci, M., Loglisci, C., Masciari, E., Raś, Z. (eds) New Frontiers in Mining Complex Patterns. NFMCP 2016. Lecture Notes in Computer Science(), vol 10312. Springer, Cham. https://doi.org/10.1007/978-3-319-61461-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-61461-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61460-1
Online ISBN: 978-3-319-61461-8
eBook Packages: Computer ScienceComputer Science (R0)