Abstract
Social community structure is widely utilized in the study of modeling disease propagation, information dissemination and etc. Therefore, detecting the social community structure is one of the most significant tasks for majority of existing works focusing on the online social network. Traditionally, they aim at predicting the existence of social relationships based on cyber interactions (e.g. online conversation) among users. However, the strength information of social relationships is not captured which is as important as the topology information of social communities. Furthermore, physical interactions (e.g., face to face conversation), which have the potential to reflect more realistic state of social relationships than cyber ones, are not taken into account in social relationship measurement. In order to measure the strength of social relationships, in this paper, we propose a hierarchical entropy-based relationship measurement approach (HERMA). HERMA is able to measure the strength of social relationships among users based on their physical interactions which could be inferred by analyzing co-location records extracted from their trajectories. To model users’ co-location records in HERMA, a hierarchical region structure is designed. Moreover, two novel concepts called user entropy and area entropy adopted by HERMA are proposed to quantify the activeness degree of an user and the openness degree of an area respectively. Finally, to validate the effectiveness of HERMA, simulations are conducted of which the results show that HERMA outperforms the baselines by leveraging the highest average accuracy on the measurement of social relationships.
Similar content being viewed by others
Notes
In the simulation, the balance splitting strategy is employed for constructing the hierarchical region structure. For example, under the setting of M=256 which means there are 256 un-overlapped unit grids in the simulation map, there is only one area consisting of 256 unit grids on the top layer. And on the layer under the top layer, there will be two un-overlapped areas while each of them is consisting of 128 unit grids. Therefore, when M = 256, it is possible to construct a hierarchical region structure with at most nine layers by employing the balance splitting strategy.
For the value of T, there may be the deviation from our real life in which the duration of many valid co-location records is much longer than several seconds. In our simulation, T is set to several seconds only for the purpose of speeding up the simulation.
References
Backstrom L, Huttenlocher D, Kleinberg J, Lan X (2006) Group formation in large social networks: membership, growth, and evolution. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, New York, NY, USA, KDD ’06, pp 44–54
Cha M, Mislove A, Gummadi KP (2009) A measurement-driven analysis of information propagation in the flickr social network. In: Proceedings of the 18th international conference on World wide web, ACM, New York, NY, USA, WWW ’09, pp 721–730
Crandall D, Cosley D, Huttenlocher D, Kleinberg J, Suri S (2008) Feedback effects between similarity and social influence in online communities. In: Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, New York, NY, USA, KDD ’08, pp 160–168
Crandall DJ, Backstrom L, Cosley D, Suri S, Huttenlocher D, Kleinberg J (2010) Inferring social ties from geographic coincidences. Proc Natl Acad Sci USA 107(52):22436–22441
De Choudhury M, Mason WA, Hofman JM, Watts DJ (2010) Inferring relevant social networks from interpersonal communication. In: Proceedings of the 19th international conference on World wide web, ACM, New York, NY, USA, WWW ’10, pp 301–310
Eagle N, Pentland A, Lazer D (2009) Inferring social network structure using mobile phone data. Proc Natl Acad Sci USA 106(36):15274–15278
Guo B, Zhang D, Yang D (2011) "read" more from business cards: Toward a smart social contact management system. In: Proceedings of the 2011 IEEE/WIC/ACM International conference on web intelligence, IEEE Computer Society, Washington, DC, USA, pp 384–387
Leskovec J, Huttenlocher D, Kleinberg J (2010) Predicting positive and negative links in online social networks. In: Proceedings of the 19th international conference on World wide web, ACM, New York, NY, USA, WWW ’10, pp 641–650
Miklas AG, Gollu KK, Chan KKW, Saroiu S, Gummadi KP, De Lara E (2007) Exploiting social interactions in mobile systems. In: Proceedings of the 9th international conference on Ubiquitous computing, Springer-Verlag, Berlin, Heidelberg, UbiComp ’07, pp 409–428
Ricotta C, Szeidl L (2006) Towards a unifying approach to diversity measures: Bridging the gap between the shannon entropy and rao’s quadratic index. Theor Popul Biol 70(3):237–243
Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27:379–423–623–656
Singla P, Richardson M (2008) 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, ACM, New York, NY, USA, WWW ’08, pp 655–664
Xiang R, Neville J, Rogati M (2010) Modeling relationship strength in online social networks. In: Proceedings of the 19th international conference on World wide web, ACM, New York, NY, USA, WWW ’10, pp 981–990
Zhang D, Guo B, Yu Z (2011) The emergence of social and community intelligence. IEEE Comput Archit Lett 44(7):21–28
Zhang D, Zhou J, Guo M, Cao J, Li T (2011) TASA: tag-free activity sensing using RFID tag arrays. IEEE Trans Parallel Distrib Syst 22(4):558–570
Zheng Y, Li Q, Chen Y, Xie X, Ma WY (2008) Understanding mobility based on GPS data. In: Proceedings of the 10th international conference on Ubiquitous computing, ACM, New York, NY, USA, UbiComp ’08, pp 312–321
Acknowledgments
This work is supported by Nokias Collaboration Grant under grant No. H-ZG19. The authors would like to thank Junjun Kong, Tao Li, Wenwen Cheng and all reviewers for their helpful suggestions and comments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ma, C., Cao, J., Yang, L. et al. Effective social relationship measurement based on user trajectory analysis. J Ambient Intell Human Comput 5, 39–50 (2014). https://doi.org/10.1007/s12652-012-0120-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-012-0120-4