A combined deep-learning and transfer-learning approach for supporting social influence prediction

Simple item page
dc.contributor.authorCuzzocrea, Alfredo
dc.contributor.authorLeung, Carson K.
dc.contributor.authorDeng, Deyu
dc.contributor.authorMai, Jiaxing Jason
dc.contributor.authorJiang, Fan
dc.contributor.authorFadda, Edoardo
dc.date.accessioned2021-02-16T22:42:16Z
dc.date.available2021-02-16T22:42:16Z
dc.date.issued2020
dc.date.submitted2021-02-03T05:23:30Zen_US
dc.description.abstractSocial influence is a phenomenon describing the spread of opinions across the population. Nowadays, social influence analysis (SIA) has a great impact. For example, viral marketing and online content recommendation are applications of SIA. Hand-crafted features, as well as domain expert knowledge, are usually required in convention social influence analysis, but they incur high costs and are not scalable. Deep learning based approaches overcome these issues. For instance, a recently used approach learned latent features of users to predict social influence. In this paper, a teleport probability from the page rank domain is integrated into the graph convolution network model for further enhance the performance of such an approach. In addition, a combined personalized propagation of neural predictions (CPPNP) algorithm leads to an impressive prediction accuracy when comparing with existing methods. Evaluation results on three well-known datasets reveal that optimizing the teleport probability enhances the performance of CPPNP. Such a combined deep-learning and transfer-learning approach well supports the social influence predictionen_US
dc.description.sponsorshipNatural Sciences and Engineering Research Council of Canada (NSERC); University of Manitobaen_US
dc.identifier.citationA. Cuzzocrea, C.K. Leung, D. Deng, J.J. Mai, F. Jiang, E. Fadda. A combined deep-learning and transfer-learning approach for supporting social influence prediction. Procedia Computer Science, 177 (2020), pp. 170-177.en_US
dc.identifier.doi10.1016/j.procs.2020.10.025
dc.identifier.urihttp://hdl.handle.net/1993/35324
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.rightsopen accessen_US
dc.subjectEmerging systemsen_US
dc.subjectDeep learningen_US
dc.subjectTransfer learningen_US
dc.subjectMachine learningen_US
dc.subjectSocial networksen_US
dc.subjectSocial network analysisen_US
dc.subjectPredictive analyticsen_US
dc.titleA combined deep-learning and transfer-learning approach for supporting social influence predictionen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Cuzzocrea_JProcCS_177_EUSPN_2020.pdf
Size:
760.23 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.24 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
University of Manitoba Scholarship
Faculty of Science Scholarly Works