Show simple item record

dc.contributor.authorAngelopoulou, Olga
dc.contributor.authorY, Shao
dc.contributor.authorMarcello, Trovati
dc.contributor.authorQ, Shi
dc.contributor.authorE, Asimakopoulou
dc.contributor.authorNik, Bessis
dc.date.accessioned2017-06-12T10:53:02Z
dc.date.available2017-06-12T10:53:02Z
dc.date.issued2017-01-01
dc.identifier.citationAngelopoulou , O , Y , S , Marcello , T , Q , S , E , A & Nik , B 2017 , ' A Hybrid Spam Detection Method Based on Unstructured Datasets ' , Soft Computing , vol. 21 , no. 1 , pp. 233-243 . https://doi.org/10.1007/s00500-015-1959-z
dc.identifier.issn1432-7643
dc.identifier.otherPURE: 11232867
dc.identifier.otherPURE UUID: cdb47293-84b3-4df5-9dc1-71e779a92272
dc.identifier.otherScopus: 85008517778
dc.identifier.urihttp://hdl.handle.net/2299/18317
dc.descriptionThis document is the accepted manuscript version of the following article: Shao, Y., Trovati, M., Shi, Q. et al. Soft Comput (2017) 21: 233. The final publication is available at Springer via http://dx.doi.org/10.1007/s00500-015-1959-z. © Springer-Verlag Berlin Heidelberg 2015.
dc.description.abstractThe identification of non-genuine or malicious messages poses a variety of challenges due to the continuous changes in the techniques utilised by cyber-criminals. In this article, we propose a hybrid detection method based on a combination of image and text spam recognition techniques. In particular, the former is based on sparse representation-based classification, which focuses on the global and local image features, and a dictionary learning technique to achieve a spam and a ham sub-dictionary. On the other hand, the textual analysis is based on semantic properties of documents to assess the level of maliciousness. More specifically, we are able to distinguish between meta-spam and real spam. Experimental results show the accuracy and potential of our approach.en
dc.format.extent11
dc.language.isoeng
dc.relation.ispartofSoft Computing
dc.subjectImage spam, Text spam, Semantic networks, Classication, Subclass Discriminant Analysis, Feature Selection, Sparse Representation
dc.titleA Hybrid Spam Detection Method Based on Unstructured Datasetsen
dc.contributor.institutionSchool of Computer Science
dc.contributor.institutionCentre for Computer Science and Informatics Research
dc.description.statusPeer reviewed
dc.date.embargoedUntil2018-01-01
rioxxterms.versionAM
rioxxterms.versionofrecordhttps://doi.org/10.1007/s00500-015-1959-z
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record