eprintid: 2521
rev_number: 10
eprint_status: archive
userid: 361
dir: disk0/00/00/25/21
datestamp: 2017-06-16 03:35:48
lastmod: 2017-06-16 03:35:48
status_changed: 2017-06-16 03:35:48
type: conference_item
metadata_visibility: show
creators_name: Vuong, Thi Hong
creators_name: Tran, Van Hien
creators_name: Nguyen, Minh Duc
creators_name: Nguyen, Thi Cam Van
creators_name: Pham, Thanh Huyen
creators_name: Tran, Mai Vu
creators_id: hongvt_57@vnu.edu.vn
creators_id: duchell.uet.vnu@gmail.com
creators_id: vutm@vnu.edu.vn
title: Social-spam profile detection based on content classification and user behavior
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: Web-based social system enables new community-based opportunities for participants to engage, share and interact. The rapid growth of Facebook has triggered a dramatic increase in spam volume and sophistication. Spammers post their status or comment in Page to send spam content to their friends or other users in the network. In this paper, we consider the problem of detecting spam accounts on Facebook based on comment content and user social behavior. We will propose a hybrid approach using Maximum Entropy (Maxent) model for classifying user comments as either spam or non-spam. We carefully conducted an empirical evaluation for our model on a large collection of comments in Vietnamese Facebook Pages and achieved promising results with an average accuracy of more than 90%.
date: 2016
date_type: published
official_url: http://doi.org/10.1109/KSE.2016.7758064
id_number: doi:10.1109/KSE.2016.7758064
full_text_status: public
pres_type: paper
pagerange: 264-267
event_title: Knowledge and Systems Engineering (KSE)
event_dates: 2016
event_type: conference
refereed: TRUE
book_title: 2016 Eighth International Conference on Knowledge and Systems Engineering (KSE)
citation:   Vuong, Thi Hong and Tran, Van Hien and Nguyen, Minh Duc and Nguyen, Thi Cam Van and Pham, Thanh Huyen and Tran, Mai Vu  (2016) Social-spam profile detection based on content classification and user behavior.  In: Knowledge and Systems Engineering (KSE), 2016.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/2521/1/vuong2016.pdf