報(bào)告題目：Social Spam Detection and Information Credibility Assessment
報(bào)告題目：Social Spam Detection and Information Credibility Assessment
主講嘉賓：王宇博士 澳大利亞迪肯大學(xué)
邀請(qǐng)人：張鵬老師
時(shí)間：2017年3月24日16:00-17:00
地點(diǎn)：深圳大學(xué)科技樓1504
內(nèi)容簡(jiǎn)介：
Being an important source for real-time information dissemination in recent years, Social Media Platforms like Twitter and Weibo have becomea prime target for spammersinevitably. A series of incidents showed that social spam and false information published on social medianot only affects user experience, but also poses significant threats of damagesfar beyond the social media platformsthemselves. In this talk, we will go through some of our recent works on social spam detection and information credibility assessment. In particular, we will first introduce a Twitter spam detection scheme that makes use of machine learning techniques and some simple statistical features of tweets. Secondly, we will discuss how we tackle two critical challenges of machine learning based Twitter spam detection, which are the "Twitter Spam Drift" problem and the class imbalance problem. Thirdly, we will introduce a novel microblogging information credibility assessment scheme that is based on gatekeeping behaviour analysis. In this scheme, we consider that the users are the gatekeepers of their own media portal on microblogging sites, as they decide which information is filtered for dissemination to their followers. We find that truthful posts and false rumours exhibit distinguishable patterns in terms of which gatekeepers forward them and what the gatekeepers comment on them. Based on this finding, we propose to assess the information credibility of popular microblog posts with Hidden Markov Models (HMMs) of gatekeeping behaviour.
嘉賓簡(jiǎn)介：
王宇， 2013年在澳大利亞迪肯大學(xué)網(wǎng)絡(luò)安全與計(jì)算實(shí)驗(yàn)室獲得計(jì)算機(jī)科學(xué)博士，目前留校從事研究工作。主要的研究領(lǐng)域包括網(wǎng)絡(luò)流量建模與分類、社交網(wǎng)絡(luò)安全、網(wǎng)絡(luò)和系統(tǒng)安全、機(jī)器學(xué)習(xí)等方面。
