Paper Info
Title
The Good, the Bad and the Bait: Detecting and Characterizing Clickbait on YouTube
Abstract
The use of deceptive techniques in user-generated video portals is ubiquitous. Unscrupulous uploaders deliberately mislabel video descriptors aiming at increasing their views and subsequently their ad revenue. This problem, usually referred to as "clickbait," may severely undermine user experience. In this work, we study the clickbait problem on YouTube by collecting metadata for 206k videos. To address it, we devise a deep learning model based on variational autoencoders that supports the diverse modalities of data that videos include. The proposed model relies on a limited amount of manually labeled data to classify a large corpus of unlabeled data. Our evaluation indicates that the proposed model offers improved performance when compared to other conventional models. Our analysis of the collected data indicates that YouTube recommendation engine does not take into account clickbait. Thus, it is susceptible to recommending misleading videos to users.
Year
DOI
Venue
2018
10.1109/SPW.2018.00018
2018 IEEE Security and Privacy Workshops (SPW)
Keywords
Field
DocType
Clickbait,YouTube,Deep Learning
Modalities,Revenue,Entertainment industry,Metadata,Internet privacy,World Wide Web,User experience design,Computer science,Artificial intelligence,Labeled data,Deep learning,Form of the Good
Conference
ISBN
Citations 
PageRank 
978-1-5386-8277-7
2
0.35
References 
Authors
6
4
Name
Order
Citations
PageRank
Savvas Zannettou15913.57
Sotirios P. Chatzis2305.94
Kostantinos Papadamou322.72
Michael Sirivianos469641.25