Facebook is one of the most popular Internet sites today. A key feature that arguably contributed to Facebook's unprecedented success is its application platform, which enables the development of third-party social-networking applications. Understanding how these applications are installed and used is important for the function and utility of web-based online social networks, e.g. to better engineer them and/or to design advertising campaigns. In this paper, we characterize the popularity and user reach of Facebook applications. We analyze application usage data gathered over a period of six months from Facebook and Adonomics - a Facebook analytics service. We also crawl publicly accessible Facebook user profiles and obtain per-user application installation statistics, for approximately 300K users and 13.6K applications. Our findings include that (i) the popularity of Facebook applications has a highly skewed distribution; (ii) although the total number of application installations increases with time, the average user activity decreases; and (iii) users with more applications installed are more likely to install new applications.
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.