Discovery of the Content and Engagement with the Content

by   Pushkal Agarwal, et al.

In the second half of the 20th century, Parliament allowed broadcasters to transmit radio and eventually television coverage of debates and meetings of select committees. More recently, in an effort to further improve transparency and citizen engagement, the UK Parliament started publishing videos of these debates and meetings itself, and tweeting details of debates as they happened. In this paper, we attempt to characterise how people engage with video data of Parliamentary debates by using more than two years of Google Analytics data around these videos. We analyse the patterns of engagement - how do they land on a particular video? How do they hear about this video, i.e., what is the (HTTP) referrer website that led to the user clicking on the video? Once a user lands on a video, how do they engage with it? For how long is the video played? What is the next destination? etc. Answering these questions is an important first step towards understanding why and how people use Parliamentary videos, and therefore, how the video delivery platform should be adapted and personalised for the needs of the citizens of the country. Taking inspiration from An, Kwak, and Jansen (2017), we employ Non-Negative Matrix Factorization (NMF) (Lee and Seung, 1999) on the video views matrix to identify different archetypes of users, and identify archetypes. A deeper examination of the archetypes we find reveals that they are primarily distinguished by how they land on the video page: Search (i.e., through a search engine), Referral (i.e., from other Parliamentary websites), Direct (i.e., through a direct link, which is embedded on another website), Social (i.e., through a social platform such as Facebook or Twitter) and Others.


page 1

page 2

page 3


Characterizing and Predicting Supply-side Engagement on Crowd-contributed Video Sharing Platforms

Video sharing and entertainment websites have rapidly grown in popularit...

Edvertisements: Adding Microlearning to Social News Feeds and Websites

Many long-term goals, such as learning a language, require people to reg...

IVSS Integration of Color Feature Extraction Techniques for Intelligent Video Search Systems

As large amount of visual Information is available on web in form of ima...

Dissecting the Workload of a Major Adult Video Portal

Adult content constitutes a major source of Internet traffic. As with ma...

Twitter DM Videos Are Accessible to Unauthenticated Users

Videos shared in Twitter Direct Messages (DMs) have opaque URLs based on...

Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos

Despite the rapid progress of the techniques for image classification, v...

Social Surplus Maximization in Sponsored Search Auctions Requires Communication

We show that computing the optimal social surplus requires Ω(mn) bits of...

Please sign up or login with your details

Forgot password? Click here to reset