You are here

Snurb's blog

How Facebook Uses Computational Processes to Police Its Ads

The final Web Science 2016 keynote for today is by Daniel Olmedilla, whose work at Facebook is to police the ads being posted on the site. Ads are the only part of Facebook where inherently unsolicited content is pushed to users, so the quality of those ads is crucial – users will want relevant and engaging content, while advertisers need to see a return on investment. Facebook itself must ensure that its business remains scalable and sustainable.

Key problem categories are legally prohibited content (e.g. ads for illegal drugs); shocking and scary content; sexually suggestive material; violent and confronting content; offensive before-and-after images; ads with inappropriate language; and images containing a large amount of text.

Explaining Viewing and Sharing Dynamics for YouTube Videos

Finally for this session at Web Science 2016 we move to Sebastian Stommel, who begins by considering what we mean by Web science in the first place. He suggests that 'big data' serve as a macroscope: a new way of looking at things at scale, and an opportunity to create generative models to explain digital traces.

Simulating Heterogeneous-Intent Cascades

The next speaker at Web Science 2016 is Onur Varol, who points out the wide variety of purposes for which people use social media, and notes that we change our online persona and usage styles according to different communicative contexts. Can we match language style and user intent, then?

The Influence of Students' Social Networks on Group Participation

The next speaker at Web Science 2016 is Jenna Mittelmeier, whose focus is on cross-cultural collaboration. Group work has always been difficult, and the majority of online contributions are from a small subset of all users; this free riding by non-participants is especially problematic in educational settings that require all users to participate equally.

Predicting Twitter-Based Information Cascades

The next session at Web Science 2016 starts with a paper by Jure Leskovec on information cascades. Such cascades emerge as users of social media platforms (re)share content through their networks, and the prediction of such processes is traditionally very difficult.

Networks of Caucasian User Groups on VKontakte

The final speaker in this Web Science 2016 session is Daniel Alexandrov, whose interest is in the use of social networking platforms in politics across the Caucasus region. This is a diverse and politically tense region, with several intractable political conflicts.

Internet Technologies in Party Decision-Making Processes in Germany

The third speaker in this session at Web Science 2016 is Gefion Thuermer, whose interest is in decision-making processes within political parties. Such processes must be equal and inclusive, which may be a problem the more Internet-based communication tools play a role.

A First Look at the Political Uses of Quote Retweets

Next up at Web Science 2016 is Yelena Mejova, who presents a paper on the new 'quote retweet' feature that Twitter introduced in April 2015. This form of retweeting includes the retweeted tweet as a URL in the retweet, and can be used for somewhat different purposes from other forms of retweeting: while button retweets may imply an endorsement of the original message, the substantial space for including the retweeter's views in a quote retweet might be used for more critical engagement with the quoted material, for instance.

The Influence of Funding on Chilean Legislative Processes

I'm now in the "Politics and the Web" session at Web Science 2016, and we're starting with a paper by Pablo Loyola, whose focus is on politics in Chile. This work is interested in the collective decision-making processes involved in constructing new legislation, and builds on the voting behaviours of MPs and on drafts-in-progress of new bills. Are these processes influenced by the funding that MPs receive from corporate interests?

Modelling Web Advertising Clickthroughs

Next at Web Science 2016 is Sergej Sizov, who focusses on the economic value of Web advertising. This is surprisingly difficult to calculate, and Sergej begins with the hypothetical example of a small Web advertising campaign. We may make a range of assumptions about click-through and purchase rates, but variance matters: in a substantial number of cases, campaigns may generate no profit whatsoever.


Subscribe to RSS - Snurb's blog