Like many users before me, I stared at my rat’s nest of Delicious bookmark tags one day and realized the futility of tagging all these links with words and phrases I’d never actually recall. At that point, I gave up on taxonomy and tried a new tactic: filing bookmarks into only two folders: Beautiful and Useful.
The beautiful examples were inspiring, artistic, and aesthetically gorgeous. The useful examples offered new functionalities, potential savings of time, and clever solutions.
This dichotomy approach failed, too, as I realized that there’s a sometimes complicated interplay between beauty and utility.
Gmail routinely sends email updates from social organizations to the spam folder. For the organizations I like, I’ll occasionally go in and rescue them by pressing the “Not spam” button. It turns out that this user feedback does actually help improve that organization’s overall deliverability. I wrote up some tips on staying out of the spam folder for an NOI Tip of the Day.
I’ve graduated, but that doesn’t make it any less exciting to see my first academic paper accepted for publication. Thanks to Carlos Castillo, Mohammed El-Haddad, and Jürgen Pfeffer for driving this paper, and for inviting me to collaborate. Take a look. Al Jazeera English provided us with some great data.
This paper presents a study of the life cycle of news articles posted online. We describe the interplay between website visitation patterns and social media reactions to the news content. We show that we can use this hybrid observation method to characterize distinct classes of articles. We also find that social media reactions can be used to predict future visitation patterns early and accurately.
We validate our methods using qualitative analysis as well as quantitative analysis on data from a large international news network, for a set of articles generating more than 3,000,000 visits and 200,000 social media reactions. We show that it is possible to model accurately the overall traffic articles will ultimately receive by observing the first ten to twenty minutes of social media reactions. Achieving the same prediction accuracy with visits alone would require to wait for three hours of data. We also describe significant improvements on the accuracy of the early prediction of shelf-life for news stories.
If you use the Chrome browser, you may have noticed that when you begin typing in the address bar, Google’s Autocompleteprediction service guesses where you might be heading to save you keystrokes. If you have Web History enabled, those guesses aren’t just popular websites, but rather the sites you’re historically most likely to visit.
I realized that this list of sites actually end up serving as a sort of internet time capsule of the last ten weeks (the amount of time the browser history spans). So, here are my Internet ABCs of my last three months of grad school at the Media Lab. Click any of the images to go to the site.