Prior work established the benefits of server-recorded user engagement measures (e.g. clickthrough rates) for improving the results of search engines and recommendation systems. Client-side measures of post-click behavior received relatively little attention despite the fact that publishers have now the ability to measure how millions of people interact with their content at a fine resolution using client-side logging. In this study, we examine patterns of user engagement in a large, client-side log dataset of over 7.7 million page views (including both mobile and non-mobile devices) of 66,821 news articles from seven popular news publishers. For each page view we use three summary statistics: dwell time, the furthest position the user reached on the page, and the amount of interaction with the page through any form of input (touch, mouse move, etc.). We show that simple transformations on these summary statistics reveal six prototypical modes of reading that range from scanning to extensive reading and persist across sites. Furthermore, we develop a novel measure of information gain in text to capture the development of ideas within the body of articles and investigate how information gain relates to the engagement with articles. Finally, we show that our new measure of information gain is particularly useful for predicting reading of news articles before publication, and that the measure captures unique information not available otherwise.
Bookmarked to read as result of reading .
[.pdf] copy available on author’s site.
New metrics specifically for news articles.
I love that there’s research1 going on in this area and it portends some potentially great things for reading, but the devil’s advocate in me can also see a lot of adtech people salivating over the potential dark patterns lurking in such research. I can almost guarantee that Facebook is salivating over this, though to be honest, they’ve really pioneered the field haven’t they, just in a much smaller area of use. Of course I’m also curious if they did or are planning any research in how people read content on social media?
I wonder what it would look/feel like to take each of these modalities and apply them individually for long periods of time to everything one read? Or to use them in rotation regardless of the subject being read? Or other permutations? I suppose in general I like to read how I like to read, but now I’m going to be more conscious of what and how I’m doing it all.
Grinberg N. Identifying Modes of User Engagement with Online News and Their Relationship to Information Gain in Text. WWW ’18 Proceedings of the 2018 World Wide Web Conference. https://dl.acm.org/citation.cfm?id=3186180
. Published April 23, 2018. Accessed April 27, 2018.
Some thoughts on creating conference lists, live tweeting and archiving events.
Live Tweeting and Twitter Lists
While attending the upcoming conference Dodging the Memory Hole 2016: Saving Online News later this week, I’ll make an attempt to live Tweet as much as possible. (If you’re following me on Twitter on Thursday and Friday and find me too noisy, try using QuietTime.xyz to mute me on Twitter temporarily.) I’ll be using Kevin Marks‘ excellent Noter Live web app to both send out the tweets as well as to store and archive them here on this site thereafter (kind of like my own version of Storify.)
In getting ramped up to live Tweet it, it helps significantly to have a pre-existing list of attendees (and remote participants) talking about #DtMH2016 on Twitter, so I started creating a Twitter list by hand. I realized that it would be nice to have a little bot to catch others as the week progresses. Ever lazy, I turned to IFTTT.com to see if something already existed, and sure enough there’s a Twitter search with a trigger that will allow one to add people who mention a particular hashtag to a Twitter list automatically.
Here’s the resultant list, which should grow as the event unfolds throughout the week:
🔖 People on Twitter talking about #DtMH2016
Feel free to follow or subscribe to the list as necessary. Hopefully this will make attending the conference more fruitful for those there live as well as remote.
Not on the list? Just tweet a (non-private) message with the conference hashtag: #DTMH2016 and you should be added to the list shortly.
Lazy like me? Click the bird to tweet: “I’m attending #DtMH2016 @rji | Dodging the Memory Hole 2016: Saving Online News http://ctt.ec/5RKt2+”
IFTTT Recipe for Creating Twitter Lists of Conference Attendees
For those interested in creating their own Twitter lists for future conferences (and honestly the hosts of all conferences should do this as they set up their conference hashtag and announce the conference), below is a link to the ifttt.com recipe I created for this, but which can be modified for use by others.
Naturally, it would also be nice if, as people registered for conferences, they were asked for their Twitter handles and websites so that the information could be used to create such online lists to help create longer lasting relationships both during the event and afterwards as well. (Naturally providing these details should be optional so that people who wish to maintain their privacy could do so.)