Opinion and topic diversity in the output sets can provide individual and societal benefits. If news aggregators relying on votes and links to select and subsets of the large quantity of news and opinion items generated each day simply select the most popular items may not yield as much diversity as is present in the overall pool of votes and links.

To help measure how well any given approach does at achieving these goals, we developed three diversity metrics that address different dimensions of diversity: inclusion/exclusion, nonalienation, and proportional representation (based on KL divergence).

To increase diversity in result sets chosen based on user votes (or things like votes), we developed the sidelines algorithm. This algorithm temporarily suppresses a voter’s preferences after a preferred item has been selected. In comparison to collections of the most popular items, from user votes on Digg.com and links from a panel of political blogs, the Sidelines algorithm increased inclusion while decreasing alienation. For the blog links, a set with known political preferences, we also found that Sidelines improved proportional representation.

Our approach differs and is complementary to work that selects for diversity or identifies bias based on classifying content (e.g. Park et al, NewsCube; ) or by classifying referring blogs or voters (e.g. Gamon et al, BLEWS). While Sidelines requires votes (or something like votes), it doesn’t require any information about content, voters, or long term voting histories. This is particularly useful for emerging topics and opinion groups, as well as for non-textual items.

The list of links is generated from link data from about 500 blogs and refreshed every 30 minutes. Some of the results will be news stories, some will be op-ed columns from major media services, others will be blog posts, and there are also some other assorted links.

At this early point in our work, the results tend to be more politically diverse than an aggregator such as Digg, but suffer from problems with redundancy (we aren’t clustering links about the same story yet). As our results get better, the set of links the gadget shows should improve.

Update 15 December: I twittered last week that I’ve added bias highlighting to the widget, but I should expand a bit on that here.

Inspired by Baio and Schachter’s coloring of political bias on Memeorandum, I’ve added a similar feature to the news aggregator widget. Links are colored according the average bias of the blogs linking to them. This is not always a good predictor of the item’s bias or whether it better supports a liberal or conservative view. Sometimes a conservative blogger writes a post to which more liberal bloggers than conservative bloggers, and in that case, the link will be colored blue.

If you don’t like the highlighting, you can turn it off in the settings.

When I first started looking at my friends’ Netflix lists, it felt a little creepy. The records of our cultural consumption (video rentals, library checkouts) have traditionally been protected by law. for all kinds of excellent reasons—tyrants, stalkers, mothers-in-law—so even though I’d been invited to look, my conscience kept telling me I’d crossed into sacred territory. I felt like an information-age window peeper, like I had dipped my toe into the shallow end of a pool whose deep end was Watergate. This feeling only intensified when many of my real-life friends refused to accept me as their Netflix friend. Though they’d talk to me all day about their DVD-watching habits—their three-month Buffy binges and methodical screenings of the entire Owen Wilson catalog—for some reason they wouldn’t let me see an actual list of the actual films they were actually renting.

This paragraph caught my attention. Like many people who find something interesting but are not actually knowledgeable about it, I will now proceed to climb on to my tiny digital soapbox and talk about it for a moment.

A few thoughts came to mind. Anderson’s initial reaction caused me to remember when I showed some colleagues last.fm this summer — they were first almost repelled by the idea that I and others would share our music history like that, but within a few minutes they started saying “show me that chart.”

Much like the Netflix’s Friends feature, last.fm profiles show a user’s actual behavior rather than a reported behavior. Compare this to what users list on Facebook or other profiles for their favorite music and movies. Those are representations users choose, and what people say they do is rarely exactly what they do.

I’m curious, then, if services like last.fm and Netflix friends will change how people express themselves in listing favorite music or movies. I used to think a little bit before filling in my favorite music or answering what track is currently stuck in my head. Music that I considered to be a guilty pleasure (generally music that is catchy but not necessarily of great critical value, c.f. some songs by Coldplay) would usually not make these lists. This all stopped one day when I noticed that my Facebook list of favorite music had grown a ways apart from my last.fm profile. This was partly by design — the same sort of decisions that people make when deciding what books to put on office or living room shelves — and partly because what I thought I listened to most wasn’t necessarily what I do listen to most. I decided to fix it by just copying over my last.fm reported top tracks.

My new method didn’t last very long. I started thinking that certain artists seemed to be missing, and quickly tack them back on to the end of the list. Sure, I’d rationalize it by saying “oh, she’s new,” or “well, they’ve only put out one album, so of course they get overwhelmed by more prolific artists.” The truth is, there was a discrepancy between what last.fm reported and what I wanted to list, and I felt a need to fix it.

Are tools that report our actual cultural consumption at odds with our ability to choose how we express ourselves? Does it matter?

I can’t say that I’m going anywhere with these thoughts (and I can say that I don’t know the first thing about self expression and identity), but I’ve been thinking about this on and off for a few days.