Re-reading my post from last month, Thoughts On Automated Recommendation Services for Libraries, I realize that I’m somewhat wrong about the role of locality in automated recommendation systems. Amazon and Netflix can (and I think they do) integrate user location data in their recommendation algorithm. They can skew results based on strong trends that appear among proximate user groups.
I’m also somewhat wrong about how recommendations work in BiblioCommons—ratings and reviews for individual titles are aggregated from multiple libraries, as well as user-created reading lists. Reviews from local library staff are prioritized over others, but I don’t know if local library user-created reading lists are prioritized. Regardless, these are individually curated pieces of content, these sections aren’t automated in the same way that Netflix is. This content is related to an individual item in the catalog and doesn’t generate lists of recommendations as one typically expects from Readers’ Advisory services.
The “Similar Titles” type of content in the sidebar in BiblioCommons is what I think of when I look for reading recommendations, and this content is also the most directly analogous to Netflix / Amazon. However, this content doesn’t get generated by BiblioCommons at all—these titles come from third party services like NoveList.
So locality can be a meaningful factor in automated recommendation systems—such systems are smart enough to recognize that local trends are important, even if they aren’t yet intelligent enough to know what local trends mean.
But libraries still don’t have enough data to make such algorithms work. We still rely on curation and the personal touch to create real value for our patrons.
Librarians talk off and on about the need for us to offer Netflix / Amazon-style automated recommendations for our patrons. It seems almost self-evident that this is something patrons have come to expect. But there’s a self-evident question about this that we must ask:
Have patrons actually told us that they want this type of service from a library?
Or do we just assume that they want this?
A library doesn’t fulfill the same role in people’s lives that Netflix does, or that Amazon does. Our patrons don’t necessarily expect the same service models from us. We may be holding ourselves accountable to a false comparison here. This is a prime example of the need for us to base decisions on verifiable user data.
Continue reading “Thoughts On Automated Recommendation Services for Libraries”
Earlier this month, I explored some stats about reading in America as a jumping-off point to emphasize my desire to be more aware of how different the world can be for different people.
What I didn’t talk about was how much those stats scared me. I understand that as an avid life-long reader my perspective is biased, but I believe that reading is one of the most important things a person can do to grow, to realize their best self, and to keep their mind healthy.
Last week, the Pew Research Center released a report (PDF) which showed that nearly a quarter of American adults haven’t read a single book in the past year in any format. That’s nearly triple the percentage from 1978. For me, this is terrifying.
So I was quite happy when I came across this article through Stephen Abram’s blog:
The Decline of the American Book Lover—And why the downturn might be over. by Jordan Weissmann (posted on The Atlantic on January 21, 2014)
I hope the author is correct in this reading of the data. I hope the state of reading in America isn’t so dire.
And let’s look at this number from the other way ‘round—just over three quarters of adult Americans still read, and most pretty regularly. That’s not nothing.
There’s so much wisdom in this post, I had to share it here:
The Mobile Challenge | The User Experience by Aaron Schmidt (posted by Library Journal on May 6, 2013)
At my library, we’re currently working on a project in conjunction with several other regional knowledge institutions to put online our full collection of historical documents regarding the Civil War in Missouri and Kansas. One piece of functionality we’re creating is a way to visually represent the relationships between people, places, and things within this pool of data. These visualizations are based on a relationship database that we constructed, using a basic semantic structure: “Object A [relationship] Object B” and we can verify this relationship with “Document X”. Thus, for example:
Iskabibble Jones is married to Bridgette Jones and we know this because of information contained in Bridgette’s letter dated …
Only, instead of statements, we represent this all graphically with links to images and documents. It’s a pretty nifty function!
The way we’re building the database for this relationship visualization tool is representative of how online data gets handled in general. It illustrates the fundamental paradigm that has governed computer development from the beginning – and, indeed, the development of mechanized data handling even before the advent of computers.
Continue reading “Data Handling in Electronic Systems – Inspiration for a Paradigm Reassessment”
In the world of social web, the idea that page views and visit lengths on a library’s core website are still relevant metrics for measuring patron engagement is outmoded. Yes, there are some pieces of content that require a visitor to spend time on your main site. But increasingly, more of a library’s relevant content is available to people through multiple avenues of engagement, across multiple accounts on multiple platforms – Facebook, Twitter, Flickr, YouTube, etc.
Many libraries, though, still determine their online strategy using page views and visit lengths on their core site as their main data input. There’s still substantial resistance to sending people away from the core library website. This is understandable – we librarians have a hang-up about all the unevaluated and uncurated data “in the wild” out there on the internet; what we present on our library website is known to be high quality and our impulse is to keep people there. Linking visitors to social media sites requires us to give up some control over the quality of their experience… and we don’t like doing that.
Continue reading “Social Web Engagement Metrics”
In library school, we spent a lot of time discussing the nature of data and information, debating the differences and relationships between them. This may seem frivolous to some, but remember that the essence of librarianship is to curate and provide access to quality information in a community. While there are many competing definitions of information, most people are willing to accept some version of this:
Information is data put into context.
It’s the “put into context” part that’s important here – raw data doesn’t really tell us anything in-and-of itself; it must be placed into meaningful context in order to be useful.
Context is everything.
Continue reading “Context Matters!”