syslog
14Sep/120

RecSys 2012: few things i remember

Posted by Daniele Quercia

random notes & thoughts

Workshops

From the Sunday's workshops, I remember this paper "Dating Sites and the Split-complex Numbers" It uses split-complex numbers to represent dating preferences in an elegant way. It seems promising. I'd be great to connect this work on previous papers on trust and distrust and on structural balance theories... I also heard that two presentations were quite good: 1) Content, Connections, and Context 2) Joseph Konstan talk abt the different decision strategies ppl have in different contexts.

On Thursday, we run a workshop on  mobile recommender systems. Francesco Calabrese of IBM Smart Cities gave an interesting invited talk about current projects on transportation systems. Then, we had a set of really good talks & one outdoor activity. What did I learn? Well, most of the existing mobile systems assume that the recommendation process unfolds in one single step - get restaurant recommendations & choose one of them. In reality, recommendations in the built environment should go beyond that. For example,

  • To mimic humans, the task of recommending restaurants should at least return 3 different recommendations (or facets): closest restaurant, best restaurant, trade-off between the two.
  • One should understand WHY people visit certain places. How did they make those decisions? Which criteria did they employ?
  • Recommender systems need to tap into established findings in the area of urban studies. For example, in our RecSys paper "Ads & the City", we exploited the fact that people are boring - they generally do not travel very far - unless what they are looking for is not readily available where they are.
  • Temporal patterns in recommender systems have not been widely studied. They have been studied on Web platforms only recently (and Neal Lathia has done great work on that!) and have been neglected in mobile platforms. That is why we had another paper in the conference titled "Spotting Trends: The Wisdom of the few"
  • Finally, and more importantly, we need far more user studies of how these systems are ACTUALLY used! Recommendations do not matter much -the experience counts ;)

And this is just scratching the surface ;)

Conference

I remember only few things from the conference (the industry track was pretty good):

  • Multiple Objective Optimization in Recommendation Systems (linkedin). Nice example of A/B testing
  • Towards Personality-Based Personalization (Thore Graepel of Microsoft Research). Nice talk about how easy is to predict personal attributes of Facebook users based on their likes. if you are interested in personality and social media, you should check out our work on Facebook and Twitter (we can predict personality traits of twitter users upon only their number of followers, following, and listed counts)
  • Building Industrial-scale Real-world Recommender Systems (Xavier Amatriain of Netflix). Brilliant (& fully packed) tutorial. Check this out for a summary.
  • Controlled experiments at Microsoft Bing (very good work): i encourage you to read  2009 guide [pdf] ; 2012 kdd paper; slides of the talk.
  • Pareto-efficient hybrization for multi-objective recommender systems (UFMG). Here the question is  how to combine different types of algorithms (hybrization).
  • User Effort vs. Accuracy in Rating-based Elicitation (PoliMI). What's the optimal number of users ratings for movie recommendations? It seems to be between 5 to 20.
  • TasteWeights: A Visual Interactive Hybrid Recommender System (UCSB). Visualization platform for your social media stream
  • Learning to rank optimizing MRR for recommendations. Very cool work.  It taps into the less is more concept, which I'm a big fan of
  • Thumbs up to real-world stuff: Beyond Lists: Studying the Effect of Different Recommendation Visualizations;  Yokie - Explorations in Curated Real-Time Search & Discovery Using Twitter; A System for Twitter User List Curation; The Demonstration of the Reviewer’s Assistant; CubeThat: News Article Recommender (browser extension for Chrome displays recommended additional news stories related to the same topic as the current news story)
  • Challenges in music recommendation (@plamere from @echonest). A couple of interesting insights: "Understanding the specifics of your domain is critical to building a good recommender"; and recommending down-tail is OK, while recommending up-tail (britney to one who likes tom waits) is risky. Might be offensive to one's music identity. So make your recommendations Hipster-Friendly ;)
2Jul/120

Social Networks: field advanced by people “not in the field”?

Posted by Daniele Quercia

On Saturday I came back from the annual meeting of the UK Social Networks Association (UKSNA). It was the perfect place to meet old friends and make new ones. The program is here . I presented our work on why Twitter is a social network, and on why people "unfriend" each other on Facebook (the latter was covered by the New Scientist today). Interesting presentations include those on Tom Snijeders' multilevel longitudinal analysis of social networks, Harrigan's work on tie formation on Twitter, Emery's on "shared Leadership", and Marcus's on the connected communities project (those are the only presentations I could listen to - i joined a bit later because of other commitments in nottingham)

I was on a panel chaired by Bernie Hogan. The panel was discussing how network studies in the social sciences could help us to investigate the use of "Social Media". Here Paola summarised her thoughts on what was said, concluding:

"...there is an unmet and unrecognised need for theories. We don't know how social influence works in online networks. How social media help to form social capital, and how comparable this is to the social capital we knew offline. Whether local or global network effects are prevalent. How online/offline multiplexity works."

It's interesting to see that all these topics have been recently covered by people on a hybrid ground - that is,  by people who are at the cross road of sociology, physics, and computer science. Namely, NB Ellison's work on building social capital in Facebook, Sinan Aral's on social influence online, and JP Onnela's on multi-slice networks. Development in the field could go no faster - by those who are not "in the field". Brokerage at work? :)

Filed under: Uncategorized No Comments
27Jun/120

Twitterology + Latourology

Posted by Daniele Quercia

I just came back from WebSci - the "Web Science" conference. Papers were sane, keynote were plenty and of very high quality, the organisation of the conference was amazing.

Papers were mostly quantitative. One critical thinker unfairly criticized these papers to be Twitterology, and proposed to fix just that with additional work, which, others argued, manages to do Twitterology and Latourology  (after Bruno Latour) at the same time - a mixed approach so-to-speak :) Unfortunately, only few papers were qualitative. I hope we will see a more balanced programme in the future - so, CHI & CSCW folks,  please consider submitting your work ;) Well-grounded qualitative work is badly needed in this young community. Tip: I would use grounded theory...

p.s. For Laturologists: EU is financing a new project. If you understand Latour (some don't) and want to help him, please refer to this video (that's where EU taxpayers' money is going)

Filed under: Uncategorized No Comments
18Apr/120

smart cities, big data

Posted by Daniele Quercia

it's the title of a very nice editorial (pdf) by mike batty. i'm from the bit (and not from the beat) generation, and yet i like to cut & paste bits from the editorial (i would recommend to fully read it though):

I first wrote about `smart cities' almost as soon as I began writing these editorials in the early 1980s. ... In the 1980s the focus on instrumenting the city using network technologies was enshrined in the idea of the wired city. ... Many of these conceptions were based on visions of what wired cities might become rather than on the reality of what was actually possible then. ... What has changed these initial conceptions of the wired city is the development of ubiquitous devices of comparatively low cost that can be deployed to sense what is happening over very small time scales - seconds and faster - as well as over very fine levels of spatial resolution.

The idea of integrating much of this diverse data together to add value to our conceptions of how it might be linked to other more traditional data as well as focusing it on specific ways to make cities more efficient and more equitable, has come to define the `smart cities movement'.

Most urban theory and indeed planning and design fifty years or more ago was predicated on radical and massive change to city form and structure through instruments such as new towns, large-scale highway building, redevelopment, and public housing schemes. Planning was little concerned with smaller-scale development except its design, for nowhere was the function of the city understood in terms of how small spaces and local movements sustained the city. In short, the routine and short term were subsumed in the much longer term. New data and big data are changing all of this...

This is an issue that has barely been broached to date - how short-term big data informs longer-term data is part and parcel of our concern for how we might integrate traditional datasets from household interviews and so on with crowd-sourced data where there is less control, and remotely or directly sensed data.

Filed under: Uncategorized No Comments
11Apr/120

Disrespect, Violence, and Privacy Outcries: From the Bible to Google

Posted by Daniele Quercia

Licia and I wrote a piece for Middleware titled "Middleware for Social Computing: A Roadmap". One of the sections was about how the middleware research agenda could promote healthy social norms at design stage. The main idea is that:

to promote the emergence of healthy social norms, system design of social media sites is crucially important. The way a new system is designed partly impacts which social norms emerge in it. However, once settled, social norms are hard to change, and when companies (e.g., Google) tell people how they must behave (e.g., they enforce the use of real identities), things go terribly wrong.

That is because being forcibly told how to use a service is perceived as a sign of disrespect by users, and disrespect has often cause violence in physical societies and, for now, only public outcries in digital systems. To explain why more unequal societies experience more violence, in their book ``The Spirit Level'', Richard G. Wilkinson and Kate Pickett cite the work of the Harvard Medical School psychiatrist James Gilligan, who has said that he has

yet to see a serious act of violence that was not provoked by the experience of being shamed and humiliated... and that did not represent the attempt to ... undo this "loss of face".

The two authors also recall that, over 2000 years ago, Cain committed the first murder in history by killing his brother Abel because God has rejected his offerings of produce but accepted the animal sacrifices brought by Abel. In King James Version of Genesis:

And the LORD had respect unto Abel and to his offering: But unto Cain and to his offering he had not respect. And Cain was very wroth

Disrespect as a cause for violence is a human truth recognised for millennia. It comes as no surprise that this truth still holds in our digital world. What is surprising, instead, is that large media companies keep on making the same mistake over and over again. When Google launched a social media service called Google Plus, most of its early adopters were using their real names, and a few were not. Google decided to go after those few with a heavy-handed regulatory policy to enforce the use of real names, and Google+ started to sink, and sink, and sink . The interaction designer behind  Google+ Paul Adams did not agreed with those brilliant engineering decisions and "was forced to move" to Facebook. Any better over there?

- daniele

Filed under: Uncategorized No Comments