We recently had a paper accepted to iConference. We used click data from Mr DLib, our recommender-as-a-service, to see if users of recommender systems in digital libraries are affected by position bias. We found that users are affected by position bias on average. Some users do seem to examine recommendations more carefully than other users. As far as we know, this is the only investigation of position bias in digital libraries, and in recommender systems for digital libraries. We have made the data available. It contains 10 million recommendations delivered by us to users, with 12,543 clicks on recommendations logged. We hope that other researchers will find this useful. For example, perhaps the click behavior of a digital library user could Read more…
AICS’2018: We Co-Organize the 26th Irish Conference on Artificial Intelligence and Cognitive Science
We are delighted to announce the 26th Irish Conference on Artificial Intelligence and Cognitive Science (AICS’2018), which we will co-organize together with Rob Brennan, Ruth Byrne, Jeremy Debattista, and a renowned program committee. AICS 2018 takes place from December 6 to 7, 2018 at Trinity College Dublin, more precisely in the Long Room Hub. Deadline for submissions is 30th September 2018. There will be three tracks for submissions, namely full papers, NECTAR Papers, and student papers. The call for papers invites papers relating particularly to machine learning, machine translation, neural networks, data mining, cognitive modelling, behaviour epistemology, evolutionary computation, recommender systems, collective intelligence, human learning, and several more. AICS 2018 is sponsored by the ADAPT Research Centre, Trinity Long Room Hub, and Trinity College Dublin. AICS dates Read more…
The ACM Conference on Recommender Systems (RecSys) is the premier conference to present new research results, systems, and techniques including machine learning and natural language processing relating to recommender systems. This year, the 12th ACM Conference on Recommender Systems takes place in Vancouver, and the call for papers has just been published. We are proud to serve on the program committee and hope to receive many interesting submissions this year.
We just returned from the 11th ACM Conference on Recommender Systems in Como, Italy. It was an amazing conference, with lots of interesting presentation relating to recommender systems. One of the hot topics at the Recommender Systems Conference was Deep Learning, though, frankly, deep learning did not always seem to deliver promising results for recommender systems. Here are a few photos.
Hypertext 2010 Security Hole: All papers downloadable and editable by anyone (2 month before conference start)
In June the ACM Hypertext 2010 will take place in Toronto. Some days ago I wanted to upload the camera ready versions of three papers being accepted at the conference. And... I was surprised. By email I got a link to a web page (namely , , and on which I could upload my camera ready papers, specify the authors, keywords, etc. No password or other kind of authorization had to be entered. Now, guess what. I played around with the URL and tried, for instance, to open the following URLs in my browser. You can probably guess what happened: I could edit the details (and see the private email addresses the primary authors provided) and upload PDF files for the other papers being accepted at Hypertext just by changing the URL. That means, I could have added or modified the author list, changed the title or uploaded a modied PDF. The screenshot shows the user interface on which I could have changed the data for the paper "Dealing with the Video Tidal Wave: The Relevance of Expertise for Video Tagging" by Sara Darvish and Alvin Chin (here is a list of all papers being accepted at Hypertext 2010) But it comes even better. After submitting my camera ready papers I was provided (more…)