Here’s a quick preview of the final programme for Search Solutions 2014. Don’t forget that the deadline for early bird registration is Friday, October 31st. Hope to see you there!

Continue Reading »

I know the official publicity isn’t due to go out for a little while just yet, but here’s a sneak peek at this year’s lineup for Search Solutions 2014. For those unfamiliar with the event, it is described as:

… a special one-day event dedicated to the latest innovations in web & enterprise search. In contrast to other major industry events, Search Solutions aims to be highly interactive, with attendance strictly limited. The programme includes presentations, panels and keynote talks by influential industry leaders on novel and emerging applications in search and information retrieval.

As last year we’ll be preceding the event with a tutorials day on November 26, which will offer conference attendees and local participants a stimulating and informative selection of practical training courses reflecting current topics and state-of-the-art methods in search and information retrieval. More on that later! Meanwhile, here is the provisional programme thus far:

Continue Reading »

I’m pleased to announce the line up for EuroHCIR 2014, which will be held at BCS London on September 13. This event is the fourth HCIR event to be held outside of the US, and as such represents a critical point in the development of the HCIR community in Europe. We’re just in the process of finalizing the programme, which will include 7 presentations, a keynote speaker and an evening social. We also hope to include an interactive group session in the afternoon – more on that later. In the meantime, I’ve appended the full list of accepted papers below. More details on the EuroHCIR website. Hope to see you there!

Continue Reading »

IRSG logoJust in case you missed it, here are the details of the latest issue of Informer, which came out today. As usual, lots of good stuff, with great mix of feature articles, research pieces and conference reviews. For further details see the Informer website. Or if you fancy becoming a contributor, get in touch!

Continue Reading »

Diana Maynard entertains the masses

Diana Maynard entertains the troops

Last week I had the privilege of organising the 13th meeting of the London Text Analytics group, which featured two excellent speakers: Despo Georgiou of Atos SE and Diana Maynard of Sheffield University. Despo’s talk described her internship at UXLabs where she compared a number of tools for analysing free-text survey responses (namely TheySay, Semantria, Google Prediction API and Weka). Diana’s talk focused on sentiment analysis applied to social media, and entertained the 70+ audience with all manner of insights based on her expertise of having worked on the topic for longer than just about anyone I know. Well done to both speakers!

Continue Reading »

Just a quick reminder that next Friday (1st August) is the deadline for submissions to EuroHCIR 2014, which I am co-organising with Max Wilson, Birger Larsen, Preben Hansen and Kristian Norling. This is the fourth year we’ve run the event, so we’re hoping for a good set of submissions to keep up momentum. As before, we’re accepting both research and practice-oriented papers, so if you have any queries (particularly about the latter) just drop me a line.

The event itself is on 13 September at BCS London, with a poster session/social scheduled for the evening before. I’ve appended a summary of the call for papers below, and further details can be found at the EuroHCIR 2014 website. Hope to see you there!

Continue Reading »

Expectation Maximization applied to a new sample of 100,000 sessions

In a previous post I discussed some initial investigations into the use of unsupervised learning techniques (i.e. clustering) to identify usage patterns in web search logs. As you may recall, we had some initial success in finding interesting patterns of user behaviour in the AOL log, but when we tried to extend this and replicate a previous study of the Excite log, things started to go somewhat awry. In this post, we investigate these issues, present the results of a revised procedure, and reflect on what they tell us about searcher behaviour.

Continue Reading »


Get every new post delivered to your Inbox.

Join 157 other followers