NoTube presentation at NEM Summit 2011

RAI presents NoTube's Personalised Semantic News at the NEM Summit Conference 2011 NoTube was at the NEM Summit 2011. Two papers that were submitted by NoTube partners were presented at the conference which took place from September 27th to 29th at Politecnico in Torino.
NoTube Demo at NEM Summit 2011 Exhibition Peter Altendorf from IRT presented a paper about the common ground of NoTube and HbbTV. Luca Vignaroli from RAI presented the Use Case 7a. The NoTube project was also demoed by RAI at the accompanying NEM Exhibition.

Posted in About Notube, News, Publication | Leave a comment

At IBC? Join us at the NoTube stand!

Find us at Connected World, Hall 13, Stand 202 – opposite the Internet Cafe!

Posted in Uncategorized | Leave a comment

See NoTube during IFA Berlin

Parallel to the IFA in Berlin, the IEEE will hold the 1st International Conference on Consumer Electronics (ICCE). On September 7, in the session on User Centered Design, Dr Lyndon Nixon of the NoTube project will present “NoTube: the television experience enhanced by online social and semantic data“, a paper written together with Lora Aroyo and Libby Miller.

Posted in Uncategorized | Leave a comment

NoTube will be at IBC 2011 – see you there!

NoTube is pleased to announce we will be at IBC again this year – you will find us at Stand 202 (opposite from the Internet Cafe!) in Hall 13 in the Connected World zone from Friday 9th September to Tuesday 13th.

Highlights this year will be live demonstrations of the NoTube showcases

You are welcome to use the customer ticket number 16555 to gain FREE ENTRY to the whole of the IBC Exhibition Area courtesy of the NoTube project.
Just use this ticket number when registering for the exhibition at http://www.ibc.org/registration and with this ticket you will also receive a five day travel pass.

Posted in About Notube, Demos, News, Personalised advertising, Showcase, Social TV | 1 Comment

NoTube highlighted in Dutch scientific centre’s annual report

SARA is the Dutch center for scientific computing. They have interviewed NoTube member Dan Brickley about some experiments he has been running on their infrastructure in the context of the NoTube project in their yearly report. Here’s a download link to their annual report: http://sara.nl/sites/default/files/SARA_Annual_Report_2010.pdf. The article on NoTube is also online at http://sara.nl/bestcase/social-media-and-television

Posted in Uncategorized | Leave a comment

Two new open source services published

Source code of several services that we developed has just been released as open source code with the Apache 2.0 license. These services include:

The services are written in Prolog on top of the ClioPatria framework. ClioPatria is a RDF-store and Web server implemented in SWI-Prolog.
The source code is available on github: https://github.com/schopman/NoTube-ClioPatria-services

Posted in Code, Linked Data, News, Publication, Recommendations | Tagged , , , , , | Leave a comment

Finding interesting new programmes – trial results

In a previous blog post about a NoTube demo for browsing an archive of BBC programmes using Linked Data techniques, I discussed the potential role of serendipity in bringing people’s attention to ‘surprisingly good’ content that they didn’t already know about.

At the time Libby and I were just about to start user testing the application. We wanted to find out if the experience of serendipitous content discovery could be supported by re-using the metadata created when BBC programmes are archived (in this case terms from the BBC subject classification system).  We chose a technique which generates a similarity measure based on the number of categories in common between any pair of programmes, and then displayed these to the user as suggestions for related programmes.

NoTube Archive Browser

NoTube Archive Browser

For the purposes of our evaluation, we identified two specific research questions. Does it help people find more interesting programmes if:

  1. they browse similar programmes rather than a random selection
  2. they see browsable subject category information about the programmes

Our hypothesis was that seeing both similar programmes and clickable subject category information (as shown in the screenshots below) would be optimal for finding interesting new programmes.

Screenshot of NoTube demo

Clicking on "railway stations" links to a list of programmes classified with that term

During the trial the 96 participants had seven days during which to browse the Web-based on-demand video collection and add programmes of interest to a playlist. The participants were randomly allocated one of four experimental conditions:

  • Random programmes, no subject categories displayed (our control)
  • Random programmes, with subject categories displayed for each
  • Similar programmes, with no categories displayed
  • Similar programmes with subject categories displayed for each (our optimal condition?)

We measured the length of the playlists and the time spent browsing as indicators of ‘interestingness’, based on the assumption that people would create longer playlists and spend more time browsing when they found the links interesting. At the end of the trial 20 of the participants also filled out an online questionnaire about their experiences.

Statistical analysis of the data we collected (Libby created some box-whisker plots)
showed no clear effects of programme similarity or the display of subject categories on the length of participants’ playlists or the time they time spent browsing. Likewise, as the graphs below illustrate, responses to the questionnaire showed no significant variation in people’s experiences between the four experimental conditions. However, the questionnaire results suggest that, regardless of the experimental condition, people did find interesting new programmes and generally liked the application.

For example, one participant remarked: “I liked the way the app threw up programmes I had forgotten about. I liked the way that on selecting one programme I always found even more interesting programmes on the related programmes list.” In total, 15 out of the 20 respondents said they would recommend the application to others.

Questionnaire results

Comparison of questionnaire results between control and optimal groups

One possible explanation for the fact that the experimental condition had no significant effect on people’s enjoyment of the application was that our ‘random’ selection was actually too good, since it tended to display a fairly reasonable set of programmes taken from a variety of well-known TV series.

Overall, the results suggest to us that adopting this type of approach to navigating large video collections (including archives, on-demand content and EPGs) could help with the ‘cold start’ problem, whereby a recommendation system cannot provide useful recommendations until a substantial amount of user activity data has been gathered. Re-using existing programme metadata to create content-based links in this way could help large media organisations to provide users with a means of accessing niche video content that might not otherwise be found, in particular if no-one has yet watched it because it hasn’t appeared in a ‘What’s popular’ or ‘What’s new’ list.

This experiment complements the work of several of our NoTube colleagues, who are also exploring the role of serendipity in using Linked Data techniques to suggest programme recommendations that are diverse, unfamiliar and ‘surprisingly good’ – difficult as this is to measure.

Posted in Evaluations, Recommendations, User Experience | 1 Comment