NoTube blog – the future of television is social and semantic

How can we best measure how good people think our recommendations are?

Posted in Thinking Out Loud by vickybuser on May 13, 2010

Recently a friend was describing how her friend had persuaded her to watch a DVD that she thought she’d absolutely hate, but ended up loving. The DVD was the 2004 BBC TV series ‘Blackpool’ (described as “part musical, part thriller, part drama”) - and my friend was initially sceptical because, as a general rule, she really doesn’t like musicals. She is a big fan however of two of the main actors, David Morrissey and David Tennant, which slightly warmed her to the idea, but it was really the insistence of her friend that made her sit down and watch it – and thoroughly enjoy it!

I think this story highlights the problem with TV programme recommendations based solely on genre: given my friend’s dislike of the ‘musicals’ genre, she would never have been recommended the programme in the first place by a genre-based recommendation system, or watched it based on genre information alone.

With NoTube TV recommendations, it has always been our intention to generate personalised recommendations based on preferences that include genres, but are not limited to them. By using linked data techniques, preferences for specific programmes can theoretically be based on any metadata associated with a programme; such as directors, writers, actors, presenters, contributors, locations, and other people (both friends and/or experts) who are watching, or have watched, the programme. As danbri has suggested, we could also make quirky connections such as “you were recommended this programme because the star, Cary Grant, used to live in your street”.

Using this approach, my friend might have been recommended ‘Blackpool’ based on the fact that two of her favourite actors are in it, and that her friend (whose taste she admires) has watched it. We’ve always believed in the importance of explaining to users why a programme has been recommended to them, but would the evidence have been strong enough to persuade my friend to try watching it? I think this issue of persuasion is important: after all, one of the things we want from a good recommendation system is for it to help us broaden our horizons and discover new, enjoyable things that we would probably not have discovered on our own.

picture credit:

If my friend hadn’t been persuaded to try the programme, she would never have discovered that she really loved it. And she would never have found out that it was actually a great recommendation for her, which could have led to other new and interesting programme suggestions.

This leads to the challenge of how you get people to subjectively evaluate the quality of the programme recommendations suggested to them by a recommendation system when:

  • Firstly, they need to be persuaded to try out some new things, which might at first seem rather too obscure or too far removed from their comfort zone.
  • They need to have the motivation to provide the system with some feedback, and the patience and commitment to give the system time to make adjustments.
  • Ideally, they also need to give reflective thought to the question of whether a programme recommendation really was ‘relevant’ or ‘useful’ – how would you really know unless you tried watching it?

In all, this requires a substantial amount of effort and dedication on behalf of the user – it’s not quite the same thing as asking people if a shopping cart transaction was confusing or not.

Further, evidence suggests that TV viewing is still commonly a social activity in which negotiation and compromise are inevitably part of the decision-making process of the group.  Group recommendations therefore have to take into account the preferences of multiple users, making these sorts of evaluations even more challenging.

In the next phase of the NoTube project we want to test the quality of our recommendations on users. To get really useful feedback we will need to tackle these various issues along the way.

Designing a touch-screen TV remote control on a smartphone

Posted in Thinking Out Loud by vickybuser on May 5, 2010

Our first demo for “Internet TV in the Social Web” includes an iPhone app that works as both a TV remote control and a ‘companion device’ for viewing programme recommendations and programme guides, managing programme playlists, and reading background information about a programme from the Web.

From a user experience perspective, there are two particularly interesting aspects to this:

  1. Usability issues relating to using a touch-screen remote for controlling a TV
  2. The idea that merging the Web with TV doesn’t have to mean showing the Web on a TV screen: instead, the Web can be integrated into the viewing experience using a ‘second screen’ companion device, leaving the TV screen free of clutter.

The second issue is worthy of a blog post of its own. In the meantime, we’re starting to explore the first issue in more detail.

Our iPhone app includes an interface for a basic TV remote that allows the user to select and browse their programme guide (EPG) on the TV screen, and to select and play programmes. Whilst anecdotal evidence suggests that people want to use their smartphones as TV remotes, the touch-screen interface poses a major design challenge. With traditional remotes we’ve all become used to changing channels or adjusting the volume without necessarily taking our eyes off the TV screen – by feeling for the desired buttons under our fingers. However, without these physical buttons, the touch-screen requires us to take our eyes off the TV screen and pay visual attention to the remote.

When we mocked-up the interfaces for our prototypes, we played around with various designs for the remote screen. However, none of these deviated much from standard remote designs, and we didn’t have time to try out anything new or to do any rigorous analysis of the usability effects of the screen layout and positioning of the controls.

We also wondered whether, and how, various input and output methods could be used to improve the user experience. These include:

  • Gesture control: for example, the Boxee Remote iPhone app offers a ‘gesture’ mode whereby users drag the Boxee logo around to the TV screen, and tap the logo to perform an action (select/play/pause). Similarly, Apple added swipe and tap finger gesture control functionality to its Remote app to control what’s seen on Apple TV. Via its Control’ interface, users can tap to select, play and pause, and flick left or right, or drag and hold, to rewind or fast-forward.
  • Sound effects, such as clicks or voiceover
  • Voice commands
  • ‘Haptics’ (tactile feedback such as vibration)
  • Accelerometer control (tilts and shakes)

Finally, could there be certain situations in which specific combinations of these ‘modes’ could be optimal, depending on the user’s individual preferences and needs? If so, how much would users want to control these modes?

We thought that this was an interesting area of research, and it also complements the work our colleagues in BBC Research and Development are doing in investigating how multi-touch software could support television viewing in the future.

The challenge of proposing some solutions to this design issue has been taken up by the some of the students attending Lora Aroyo’s HCI course at VU University Amsterdam. The students are currently mid-way through their assignment, and we’re really looking forward to seeing what they come up with.

NoTube to use BMF and TV-Anytime – Collaboration with EBU and egta for new metadata scheme for ads

Posted in Uncategorized by pjotrek078 on May 4, 2010

One of the tricky things in NoTube is that there are many different metadata formats that are both provided and consumed by the various services that will make up the NoTube system. To make sure that the metadata used is understood correctly by every service, the alignment and conversion of metadata is necessary. Regarding the metadata which concerns TV content, the WP2 team has achieved three major steps in the past months. First, we have tried to gather all the requirements of the three NoTube Use Cases. This has been achieved working together closely with the use case partners. Then, we took a comprehensive look around to see which existing metadata models appear as potential candidates. Last but not least, we checked the most promising models against the use case requirements to identify the most suitable candidates.

For the metadata that is provided together with TV content by content providers such as RAI, we decided to use the Broadcast Metadata Exchange Format (BMF) as the input interface format to the Service Provider side. BMF is a powerful metadata model which covers all metadata in the life-cycle of a TV production – from the initial planning and the pre-production all the way to distribution and archiving. It is intended to be used as an exchange model by systems that are interchanging metadata in different steps of the TV production process to increase the interoperability between the many systems involved in this process. Such a uniform interface which is able to handle various broadcast metadata formats will make NoTube future-proof and enable other broadcasters to connect to the system.

On the Home Ambient side, we will be using TV-Anytime which has been identified to meet the requirements of the NoTube use cases. TV-Anytime is an internationally agreed and accepted metadata schema in the TV consumer domain already widely used in consumer devices like PVRs etc. After evaluating the requirements for the Service Provider side, we figured that TV-Anytime will suffice for these needs as well.

However, a bit more difficult, for advertisement metadata there is currently no common format around used for TV ads. Thanks to IRT’s involvement in the European Broadcasting Union (EBU), we learned about the collaboration between EBU and egta, the trade association of television and radio sales houses. Together, they are working out a unified metadata scheme for ads which we will be using for adaptive advertising in NoTube. We already discussed the preliminary schema with the EBU and provided feedback from NoTube’s ads experts back to EBU and egta.

To allow an exchange of information and thus the interoperability between the Service Provider and the Home Ambient side, a metadata transformation is required. The internal transformations as well as the transformation of external sources into the NoTube metadata formats will be tackled in WP2 in the coming months.