Is Twitter A Substitute For Set Top Box Data?

Posted on June 2nd, 2009 by Pravin Chandiramani

Everybody with a television and a remote control channel surfs.  Even the most directed viewer allocates some part of their hours in front of the television flipping through channels, lingering for several seconds on a program before returning to the guide, visiting their next favorite network or moving on to the adjacent channels on the dial.

Channel surfing is essential to the television viewing experience, especially as the number of channels and the volume of programming on television explodes.  Following from the explosion of television content, viewers’ ability to discover new programs is impaired and their estimation of the opportunity costs of choosing a program is increased.

At Simulmedia, we think that certain viewers will spend less time surfing if they were better informed of program content and schedules.  We also think that, through segmenting viewers by their surfing habits, we might better identify the viewers that will surf less and tune in more after exposure to the right program promotions.  Scheduling promotions in spots that index highly for viewers likely to enter favorable surfing modes will encourage their substituting viewing time for surfing time and increase the ratings of the programs they choose.

To investigate surfing behavior further we tapped into data from Twitter, where dozens of people announce to the world that they are channel surfing every day.  Unlike traditional ratings or second-by-second set-top-box information, Twitter has rich qualitative information that reveals motivations behind viewers’ surfing.

A semantic analysis of the data revealed that the tweets could be clustered into 8 distinct channel surfing modes. Each of these modes represents a different state-of-mind, which in turn could correspond to receptivity to program promotion. The modes are listed below:

channel surfing tweets

1. Anticipation composed of people who tweeted about surfing as they waited for a program to start. For example, “channel surfing waiting until 3pm when ellen comes on!.

2. Searching – composed of people who indicated that they were searching for something to watch. For example “Channel surfing . looking for some good cable tv“.

3. Multi-tasking – composed of people who were doing other things besides surfing and twittering. For example “Channel surfing and reading Roenick’s latest comments on how he thinks Babcock hates Cheli..“.

4. Split-attention composed of people who distribute their attention between several programs at once. For example “Channel surfing between Idol and Lakers“.

5. About to sleep – composed of people who are just biding time by channel surfing before they fall asleep. For example “channel surfing, probably til I fall asleep.”.

6. Relaxing composed of people who have indicated that they were in a relaxed state of mind and were channel surfing. For example “Plans fell through so chillaxing n channel surfing“. 

7. Bored & Awake composed of insomniacs who are bored, and are surfing in the hope they fall asleep soon. For example Channel surfing because I can’t sleep…..”

8. Converts composed of people who found something to watch while surfing. For example, “Channel surfing and found last 15 mins of Penn State trouncing Stanford in the Championship game in women’s college#rugby on ESPNU“.

We’d expect viewers in different modes to respond differently to program promotion.  Of the eight surfing modes, Anticipation and Split-attention are likely the most difficult to sway with promotions.  Viewers in Anticipation mode surf to kill time before a scheduled program.  Viewers in the Split-attention mode are watching multiple channels at the same time.

On the other end of the discovery spectrum, we’d expect viewers in the Searching and Converting mode, roughly 30% of classified tweets, to be most likely to change their surfing time to watching time.  Directing promotions to viewers who are in Searching and Converting modes presents a untapped opportunity to increase ratings and also provide better media choices to these viewers.

Cet article, publié dans Uncategorized, est tagué , , , , , . Ajoutez ce permalien à vos favoris.

Laisser un commentaire

Entrez vos coordonnées ci-dessous ou cliquez sur une icône pour vous connecter:


Vous commentez à l'aide de votre compte Déconnexion /  Changer )

Photo Google+

Vous commentez à l'aide de votre compte Google+. Déconnexion /  Changer )

Image Twitter

Vous commentez à l'aide de votre compte Twitter. Déconnexion /  Changer )

Photo Facebook

Vous commentez à l'aide de votre compte Facebook. Déconnexion /  Changer )


Connexion à %s