The U.S. Patent and Trademark Office
published a peculiar Apple filing describing an ad service that targets users
based on hard-to-quantify metrics like behavior and mood. Apple's
"Inferring user mood based on user and group characteristic data" patent
application looks to offer advertisers and content providers a more intuitive
and effective way to target users.
A user's responsiveness to targeted content
delivery — advertisements — can be affected by any number of factors. Among
these are location, time, current activity and mood. Apple wants to leverage
user mood and mood-associated characteristic data to provide a more accurate
method of ad targeting. Apple’s patent describes a way in which mood can be
assessed too to add an extra dimension to the advertiser’s arsenal of consumer
intelligence.
Apple’s filing says it can determine mood
based on different types of data, including the heart rate, blood pressure,
adrenaline level and body temperature many of which are now being volunteered
by users of devices in the quantified self space like fitness trackers and more
advanced health sensors. It can also use signals as what type of content a user
is viewing, which applications they are using and what kind of music they are
listening to and even how they are interacting with social network for finding
outwardly expressed cues regarding mood.
Described by the filing, mood-associated
characteristics can be physical, behavioral, spatial or temporal. For example,
the heart rate, blood pressure, perspiration, body temperature and vocal
expressions may all be used to determine a user's mood. Behavioral cues means
which type of media is being consumed, the sequence in which applications are
launched and social networking activities among others.
In some embodiments, mood is gauged by a
camera which when used in tandem with facial recognition software, it can
measure facial expressions.
On the backend, a database consisting of a
user's profile is automatically updated based on a set of rules instituted
either by the system or the user. Pieces of the profile may be revised as need
based on learning algorithms that tap into external data like iTunes
registration and usage information.
The document explains the technology Apple is
developing analyzes mood-associated character data that has been gathered over
a period of time. This data, when analyzed, would be used to create at least
one “baseline mood profile” for the user.
Apple dedicates a part of the property to
address privacy concerns and states the information gathered should not be used
for illegal purposes. The system is meant to enhance user’s experience by
serving relevant ads while at the same time providing advertisers with more
effective distribution tools.
Mood and sentiment analysis is a kind of hot
area in online media these days, thanks to continuing improvements in machine
learning, so it is not surprising to see Apple take some exploratory steps in
that direction.
Author : Iman Majeed Source : US Patent
0 comments:
Post a Comment