IDENTIFYING KEY MEDIA EVENTS AND MODELING CAUSAL RELATIONSHIPS BETWEEN KEY EVENTS AND REPORTED FEELINGS

• US 20090158308A1
• Filed: 12/18/2007
• Published: 06/18/2009
• Est. Priority Date: 12/18/2007
• Status: Active Grant

• Current Assignee: Nielsen Consumer LLC (Nielsen Holdings plc)
• Original Assignee: Nielsen Company (US) LLC (RR Donnelley & Sons Company)
• Inventors: Weitzenfeld, Daniel, Fettiplace, Michael R., Lee, Hans C.
• Granted Patent: US 8,347,326 B2
• Time in Patent Office: Days
• US Class Current: 725/10
• CPC Class Codes: H04H 60/33 Arrangements for monitoring the users' behaviour or opinions
• CPC Class Codes: H04H 60/73 using meta-information
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45

Abstract

A novel approach enables an event-based framework for evaluating a media instance based on key events of the media instance. First, physiological responses are derived and aggregated from the physiological data of viewers of the media instance. The key events in the media instance can then be identified, wherein such key events drive and determine the viewers'"'"' responses to the media instance. Causal relationship between the viewers'"'"' responses to the key events and their surveyed feelings about the media instance can further be established to identify why and what might have caused the viewers to feel the way they do.

Claims

1. A system to support key events identification, comprising:

a response module embedded in a first readable medium which, while in operation;

accepts and/or records physiological data from each of a plurality of viewers watching a media instance;

derives and aggregates one or more physiological responses from the collected physiological data;

an event defining module embedded in a second readable medium which, while in operation, defines the media instance into a plurality of events;

a key event module embedded in a third readable medium which, while in operation;

accepts the plurality of events defined in the media instance;

identifies one or more key events in the media instance, wherein the one or more key events drive the one or more physiological responses to the media instance from the plurality of viewers;

reports the one or more key events to an interested party of the media instance.

2. The system of claim 1, further comprising:

a reaction database which stores pertinent data of the media instance, wherein such pertinent data includes survey questions and results asked for each of the plurality of viewers before, during, and/or after their viewing of the media instance.

3. The system of claim 1, wherein:

the media instance is one of;

a video, an advertisement clip, a movie, a computer application, a printed media, a video game, a website, an online advertisement, a recorded video, a live performance, a debate, and other types of media instance from which a viewer can learn information or be emotionally impacted.

4. The system of claim 1, wherein:

the physiological data is one or more of;

heart rate, brain waves, electroencephalogram (EEG) signals, blink rate, breathing, motion, muscle movement, galvanic skin response and any other response correlated with changes in emotion of a viewer of a media instance.

5. The system of claim 1, wherein:

each of the one or more physiological responses is one of;

liking, intent to purchase or recall, emotional engagement, thinking, adrenaline, other emotional experiences to the media instance, and other response to sensory stimulations from food or a scented product.

6. The system of claim 1, wherein:

the response module either retrieves the physiological data from a storage device or measures the data via one or more physiological sensors attached to each of the plurality of viewers either in separate or integrated form.

7. The system of claim 1, wherein:

the response module derives the one or more physiological responses via a plurality of statistical measures.

8. The system of claim 1, wherein:

the event defining module defines occurrence and duration of the plurality of events in the media instance by identifying salient positions in the media instance.

9. The system of claim 1, wherein:

the event defining module defines occurrence and duration of the plurality of events in the media instance via one or more of;

a hypothesis approach, a time shift approach, a turning point approach, and a multi-component event approach.

10. The system of claim 1, wherein:

the key event module automatically spots statistically significant points in the one or more physiological responses that are relevant to identify the one or more key events in the media instance.

11. The system of claim 1, wherein:

the key event module, while in operation,

collects demographic data of the plurality of viewers;

categorizes the plurality of viewers into a plurality of groups based on one or more of;

race, gender, age, education, demographics, income, buying habits, intent to purchase, and intent to tell;

identifies the key events that are polarizing and cause statistically significant difference in the physiological responses from the plurality of groups of the plurality of viewers.

12. A system to support key events identification, comprising:

a response module embedded in a first readable medium which, while in operation;

accepts and/or records physiological data from each of a plurality of viewers watching a media instance;

derives and aggregates one or more physiological responses from the collected physiological data;

an event defining module embedded in a second readable medium which, while in operation, defines the media instance into a plurality of events;

a key event module embedded in a third readable medium which, while in operation;

retrieves from the reaction database a surveyed outcome from the plurality of viewers of the media instance;

establishes a causal relationship between the physiological responses from the plurality of viewers to the plurality of events and the surveyed outcome of their feelings about the media instance;

identifies one or more key events in the media instance based on the correlation between the one or more physiological responses and the surveyed outcome.

13. The system of claim 12, wherein:

the surveyed outcome is one of;

liking, effectiveness, purchase intent, and post viewing product selection.

14. The system of claim 12, wherein:

the key event module runs multivariate regression analysis via a multivariate model that incorporates the physiological responses from the viewers as well as the survey outcome from the viewers to identify which of the one or more key events drive the surveyed outcome.

15. The system of claim 12, wherein:

the key event module reports to the interested party which of the one or more key events in the media instance actually cause the surveyed outcome.

21. The method of claim 15, further comprising:

improving the media instance based on the physiological responses from the plurality of viewers to the one or more key events.

16. A method to support key events identification, comprising:

deriving and aggregating one or more physiological responses based on physiological data from a plurality of viewers watching a media instance;

defining the media instance into a plurality of events;

identifying one or more key events in the media instance based on the one or more physiological responses from the plurality of viewers;

reporting the one or more key events to an interested party of the media instance.

17. The method of claim 16, further comprising:

retrieving the physiological data from a storage device or measuring the data via one or more physiological sensors attached to each of the plurality of viewers either in separate or integrated form.

18. The method of claim 16, further comprising:

deriving the one or more physiological responses via a plurality of statistical measures.

19. The method of claim 16, further comprising:

spotting statistically significant points in the one or more physiological responses that are relevant to identify the one or more key events in the media instance automatically.

20. The method of claim 16, further comprising:

collecting demographic data of the plurality of viewers;

categorizing the plurality of viewers into a plurality of groups based on one or more of;

race, gender, age, education, demographics, income, buying habits, intent to purchase, and intent to tell;

identifying the key events that are polarizing and cause statistically significant difference in the physiological responses from the plurality of groups of the plurality of viewers.

22. The method to support key events identification, further comprising:

deriving and aggregating one or more physiological responses based on physiological data from a plurality of viewers watching a media instance;

defining the media instance into a plurality of events;

retrieving a surveyed outcome from the plurality of viewers of the media instance;

establishing a correlation between the one or more physiological responses to the plurality of events in the media instance and the surveyed outcome of feelings of the plurality of viewers about the media instance;

identifying one or more key events in the media instance based on the correlation between the one or more physiological responses and the surveyed outcome.

23. The method of claim 22, further comprising:

running multivariate regression analysis via a multivariate model that incorporates the physiological responses from the viewers as well as the survey outcome from the viewers to identify which of the one or more key events drive the surveyed outcome.

24. The method of claim 22, further comprising:

reporting to the interested party which of the one or more key events in the media instance actually cause the surveyed outcome.

25. A machine readable medium having instructions stored thereon that when executed cause a system to:

derive and aggregate one or more physiological responses based on physiological data from a plurality of viewers watching a media instance;

define the media instance into a plurality of events;

identify one or more key events in the media instance based on the one or more physiological responses from the plurality of viewers or a correlation between the one or more physiological responses and a surveyed outcome from the plurality of viewers;

report the one or more key events to an interested party of the media instance.