Method and system for rating media and events in media based on physiological data

Abstract

Various embodiments of the present invention enable a bottom up analysis approach that derives physiological responses from measured physiological data of viewers of a media, and calculates scores of instances of an event type based on the physiological responses. The scores are then aggregated to rate the event type in addition to scoring the individual event instances. The approach can also form an overall rating of the media by aggregating the event ratings of set of event types within the media.

Description

BACKGROUND

1. Field of Invention

This invention relates to the field of media and event rating based on physiological response from viewers.

2. Background of the Invention

Prior approaches to analyze viewers' responses to a media focus around a top down view, which is based on an averaged response to a survey, viewer “knobs”, physiological data or other rating schemes. This view limits the accuracy of the analysis due to cognitive bias of each individual viewer, as the viewer usually only remembers a small number of key events and forgets others. Consequently, one or two negative events in the media can dominate what the viewer thinks of the media afterwards, even if other positive events happened during the viewer's experience of the media.

The physiological data, which includes but is not limited to heart rate, brain waves, motion, muscle movement, galvanic skin response, and others responses of the viewer of the media, can give a trace of the viewer's emotion changes while he/she is watching the media. However, such data by itself does not create an objective measure of the media that allows the media or its events to be benchmarked and/or compared to other instances of media or events objectively.

SUMMARY OF INVENTION

Various embodiments of the present invention enable a bottom up analysis approach that derives physiological responses from measured physiological data of viewers of a media, and calculates scores of instances of an event type based on the physiological responses. The scores are then aggregated to rate the event type in addition to scoring the individual event instances. The approach can further form an overall rating of the media by aggregating the ratings of set of event types within the media.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is an illustration of an exemplary system to support media and events rating in accordance with one embodiment of the present invention.

FIG. 2 (a)-(b) are flow charts illustrating exemplary processes to support media and events rating in accordance with one embodiment of the present invention.

FIG. 3 shows an exemplary integrated headset used with one embodiment of the present invention.

FIG. 4( a)-(c) show exemplary traces of physiological responses measured and exemplary dividing lines of a media in accordance with one embodiment of the present invention.

FIG. 5 shows an exemplary profile of a joke in an advertisement as generated in accordance with one embodiment of the present invention.

FIG. 6 shows overall event ratings for three exemplary types of events in two movies calculated in accordance with one embodiment of the present invention.

DETAILED DESCRIPTION OF EMBODIMENTS OF THE INVENTION

The invention is illustrated by way of example and not by way of limitation in the figures of the accompanying drawings in which like references indicate similar elements. It should be noted that references to “an” or “one” or “some” embodiment(s) in this disclosure are not necessarily to the same embodiment, and such references mean at least one.

An effective media that connects with its audience/viewers is able to elicit the desired emotional response and it is well established that physiological response is a valid measurement for viewers' changes in emotions. Various embodiments of the present invention enable a bottom up analysis approach that derives physiological responses from measured physiological data of viewers of a media, and calculates scores of instances of an event type based on the physiological responses. The scores are then aggregated to rate the event type in addition to scoring the individual event instances. The approach can further form an overall rating of the media by aggregating the ratings of set of event types within the media. Such an approach allows instances of an event type to be objectively measured against prior instances of the same event type in the media, and the current media to be objectively measured against another media. In addition, a slice and combine approach can be adopted, which defines the media into one or more key and repeatable event types each having a plurality of event instances based on the physiological data measured, and then aggregates the score of every event instance and every event type to measure the viewers' overall responses to the media. The entire approach can also be automated as each step of the approach can be processed by a computing device, allowing for objective measure of a media without much human input or intervention.

A key principle behind the present invention is that one cannot look at an individual response to a media and make a judgment about the media. For a non-limiting example, a movie having multiple key scenes (events) can only be ranked accurately via a full analysis of viewers' responses to each of the scenes. Such analysis includes but is not limited to whether the intense scenes were actually intense, whether the love scenes turn viewers off or engage them, whether the viewers thought the jokes were funny, etc. Only when these individual scene types are aggregated and evaluate as a whole, can the movie be compared objectively and automatically to other movies in the same genre. In addition, only by knowing the typical response to be expected to a certain scene (event type), can a new instance of the scene be rated objectively.

FIG. 1 is an illustration of an exemplary system to support media and events rating in accordance with one embodiment of the present invention. Although this diagram depicts components as functionally separate, such depiction is merely for illustrative purposes. It will be apparent to those skilled in the art that the components portrayed in this figure can be arbitrarily combined or divided into separate software, firmware and/or hardware components. Furthermore, it will also be apparent to those skilled in the art that such components, regardless of how they are combined or divided, can execute on the same computing device or multiple computing devices, and wherein the multiple computing devices can be connected by one or more networks.

Referring to FIG. 1, one or more sensors 103 are utilized to measure and record physiological data from each of a plurality of viewers 102 who are watching a media 101. Alternatively, an integrated sensor headset can be adopted as discussed in details later. Here, the media can be one or more of a movie, a video, a television program, a television commercial, an advertisement, a video game, an interactive online media, a print, and any other media from which a viewer can learn information or be emotionally impacted. The physiological data measured can include but is not limited to, 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. Each of the one or more sensors can be one of: an electroencephalogram, an accelerometer, a blood oxygen sensor, a galvanometer, an electromygraph, and any other physiological sensor. Physiological data in the body have been shown to correlate with emotional changes in humans. By sensing these exact changes instead of using surveys, knobs or other easily biased measures of response, the present invention improves both the data that is recorded and the granularity of such data as physiological responses can be recorded many times per second.

In some embodiments, a receiving module 104 is operable to accept and/or record the physiological data of each of a plurality of viewers watching the media, wherein the physiological data may be measured and/retrieved via other means and/or from a storage.

In some embodiments, a defining module 105 is operable to define and mark occurrences and durations of one or more event types each having a plurality of event instances happening in the media. The duration of each of event instances in the media can be constant, non-linear, or semi-linear in time. In some embodiments, such event definition may happen after the physiological data of the viewers has been measured, where the defining module 105 can define the media into one or more event types each having a plurality of event instances in the media based on the physiological data measured from the plurality of viewers.

In some embodiments, a rating module 106 is operable to derive a plurality of physiological responses from the physiological data measured from the plurality of viewers and calculate a score for each of the plurality of event instances of one of the event types in the media based on the plurality of physiological responses. Here, the physiological response can be one or more of: thought, liking, engagement, immersion, physical engagement, valence, and vigor, wherein thought and liking can be calculated from EEG. The rating module is further operable to rate the specific event type by aggregating the scores of instances of the event type once such scores are calculated. In addition, the rating module may optionally rate the media by aggregating ratings of the event types in the media.

FIG. 2 (a)-(b) are flow charts illustrating exemplary processes to support media and events rating in accordance with one embodiment of the present invention. Although this figure depicts functional steps in a particular order for purposes of illustration, the process is not limited to any particular order or arrangement of steps. One skilled in the art will appreciate that the various steps portrayed in this figure could be omitted, rearranged, combined and/or adapted in various ways.

Referring to FIG. 2 (a), physiological data from each of a plurality of viewers watching a media is received or measured at step 201. The media can then be defined into a plurality of event types each having a plurality of event instances in the media based on the physiological data measured from the plurality of viewers at step 202. A plurality of physiological responses can be derived from the physiological data at step 203. At step 204, a score for each of the plurality of event instances of a specific event type is calculated based on the plurality of physiological responses, and step 205 rates the specific event type by aggregating the scores of the plurality of event instances of the specific event type. Step 204 and 205 can be repeated for each type in the media, and the media itself can be rated based on aggregated ratings of the event types in the media at step 206.

In some embodiments, the physiological data can be used to define the media into key, repeated event instances/types that are comparable across other media in the same genre. Referring to FIG. 2 (b), occurrences and durations of a plurality of event types each having a plurality of event instances in a media can be defined and/or marked at step 201, before physiological data from each of a plurality of viewers watching the media is received or measured at step 202. Step 203-206 are identical to those steps shown in FIG. 2(a).

In some embodiments, an integrated physiological sensing headset capable of sensing a plurality of measures of biological response can be placed on a viewer's head for measurement of his/her physiological data while the viewer is watching an event of the media. The data can be recorded in a program on a computer that allows viewers to interact with media while wearing the headset. FIG. 3 shows an exemplary integrated headset used with one embodiment of the present invention. Processing unit 301 is a microprocessor that digitizes physiological data and then processes it into physiological responses that include but are not limited to thought, engagement, immersion, physical engagement, valence, vigor and others. A three axis accelerometer 302 senses movement of the head. A silicon stabilization strip 303 allows for more robust sensing through stabilization of the headset that minimizes movement. The right EEG electrode 304 and left EEG electrode 306 are prefrontal dry electrodes that do not need preparation to be used. Contact is needed between the electrodes and skin but without excessive pressure. The heart rate sensor 305 is a robust blood volume pulse sensor positioned about the center of the forehead and a rechargeable or replaceable battery module 307 is located over one of the ears. The adjustable strap 308 in the rear is used to adjust the headset to a comfortable tension setting for many different head sizes.

In some embodiments, the integrated headset can be turned on with a push button and the viewer's physiological data is measured and recorded instantly. The data transmission can be handled wirelessly through a computer interface that the headset links to. No skin preparation or gels are needed on the viewer to obtain an accurate measurement, and the headset can be removed from the viewer easily and can be instantly used by another viewer, allows measurement to be done on many participants in a short amount of time and at low cost. No degradation of the headset occurs during use and the headset can be reused thousands of times.

In some embodiments, the viewers' physiological responses can be derived via a plurality of formulas, which use the physiological data of the viewers as inputs. Facial expression recognition, “knob” and other measures of emotion can also be used as inputs with comparable validity. Each of the derived physiological responses, which can include but are not limited to, “Engagement,” “Adrenaline,” “Thought,” and “Valence,” combines physiological data from multiple sensors into a multi-dimensional, simple-to-understand, representation of viewers' emotional response. FIG. 4(a) shows an exemplary trace of “Engagement” for a player playing Call of Duty 3 on the Xbox 360 measured in accordance with one embodiment of the present invention. The trace is a time based graph, with the beginning of the session on the left and the end on the right. Two sections (event instances) 401 and 402 are circled, where 401 on the left shows low “Engagement” during a game play that happens during a boring tutorial section. 402 shows a high “Engagement” section that has been recorded when the player experiences the first battle of the game.

In some embodiments, the viewers' physiological responses (e.g., strong, boring, funny, engaging, etc) over a large number of instances of each event type can be calculated, analyzed and correlated with the measures of such responses to individual event types (e.g., branding moment, product introduction, video game cut scene, fight, level restart, etc) to create a context-specific event profile for each event type. These profiles can then be used to rate each event instance that happens in a new piece of media, creating, in some cases, thousands to millions of individual bottom up measures of the media over up to hundreds to thousands of participating viewers. Combining this many individual scores greatly increases the accuracy of measurement of the overall media compared to asking survey questions and getting one hundred responses to 1 to 10 dimensions of subjective measures. For a non-limiting example of 100 viewers watching a movie having 1000 key event instances, 5 dimensions of physiological responses (e.g., thought, engagement, valence, immersion, physical engagement) are calculated for each of the viewers, and 6 math permutations (e.g., average value, deviation from mean, 1st order trend, 2nd order trend, positive response, negative response, etc) are calculated for each event instance based on the physiological responses of the viewers. Consequently, 3,000,000 (100*1000*5*6) pieces of scores are available to rate the movie vs. 100-1000 measures from surveys. These scores are then combined to create an overall rating for the movie, such rating may include but is not limited to, Individual event (scene) strength—did players like cut scenes, were jokes funny, overall quality of the events, strong and weak types of events, strong and weak events of the movie—the events in the middle had a strong response but the beginning ones did not.

In some embodiments, the occurrence and duration of an event instance or type can be defined and recorded. For a non-limiting example, an event type in a video game may be defined as occurring every time a “battle tank” appears in the player's screen and lasting as long as it remains on the screen. For another non-limiting example, an event in a movie may be defined as occurring every time a joke is made. An event type may be defined in such a way that an instance of the event type occurs only once for each piece of media. Alternatively, the event type may also be defined in such a way that many instances of the event type occur in a media.

In some embodiments, event instances can be tagged for each recorded piece of media, allowing for efficient and accurate conclusions to be made. For a non-limiting example, FIG. 4(b) shows two exemplary traces of the “Engagement” data of a video game player measured in accordance with one embodiment of the present invention. The boxes 403, 404, and 405 in the pictures correspond to a specific “weapon use” event type that has been tagged. At each point where the event instance appears, “Engagement” rises sharply. The picture in FIG. 4(b) shows one type of event being tagged, but the approach can be extended to many event instances being tagged with different event types, allowing the media to be sliced into pieces. For another non-limiting example, FIG. 4(c) shows exemplary vertical lines that divide the piece of media into event instances in accordance with one embodiment of the present invention. Key event types define every important thing that a player of the video game or other media may encounter and/or interact with. Here, the physiological data/response is overlaid with the tags of the event instances, and both can be toggled on and off.

In some embodiments, a score can be generated for an event instance based on the physiological data or response of the viewer during the event instance using a formula or rule. In one embodiment, the formula can be based on expert knowledge of the desired response to the event type of the instance and the formula can take the form of a weighted sum of the changes in each of the derived physiological responses across the event instance. For a non-limiting example, the formula can be defined by a weighted sum of multiple inputs from each of physiological responses over time (vector), wherein each of the vectors may rise, fall, peak, reach high, reach low, or have a distinct profile. For a non-limiting example, there can be a profile of the physiological response to punch lines in jokes that correlates with how good the joke is based on the analysis of many advertisements. There can be two aspects of the profile: the first is that the “Thought” vector of physiological response must increase, showing that the viewer thought about what was happening directly before the punch line and during the first part of the punch line; the second is that the “Valence” or reward feeling for viewers must increase once the punch line is given, indicating that the viewers liked the punch line after engaging in thinking about the punch line. Thus, a mathematical profile of rise in Thought and Valence at specific times is created for the event type of a joke. Such profile can then be applied to each instance of a joke to assess the effectiveness of the punch line of the joke. Punch lines that do not fit this response profile will not create a good experience in viewers.

FIG. 5 shows an exemplary profile of Joke Punchlines in an advertisement as generated in accordance with one embodiment of the present invention. The profile can be created either through expert knowledge of the subject matter or through a mathematical formula. If the physiological response of an instance of this event type matches this profile, the event instance is considered a success. For a non-limiting example, the following formula can be used to calculate the score of an instance of the joke:

Score=0.25×(Thought Rose during punch line)+0.75×(Valence rose after punch line)

Where the resulting weights are 25% based on Thought rising during the punch line and 75% based on Valence rising after the punch line.

In some embodiments, scores of event instances in the media can be used to pinpoint whether and/or which of the event instances need to be improved or changed, and which of the event instances should be kept intact based on the physiological responses from the viewers. In the non-limiting example above, a punch line that does not fit its response profile and thus does not create a good experience in viewers should be improved.

In some embodiments, the number of variables used in the scoring formula can be very large and the formula can also be a higher ordered polynomial to account for non-linear scoring if need be. For a non-limiting example, a more complex version of the formula shown above would calculate the score based on how much thought and how much positive valence there is at each point during the joke. This would penalize small increases in Thought and Valence where people did not strongly engage in the joke, while rewarding punch lines which had very large rises in Thought and Valence, corresponding to strong engagement in the joke.

In some embodiments, a set of logical rules can be adopted, which define an event instance as “good” or “successful” as having a score above a predetermined number, whereby the formula outputs a score reflecting how engaging the event instance is. Other embodiments use the score for rankings or ratings are also possible. Referring back to the non-limiting example shown in FIG. 4(b) where a weapon event type is tagged, the simple explanation of the profile for this event type is that if Engagement rises strongly, an event instance of the type is good. In this example, all event instances are good, which would lead to a high score for the event type. This calculation scheme can be done over hundreds of instances of multiple key event types.

In some embodiments, the formula can utilize prior instances of similar event types in the current and/or other pieces of media to calculate the score of the instance. A set of rules can be created with viewers' physiological responses across those other similar events as inputs. For a non-limiting example, a score of 1 (representing “good” or “successful”) could be given to an instance of an event type if the slope of Engagement over the event exceeds the average slope of Engagement over other event instances of similar event types in other pieces of media. The exact implementation of this approach can be done many ways, and the following process is a non-limiting example of such implementation:

• • 1. Tagging a large set of instances of an event type in the media along with the physiological responses from the viewers of these instances.
  • 2. Choosing a rating mechanism to allow for each instance of the event type to be rated.
  • 3. Calculating various different mathematical measures of the physiological responses from the viewers over an event instance. Such measures may include but are not limited to, average, 1 st order derivative, 2nd order derivative, polynomial approximations, (standard) deviations from the mean, (standard) deviations of derivatives from the mean, and profiles of the physiological responses, which can be implemented with convolution or other methods that takes into account one or more of: peaking in the middle, spiking in the beginning, being flat, etc.
  • 4. Repeating calculation at step 3 for all physiological responses.
  • 5. Transforming the large number of measures into defined outcome (score) for the event instance. Such transformation can be done via one or more of: convolution, weighted sum, positive or negative slope, a polynomial formula, least squares, support vector machines, neural networks and other machine learning approaches.
  • 6. Repeating transformation at step 5 for all instances of the event type. A ranking, rating or score for each individual event instance can be calculated via this or any other similar approaches, allowing instances of an event type to be compared objectively.

In some embodiments, a subset of the overall population of viewers can be aggregated to differentiate the responses for the subset, which groups the viewers by one or more of: race, gender, age, buying habits, demographics, and income. The averaged rating of the event type can then be associated and/or compared to such grouping of the viewers.

In some embodiments, the scores of event instances of an event type can be aggregated as input to a formula used to rate of the event type, where the formula may be mathematical or may be logical; it may also be designed by expert knowledge or by previous ratings of similar event types. Such aggregation can be done via one or more of:

• • Averaging for each event type. This approach averages the scores of all event instances of the event type throughout the media and also over many viewers.
  • Performance. A simple average may not always give an accurate view of the overall performance of the media. For a non-limiting example, if 75% of event instances are very highly rated, while the rest are mediocre, the overall rating of the event type may be around 75-80%, which could seem to be good. In reality however, the viewers who watch the media will not like one quarter of the media, which leads to a very low score. A performance metric takes into account the distribution of scores of instances of the event type. Using prior distributions of the instances as a reference, the performance metric can define how good the overall distribution of the instances is and if viewers will like the event type/media or not. One non-limiting implementation of performance metric can be done through histogram matching for the event type.
  • “Success” ratio. The formulas output a “success” ratio in percentage points, or another score for each event type. More specifically, a “success” ratio of an event type can be defined via an aggregated view of the performance of the event type/media in a specific aspect characterized by the definition of the event type, and a “success” ratio above a predetermined number is defined to be a successful event type.

In some embodiments, the rating process described above can be repeated for different types of events within the same media. In addition, the media itself can be rated with the ratings of different event types used as inputs to a rating formula. This rating formula or rule can also be based on expert knowledge or previous physiological response to the media as described above. For a non-limiting example, a media can be rated as “success” if a majority of its event types are rated as “success.” Alternatively, a media can be rated as “success” its event types are rated as “success” more than other comparable media. Other rules, linear or other rating scales can also be used. FIG. 6 shows overall event ratings for three exemplary types of events in two movies calculated in accordance with one embodiment of the present invention. The first movie is an action movie and the response to the “Action Packed” and “Suspenseful” event types is very strong while the “Funniness” event type, such as jokes do not create a strong response. The second movie is a comedy, which creates the opposite responses compared to the action movie. Both movies are given a high rating because the event types have the correct profile for a successful movie in their genre.

One embodiment may be implemented using a conventional general purpose or a specialized digital computer or microprocessor(s) programmed according to the teachings of the present disclosure, as will be apparent to those skilled in the computer art. Appropriate software coding can readily be prepared by skilled programmers based on the teachings of the present disclosure, as will be apparent to those skilled in the software art. The invention may also be implemented by the preparation of integrated circuits or by interconnecting an appropriate network of conventional component circuits, as will be readily apparent to those skilled in the art.

One embodiment includes a computer program product which is a machine readable medium (media) having instructions stored thereon/in which can be used to program one or more computing devices to perform any of the features presented herein. The machine readable medium can include, but is not limited to, one or more types of disks including floppy disks, optical discs, DVD, CD-ROMs, micro drive, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of media or device suitable for storing instructions and/or data. Stored on any one of the computer readable medium (media), the present invention includes software for controlling both the hardware of the general purpose/specialized computer or microprocessor, and for enabling the computer or microprocessor to interact with a human viewer or other mechanism utilizing the results of the present invention. Such software may include, but is not limited to, device drivers, operating systems, execution environments/containers, and applications.

The foregoing description of the preferred embodiments of the present invention has been provided for the purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations will be apparent to the practitioner skilled in the art. Particularly, while the concept “module” is used in the embodiments of the systems and methods described above, it will be evident that such concept can be interchangeably used with equivalent concepts such as, class, method, type, interface, bean, component, object model, and other suitable concepts. Embodiments were chosen and described in order to best describe the principles of the invention and its practical application, thereby enabling others skilled in the art to understand the invention, the various embodiments and with various modifications that are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the following claims and their equivalents.

Claims

1. A system to support media and events rating, comprising: one or more sensors operable to measure physiological data from each of a plurality of viewers watching a media;a defining module operable to define the media into one or more event types each having a plurality of event instances in the media based on the physiological data measured from the plurality of viewers; anda rating module operable to: derive a plurality of physiological responses from the physiological data measured from the plurality of viewers;calculate a score for each of the plurality of event instances of a specific one of the one or more event types in the media based on the plurality of physiological responses; andrate the specific one event type by aggregating the scores of the plurality of event instances of the specific one event type.

2. A system to support media and events rating, comprising: a defining module operable to define and mark occurrences and durations of one or more event types each having a plurality of event instances in a media; anda receiving module operable to accept physiological data from each of a plurality of viewers watching the media;a rating module operable to: derive a plurality of physiological responses from the physiological data;calculate a score for each of the plurality of event instances of a specific one of the one or more event types in the media based on the plurality of physiological responses; andrate the specific one event type by aggregating the scores of the plurality of event instances of the specific one event type.

3. The system of claim 2, wherein: the receiving module is further operable to record the physiological data measured from each of the plurality of viewers watching the media.

4. The system of claim 1, wherein: the media is one of: a movie, a video, a television program, a television commercial, an advertisement, a video game, an interactive online media, a print and any other media from which a viewer can learn information or be emotionally impacted.

5. The system of claim 1, wherein: duration of each of the one or more event types in the media is constant, non-linear, or semi-linear in time.

6. The system of claim 1, wherein: each of the one or more sensors is one of: an electroencephalogram, an accelerometer, a blood oxygen sensor, a galvanometer, an electromygraph, and any other physiological sensor.

7. The system of claim 1, wherein: the one or more sensors include an integrated sensor headset comprising one or more of: one or more axis accelerometers;one or more EEG electrodes;one or more heart rate sensors; anda processing unit.

8. The system of claim 1, wherein: the physiological data is one or more of: heart rate, brain waves, EEG signals, blink rate, breathing, motion, muscle movement, galvanic skin response and any other response correlated with changes in emotion.

9. The system of claim 1, wherein: the physiological responses are one or more of: thought, liking, engagement, immersion, physical engagement, valence, and vigor in the media.

10. The system of claim 1, wherein: the rating module is further operable to: calculate one of more of the following mathematical measures of the plurality of physiological responses: average, derivative, polynomial approximation, deviation from the mean, and deviation of the derivative from the mean; andtransform the mathematical measures into score for each of the plurality of event instances of the specific one event type via one or more of: convolution, weighted sum, positive or negative slope, a polynomial formula, a least squares formula, a support vector machine, and a neural network.

11. The system of claim 1, wherein: the rating module is further operable to calculate the score for each of the plurality of event instances of the specific one event type using one or more of: a formula, a rule, prior instances of the specific one event type in this or other media of same genre, or a profile of one or more the plurality of physiological responses to the specific one event type.

12. The system of claim 11, wherein: the rating module is further operable to calculate a good score for an event instance of the specific one event type if the physiological responses to the event instance matches the profile.

13. The system of claim 11, wherein: the rating module is further operable to pinpoint one or more of the plurality of event instances of the specific one event type that need to be improved or changed based on their scores.

14. The system of claim 11, wherein: the rating module is further operable to define the profile based on one or more of: expert knowledge, physiological responses to similar event types, and data from other media.

15. The system of claim 1, wherein: the rating module is further operable to rate the specific one event type by one or more of:averaging, performance, a mathematical formula, and a logic formula.

16. The system of claim 1, wherein: the rating module is further operable to rate the media by aggregating ratings of the one or more event types in the media.

17. The system of claim 1, wherein: the rating module is further operable to display the score/rating of one or more of: the media, the specific one event type, and the plurality of event instances of the specific one event type.

18. The system of claim 1, wherein: the rating module is further operable to: group the plurality of viewers by one or more of race, gender, age, demographics, income, habits, and interests; andassociate and/or compare the score/rating of one or more of the media, the specific one event type, and the plurality of event instances of the specific one event type according to such grouping of the plurality of viewers.

19. A method to support media and events rating, comprising: receiving and/or measuring physiological data from each of a plurality of viewers watching a media;defining the media into one or more event types each having a plurality of event instances in the media based on the physiological data measured from the plurality of viewers;deriving a plurality of physiological responses from the physiological data;calculating a score for each of the plurality of event instances of a specific one of the one or more event types in the media based on the plurality of physiological responses; andrating the specific one event type by aggregating the scores of the plurality of event instances of the specific one event type.

20. A method to support media and events rating, comprising: defining and marking occurrences and durations of one or more event types each having a plurality of event instances in a media;receiving and/or measuring physiological data from each of a plurality of viewers watching the media;derive a plurality of physiological responses from the physiological data;calculating a score for each of the plurality of event instances of a specific one of the one or more event types in the media based on the plurality of physiological responses; andrating the specific one event type by aggregating the scores of the plurality of event instances of the specific one event type.

21. The method of claim 19, further comprising: calculating one of more of the following mathematical measures of the physiological data:average, derivative, polynomial approximation, deviation from the mean, and deviation of the derivative from the mean; andtransforming the mathematical measures into score for each of the plurality of event instances of the specific one event type via one or more of: convolution, weighted sum, positive or negative slope, a polynomial formula, a least squares formula, a support vector machine, and a neural network.

22. The method of claim 19, further comprising: calculating the score for each of the plurality of event instances of the specific one event type using one or more of: a formula, a rule, prior instances of the specific one event type in this or other media of same genre, or a profile of one or more of the plurality of physiological responses to the specific one event type.

23. The method of claim 22, further comprising: calculating a good score for an event instance of the specific one event type if the physiological responses to the event instance matches the profile.

24. The method of claim 22, further comprising: pinpointing one or more of the plurality of event instances that need to be improved or changed based on their scores.

25. The method of claim 22, further comprising: defining the profile based on one or more of: expert knowledge, physiological responses to similar event types, and data from other media.

26. The method of claim 19, further comprising: rating the specific one event type by one or more of: averaging, performance, a mathematical formula, and a logic formula.

27. The method of claim 19, further comprising: rating the media by aggregating ratings of the one or more event types in the media.

28. The method of claim 19, further comprising: recording the physiological data measured from each of the plurality of viewers watching the media.

29. The method of claim 19, further comprising: displaying the score/rating of one or more of: the media, the specific one event type, and the plurality of event instances of the specific one event type.

30. The method of claim 19, further comprising: grouping the plurality of viewers by one or more of race, gender, age, demographics, income, habits, and interests; andassociating and/or comparing the score/rating of one or more of the media, the specific one event type, and the plurality of event instances of the specific one event type according to such grouping of the plurality of viewers.

31. A machine readable medium having instructions stored thereon that when executed cause a system to: receive and/or measure physiological data from each of a plurality of viewers watching a media;define the media into one or more event types each having a plurality of event instances in the media based on the physiological data measured from the plurality of viewers;derive a plurality of physiological responses from the physiological data;calculate a score for each of the plurality of event instances of a specific one of the one or more event types in the media based on the plurality of physiological responses; andrate the specific one event type by aggregating the scores of the plurality of event instances of the specific one event type.

32. A system to support media and events rating, comprising: means for defining and marking occurrences and durations of one or more event types each having a plurality of event instances in a media;means for receiving and/or measuring physiological data from each of a plurality of viewers watching the media;means for derive a plurality of physiological responses from the physiological data;means for calculating a score for each of the plurality of event instances of a specific one of the one or more event types in the media based on the plurality physiological responses; andmeans for rating the specific one event type by aggregating the scores of the plurality of event instances of the specific one event type.