Electronic communication warning and modification

• US 9,402,576 B2
• Filed: 09/12/2012
• Issued: 08/02/2016
• Est. Priority Date: 09/12/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kanevsky, Dimitri, Kozloski, James R., Pickover, Clifford A., Sainath, Tara N
• Primary Examiner(s): KHAN, AFTAB N
• Application Number:
  US13/611,406
• Publication Number:
  US 20140074943A1
• Time in Patent Office: 1,420 Days
• Field of Search: 709/206, 709/207, 715/752, 715/753, 707/100
• US Class Current: 1/1
• CPC Class Codes: A61B 5/163 by tracking eye movement, gaze, or pupil change
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: H04L 51/212 using filtering or selective blocking

Abstract

Techniques for electronic communication warning and modification. A method includes automatically detecting an emotional state of a sender of an electronic communication, encoding the detected emotional state of the sender, using input from at least one additional source, as metadata, embedding the metadata in the electronic communication to create an annotated version of the electronic communication, and transmitting the annotated version of the electronic communication to a recipient.

Claims

1. A method for exchanging an electronic communication in annotated form based on a detected emotional state of a sender of the electronic communication, the method comprising the following steps:

automatically detecting an emotional state of the sender of the electronic communication wherein said automatically detecting comprises;

analyzing sender biometrics comprising one or more physiological measurements and/or one or more motor-behavioral measurements derived from engagement with a keyboard, a pointer and/or a touch-screen of a sender device used by the sender to generate the electronic communication; and

correlating, via a hardware processor, said sender biometrics with multiple biometric measurements amassed in a database using one or more statistical learning methods, wherein the multiple biometric measurements amassed in the database correspond to one or more emotional states;

encoding the detected emotional state of the sender, using input from at least one additional source, as metadata;

embedding the metadata in the electronic communication to create an annotated version of the electronic communication;

delaying transmission of the annotated version of the electronic communication to a recipient by a pre-determined amount of time that is a function of;

(i) a moving average of the detected emotional state of the sender computed over a given interval of time and (ii) an evaluated amount of a risk of miscommunication, evaluated based on content of the electronic communication, in relation to a given risk of communication threshold;

redirecting, during the pre-determined amount of time associated with said delaying, (i) the annotated version of the electronic communication to a designated third party reviewer and (ii) an alert to the designated third party reviewer that a review and/or an automated mediation between the sender and the designated third party reviewer is required, wherein said redirecting is based on the detected emotional state of the sender, and wherein the designated third party reviewer comprises at least one of (a) a caregiver of the sender, (b) a manager of the sender, and (c) an individual identified as trusted by the sender;

providing a signal to the sender in connection with said delaying, wherein said signal comprises;

a notification of said delaying of the transmission of the annotated version of the electronic communication to the recipient; and

a prompt enabling the sender to modify the pre-determined amount of time of said delaying via one or more mechanisms;

extracting the metadata from the annotated version of the electronic communication of the recipient;

converting the metadata into a representation of the detected emotional state of the sender to present to the recipient with the annotated version of the electronic communication, wherein said converting comprises implementing a machine-learning element to interpret a context of the recipient based on the detected emotional state of the sender, and in accordance with one or more user attributes derived from a user profile of the recipient; and

transmitting, subsequent to (a) said delaying by the pre-determined amount of time and (b) said redirecting, (i) the representation of the emotional state of the sender and (ii) the annotated version of the electronic communication to the recipient in accordance with at least one pre-determined preference specified by the recipient in a recipient profile;

wherein at least one or more of the steps are carried out via a processor.

2. The method of claim 1, wherein the electronic communication comprises an email, an instant message, a voice mail, a communication in a virtual universe, an animated communication, a video segment, a text message, a tweet, and/or a forwarding of a separate message.

3. The method of claim 1, wherein the at least one pre-determined recipient preference comprises receiving the annotated version of the electronic communication in computer graphic form and/or in audio form.

4. The method of claim 1, wherein the representation of the detected emotional state of the sender is in a form of a graphic, a color change, an animation, a sound, and/or at least one keyword.

5. The method of claim 1, further comprising:

receiving input from the recipient and/or a third party.

6. The method of claim 1, further comprising:

receiving input from the sender, recipient, and/or third party in a form of a subsequent training to provide notification that the emotional state was not represented appropriately to the recipient.

7. The method of claim 1, wherein said automatically detecting the emotional state of the sender comprises analyzing at least one of sender typing speed, sender typing errors, and sender typing rhythm.

8. The method of claim 1, wherein said automatically detecting the emotional state of the sender comprises analyzing sender biometrics derived from eye tracking.

9. The method of claim 1, wherein said automatically detecting the emotional state of the sender comprises analyzing the sender voice characteristic.

10. The method of claim 1, further comprising:

providing the sender with a notification of the detected emotional state, wherein the notification comprises at least one of an audio message, a tactile message, a speech message, a tone, an image, a lack of responsiveness in a communication device, a vibration, a color change on a screen, a change in avatar appearance in a virtual world, and a change of appearance of an environment in a virtual world.

11. The method of claim 1, wherein said automatically detecting the emotional state of the sender comprises analyzing gesture recognition of the sender.

12. The method of claim 1, wherein said automatically detecting the emotional state of the sender comprises scanning the electronic communication to identify one or more keywords that indicate a particular emotional state of the sender.

13. The method of claim 12, wherein said identifying one or more keywords that indicate a particular emotional state is based on discovered and/or learned emotional states derived in connection with user feedback.

14. A method for automatically managing a transmission of an electronic communication based on an emotional state of a sender of the electronic communication, the method comprising:

automatically detecting the emotional state of the sender of the electronic communication wherein said automatically detecting comprises;

analyzing sender biometrics comprising one or more physiological measurements and/or one or more motor-behavioral measurements derived from engagement with a keyboard, a pointer and/or a touch-screen of a sender device used by the sender to generate the electronic communication;

correlating, via a hardware processor, said sender biometrics with multiple biometric measurements amassed in a database, wherein the multiple biometric measurements amassed in the database using one or more statistical learning methods, correspond to one or more emotional states;

generating a representation of the detected emotional state of the sender to present to a given recipient with the annotated version of the electronic communication, wherein said generating comprises implementing a machine-learning element to interpret a context of the given recipient based on the detected emotional state of the sender, and in accordance with one or more user attributes derived from a user profile of the given recipient;

providing the sender of the electronic communication with a notification of the detected emotional state of the sender;

delaying transmission of the electronic communication to the given recipient by a pre-determined amount of time that is a function of;

(i) a moving average of the detected emotional state of the sender computed over a given interval of time and (ii) an evaluated amount of a risk of miscommunication, evaluated based on content of the electronic communication, in relation to a given risk of communication threshold;

providing a signal to the sender in connection with said delaying, wherein said signal comprises;

a notification of said delaying of the transmission of the an electronic communication to the recipient; and

a prompt enabling the sender to modify the pre-determined amount of time of said delaying via one or more mechanisms; and

deploying an action to facilitate modification and/or cancellation of the transmission of the electronic communication during said delaying, wherein said action comprises redirecting (i) the electronic communication to a designated third party reviewer and (ii) an alert to the designated third party reviewer that a review and/or an automated mediation between the sender and the designated third party reviewer is required, wherein said redirecting is based on the detected emotional state of the sender, and wherein the designated third party reviewer comprises at least one of (a) a caregiver of the sender, (b) a manager of the sender, and (c) an individual identified as trusted by the sender.

15. The method of claim 14, wherein the notification comprises at least one of an audio message, a tactile message, a speech message, a tone, an image, a lack of responsiveness in a communication device, a vibration, a color change on a screen, a change in avatar appearance in a virtual world, and a change of appearance of an environment in a virtual world.