AUTOMATED RECEIVER MESSAGE SENTIMENT ANALYSIS, CLASSIFICATION AND PRIORITIZATION

• US 20180089168A1
• Filed: 09/26/2016
• Published: 03/29/2018
• Est. Priority Date: 09/26/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Arquero, Gregg M., Dow, Eli M., Hossain, Syed F., Schaeffer, Joshua, Tang, Yunli
• Granted Patent: US 10,007,661 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/151 Transformation
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: H04L 51/046 Interoperability with other network applications or services
• CPC Class Codes: H04L 51/224 providing notification on incoming messages, e.g. pushed notifications of received messages
• CPC Class Codes: H04L 51/226 Delivery according to priorities

Abstract

Techniques are provided for performing automated operations to analyze and prioritize incoming user messages. An indication of a message sent to a recipient user is received. Based at least in part on configuration information associated with the recipient user, the received message is analyzed. Analyzing the received message includes at least one of determining sentiments associated with the received message, determining intentions associated with the received message, determining document classes associated with the received message, and generating summary information corresponding to the received message. Based at least in part on the analyzing of the received message, a prioritized listing of multiple messages associated with the recipient user, including the received message, is displayed to the recipient user.

Claims

1. A computer-implemented method for analyzing and prioritizing incoming user messages comprising:

receiving, by one or more computing systems, an indication of a message sent to a recipient user;

analyzing, by the one or more computing systems and based at least in part on one or more natural-language processing libraries and on configuration information associated with the recipient user, a received message, wherein analyzing the received message includes;

determining, by a classification engine of the one or more computing systems, one or more document classes associated with the received message, wherein the determining one or more document classes is based at least on key sentences extracted from text within a body of the received message;

performing intention analysis of the received message in order to determine one or more intentions associated with the received message, wherein the intentions correspond to different types of sentiment comprising an angry sentiment, an unhappy sentiment, and a neutral sentiment; and

generating, by the one or more computing systems, summary information corresponding to the received message, wherein the generating summary information is based at least on the key sentences extracted from text within the body of the received message; and

displaying, by the one or more computing systems and based at least in part on the analyzing of the received message, a prioritized listing to the recipient user of multiple messages associated with the recipient user, wherein the prioritized listing of multiple messages includes the received message, the prioritized listing of multiple messages are prioritized by sentiment type, the topmost messages of the prioritized listing of multiple messages are associated with the angry sentiment, messages associated with the unhappy sentiment are listed subsequent to the messages associated with the angry sentiment, and messages associated with the neutral sentiment are listed subsequent to the messages associated with the unhappy sentiment.

2. The computer-implemented method of claim 1 wherein analyzing the received message includes generating summary information corresponding to the received message, and wherein generating summary information corresponding to the received message includes extracting one or more key sentences from the received message.

3. The computer-implemented method of claim 1 wherein analyzing the received message includes determining one or more sentiments associated with the received message, and wherein the method further comprises determining one or more additional sentiments associated with each of at least some of the multiple messages.

4. The computer-implemented method of claim 3 wherein displaying the prioritized listing of the multiple messages associated with the recipient user includes displaying an indication of at least one of the one or more sentiments associated with each of the at least some of the multiple messages.

5. The computer-implemented method of claim 3 wherein the method further comprises determining an aggregate sentiment associated with the at least some of the multiple messages, and wherein displaying the prioritized listing of the multiple messages associated with the recipient user includes displaying an indication of the aggregate sentiment.

6. The computer-implemented method of claim 5, further comprising providing an indication of the aggregate sentiment to one or more users other than the recipient user associated with the multiple messages.

7. The computer-implemented method of claim 1 wherein analyzing the received message includes determining one or more document classes associated with the received message, wherein the method further comprises determining one or more additional document classes associated with each of at least some of the multiple messages, and wherein displaying the prioritized listing of the multiple messages associated with the recipient user includes displaying an indication of at least one of the one or more document classes associated with each of the at least some of the multiple messages.

8. The computer-implemented method of claim 1 wherein the received message is an e-mail message, and wherein the configuration information associated with the recipient user is provided via a software application plugin executed in conjunction with an email client of the recipient user.

9. The computer-implemented method of claim 1 wherein analyzing the received message includes determining one or more intentions associated with the received message, and wherein determining the one or more intentions includes determining an action time associated with at least one or the one or more intentions.

10. The computer-implemented method of claim 9 wherein displaying the prioritized listing of the multiple messages is further based on the determined action time associated with the at least one intention.

11. The computer-implemented method of claim 1, further comprising:

analyzing at least some of the multiple messages in a manner substantially similar to the analyzing of the received message, and

prior to displaying the prioritized listing of the multiple messages, prioritizing the multiple messages based on the analyzing of the at least some of the multiple messages.

12. A non-transitory computer-readable medium having stored contents that, when executed, configure a computing system to perform a method for analyzing and prioritizing incoming user messages, the method comprising:

receiving, by the configured computing system, an indication of a message sent to a recipient user;

analyzing, by the configured computing system and based at least in part on one or more natural-language processing libraries and on configuration information associated with the recipient user, a received message, wherein analyzing the received message includes;

determining, by a classification engine of the configured computing system, one or more document classes associated with the received message, wherein the determining one or more document classes is based at least on key sentences extracted from text within a body of the received message;

performing intention analysis of the received message in order to determine one or more intentions associated with the received message, wherein the intentions correspond to different types of sentiment comprising an angry sentiment, an unhappy sentiment, and a neutral sentiment; and

generating, by the configured computing system, summary information corresponding to the received message, wherein the generating summary information is based at least on the key sentences extracted from text within the body of the received message; and

displaying, by the configured computing system and based at least in part on the analyzing of the received message, a prioritized listing to the recipient user of multiple messages associated with the recipient user, wherein the prioritized listing of multiple messages includes the received message, the prioritized listing of multiple messages are prioritized by sentiment type, the topmost messages of the prioritized listing of multiple messages are associated with the angry sentiment, messages associated with the unhappy sentiment are listed subsequent to the messages associated with the angry sentiment, and messages associated with the neutral sentiment are listed subsequent to the messages associated with the unhappy sentiment.

13. The non-transitory computer-readable medium of claim 12 wherein analyzing the received message includes generating summary information corresponding to the received message, and wherein generating summary information corresponding to the received message includes extracting one or more key sentences from the received message.

14. The non-transitory computer-readable medium of claim 12 wherein analyzing the received message includes determining one or more sentiments associated with the received message, and wherein the method further comprises determining one or more additional sentiments associated with each of at least some of the multiple messages.

15. The non-transitory computer-readable medium of claim 14 wherein displaying the prioritized listing of the multiple messages associated with the recipient user includes displaying an indication of at least one of the one or more sentiments associated with each of the at least some of the multiple messages.

16. The non-transitory computer-readable medium of claim 14 wherein the method further comprises determining an aggregate sentiment associated with the at least some of the multiple messages, and wherein displaying the prioritized listing of the multiple messages associated with the recipient user includes displaying an indication of the aggregate sentiment.

17. The non-transitory computer-readable medium of claim 16, further comprising providing an indication of the aggregate sentiment to one or more users other than the recipient user associated with the multiple messages.

18. The non-transitory computer-readable medium of claim 12 wherein analyzing the received message includes determining one or more document classes associated with the received message, wherein the method further comprises determining one or more additional document classes associated with each of at least some of the multiple messages, and wherein displaying the prioritized listing of the multiple messages associated with the recipient user includes displaying an indication of at least one of the one or more document classes associated with each of the at least some of the multiple messages.

19. The non-transitory computer-readable medium of claim 12 wherein the received message is an e-mail message, and wherein the configuration information associated with the recipient user is provided via a software application plugin executed in conjunction with an email client of the recipient user.

20. A system, comprising:

one or more processors; and

at least one memory, the memory including instructions that, upon execution by at least one of the one or more processors, cause the system to perform a method for analyzing and prioritizing incoming user messages, the method comprising;

receiving an indication of a message sent to a recipient user;

analyzing a received message based at least in part on one or more natural-language processing libraries and on configuration information associated with the recipient user, wherein analyzing the received message includes;

determining one or more document classes associated with the received message, wherein the determining one or more document classes is based at least on key sentences extracted from text within a body of the received message;

performing intention analysis of the received message in order to determine one or more intentions associated with the received message, wherein the intentions correspond to different types of sentiment comprising an angry sentiment, an unhappy sentiment, and a neutral sentiment; and

generating summary information corresponding to the received message, wherein the generating summary information is based at least on the key sentences extracted from text within the body of the received message; and

displaying, based at least in part on the analyzing of the received message, a prioritized listing to the recipient user of multiple messages associated with the recipient user, wherein the prioritized listing of multiple messages includes the received message, the prioritized listing of multiple messages are prioritized by sentiment type, the topmost messages of the prioritized listing of multiple messages are associated with the angry sentiment, messages associated with the unhappy sentiment are listed subsequent to the messages associated with the angry sentiment, and messages associated with the neutral sentiment are listed subsequent to the messages associated with the unhappy sentiment.