Cross-lingual seeding of sentiment

• US 9,438,732 B2
• Filed: 09/09/2013
• Issued: 09/06/2016
• Est. Priority Date: 04/08/2013
• Status: Active Grant

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Incorporated
• Inventors: Skiba, David, Erhart, George W., Becker, Lee, Matula, Valentine C.
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US14/021,889
• Publication Number:
  US 20140303981A1
• Time in Patent Office: 1,093 Days
• Field of Search: 704/270, 704 7- 10
• US Class Current: 1/1
• CPC Class Codes: A47L 13/20 Mops
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: H04L 51/046 Interoperability with other network applications or services
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04M 2201/18 Comparators
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 2203/551 Call history recording a computer conference H04L12/1831
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A contact center system can receive messages from social media sites or centers. The messages may be in a foreign language. The system can review messages by identifying content in the social media messages with negative/positive sentiment and then identify a seed term in the messages. A seed term can be a word in another language, different from the message body. The seed term is then used to find one or more other words, in the foreign language, that are correlated with the seed term. The identification of the found words in other messages can then be used to determine sentiment in the foreign language.

Claims

1. A communication system comprising:

a social media gateway in communication with a social media network, the social media gateway operable to receive a social media message, from a customer, on the social media network;

a dialog system in communication with the social media gateway, the dialog system operable to determine an agent routing for the social media message, wherein the dialog system compromises;

a text processing component that is operable to receive and analyze the social media message, wherein the text processing component compromises;

a seed term identifier operable to;

receive a first message in a foreign language; and

identify a seed term within the first message, wherein the seed term is in a different language;

a negative/positive term identifier in communication with the seed term identifier, wherein the negative/positive term identifier is operable to analyze the first message for a sentiment term in the foreign language;

a parser in communication with the negative/positive term identifier, wherein the parser is operable to store the sentiment term; and

the negative/positive message identifier in communication with the parser, wherein the negative/positive message identifier is operable to;

retrieve the sentiment term with known sentiment in the foreign language;

identify the sentiment term, associated with the seed term, in a second message; and

based on the identification of the sentiment term, determine that the second message has a known sentiment.

2. The communication system as defined in claim 1, further comprising a statistics analyzer in communication with the parser, wherein the statistics analyzer is operable to determine statistical information about the sentiment term, wherein the statistical information includes a confidence score that the sentiment term indicates a sentiment.

3. The communication system as defined in claim 2, wherein the statistics analyzer is further operable to:

determine if the confidence score reaches or crosses a predetermined threshold;

if the confidence score reaches or crosses the predetermined threshold, signify that the sentiment term indicates the known sentiment;

if the confidence score does not reach or cross the predetermined threshold, receive a third message; and

instructions to re-calculate the confidence score using analysis associated with the third message.

4. The communication system as defined in claim 3, wherein each seeding term includes two or more sentiment terms associated therewith.

5. The communication system as defined in claim 4, wherein each message includes two or more seeding terms, and wherein at least one of the seeding terms is in English.

6. A method for determining sentiment in a foreign language, the method comprising:

receiving a social media message, with a social media gateway in communication with a social media network, from a customer on the social media network;

determining an agent routing for the social media message, with a dialog system in communication with the social media gateway;

receiving and analyzing the social media message with a text processing component of the dialog system, the text processing component comprising a seed term identifier;

receiving, with the seed term identifier, a first message in a foreign language;

identifying, with the seed term identifier, a seed term within the first message, wherein the seed term is in a different language;

analyzing, with a negative/positive term identifier in communication with the seed term identifier, the first message for a sentiment term in the foreign language;

storing, with a parser in communication with the negative/positive term identifier, the sentiment term;

retrieving, with the negative/positive message identifier in communication with the parser, the sentiment term with known sentiment in the foreign language;

identifying, with the negative/positive message identifier in communication with the parser, the sentiment term, associated with the seed term, in a second message; and

based on the identification of the sentiment term, determining, with the negative/positive message identifier in communication with the parser, that the second message has a known sentiment.

7. The method as defined in claim 6, further comprising:

determining statistical information about the sentiment term.

8. The method as defined in claim 7, wherein the statistical information includes a confidence score that the sentiment term indicates a sentiment, and wherein the sentiment may be positive or negative.

9. The method as defined in claim 8, wherein the confidence score is a probability, the method further comprising:

determining if the confidence score reaches or crosses a predetermined threshold; and

if the confidence score reaches or crosses the predetermined threshold, signifying that the sentiment term indicates the known sentiment.

10. The method as defined in claim 9, further comprising:

if the confidence score does not reach or cross the predetermined threshold, receiving a third message;

re-calculating the confidence score using analysis associated with the third message.

11. The method as defined in claim 10, wherein each seeding term includes two or more sentiment terms associated therewith.

12. The method as defined in claim 11, wherein each message includes two or more seeding terms.

13. The method as defined in claim 12, wherein at least one of the seeding terms is in English.

14. The method as defined in claim 13, further comprising:

analyzing a known negative/positive message;

identifying seeding terms; and

storing the seeding terms.

15. A non-transitory computer readable medium having stored thereon processor executable instructions that cause a computing system to execute a method for generating an agent routing, the instructions comprising:

instructions to receive a social media message, with a social media gateway in communication with a social media network, from a customer on the social media network;

instructions to determine an agent routing for the social media message, with a dialog system in communication with the social media gateway;

instructions to receive and analyze the social media message with a text processing component of the dialog system, the text processing component comprising a seed term identifier;

instructions to receive, with the seed term identifier, a first message in a foreign language;

instructions to identify, with the seed term identifier, a seed term within the first message, wherein the seed term is in a different language;

instructions to analyze, with a negative/positive term identifier in communication with the seed term identifier, the first message for a sentiment term in the foreign language;

instructions to store, with a parser in communication with the negative/positive term identifier, the sentiment term;

instructions to retrieve, with the negative/positive message identifier in communication with the parser, the sentiment term with known sentiment in the foreign language;

instructions to identify, with the negative/positive message identifier in communication with the parser, the sentiment term, associated with the seed term, in a second message; and

instructions to, based on the identification of the sentiment term, determine, with the negative/positive message identifier in communication with the parser, that the second message has a known sentiment.

16. The computer readable medium as defined in claim 15, further comprising instructions to determine statistical information about the sentiment term, wherein the statistical information includes a confidence score that the sentiment term indicates a sentiment.

17. The computer readable medium as defined in claim 16, further comprising:

instructions to determine if the confidence score reaches or crosses a predetermined threshold; and

if the confidence score reaches or crosses the predetermined threshold, instructions to signify that the sentiment term indicates the known sentiment.

18. The computer readable medium as defined in claim 17, further comprising:

if the confidence score does not reach or cross the predetermined threshold, instructions to receive a third message; and

instructions to re-calculate the confidence score using analysis associated with the third message.

19. The computer readable medium as defined in claim 17, wherein each seeding term includes two or more sentiment terms associated therewith.

20. The computer readable medium as defined in claim 19, wherein each message includes two or more seeding terms, and wherein at least one of the seeding terms is in English.