Identifying entity representatives for topics reflected in content items using natural language processing

Patent metadata

Field	Value
Publication number	US-10296530-B2
Application number	US-201615252159-A
Country	US
Kind code	B2
Filing date	Aug 30, 2016
Priority date	Aug 30, 2016
Publication date	May 21, 2019
Grant date	May 21, 2019

Abstract

A topical representative assessment system implements techniques for determining entities that are ambassadors for one or more topics. The ambassadors are determined based on content items that they have authored or content items that are otherwise attributed to them. An ambassador may be any type of entity such as a person, a company, or an organization. Machine analytics may be used to determine whether a content item corresponds to a specific topic, determine a sentiment for a content item, analyze feedback for a content item, or any combination of these.

First claim

What is claimed is:

1. A system comprising:
one or more processors;
one or more storage media storing instructions which, when executed by the one or more processors, cause:
receiving a selection of a first topic to which a content item may pertain;
for each entity of a first plurality of entities:
identifying one or more content items that were authored by said each entity and that corresponds to the first topic;
for each content item in the one or more content items:
generating a value that indicates sentiment of said each entity relative to the first topic;
determining a level of engagement of said each content item by a second plurality of entities;

based on the value and the level of engagement, generating an ambassador score for said each entity in the first plurality of entities.

2. The system of claim 1 , wherein the one or more storage media storing instructions which, when executed by the one or more processors, further cause:
generating, based on the ambassador score for each said each entity in the first plurality of entities, a ranking of the first plurality of entities;
displaying, on a computer device, the ranking of the first plurality of entities.

3. The system of claim 1 , wherein determining the level of engagement comprises:
for a plurality of feedback associated with each said each content item, determining the feedback comprises a text portion;
for each feedback of the plurality of feedback, analyzing the text portion of said feedback to determine whether the text portion corresponds to at least one of a positive feedback indicator, a negative feedback indicator, or a neutral feedback indicator;
determining the level of engagement based at least in part on the determined positive feedback indicator, negative feedback indicator, or the neutral feedback indicator for each feedback of the plurality of feedback.

4. The system of claim 1 , wherein determining the level of engagement comprises:
for a plurality of feedback associated with each said each content item, determining the level of engagement based at least in part on a number of feedback of the plurality of feedback.

5. The system of claim 1 , wherein determining the level of engagement comprises:
for a plurality of feedback associated with each said each content item, determining the level of engagement based at least in part on whether a feedback indicator comprises a positive feedback indicator or a negative feedback indicator.

6. The system of claim 1 , wherein the receiving the selection of the first topic occurs before identifying the one or more content items.

7. The system of claim 1 , wherein the one or more storage media storing instructions which, when executed by the one or more processors, further cause:
receiving a selection of a second topic to which a content item may pertain;
for each entity of the first plurality of entities:
identifying one or more second content items that were authored by said each entity and that corresponds to the second topic that is different than the first topic;
for each content item in the one or more second content items:
generating another value that indicates sentiment of said each entity relative to the second topic;
determining another level of engagement of said each content item by a third plurality of entities that is different than the second plurality of entities;

based on the other value and the other level of engagement, generating another score for said each entity in the first plurality of entities.

8. The system of claim 7 , wherein a first content item corresponds to the first topic and the second topic.

9. The system of claim 1 , wherein determining the level of engagement comprises:
determining, for a particular content item, that said each entity that authored the particular content item provided feedback;
determining to not include the feedback provided by said each entity when determining the level of engagement.

10. The system of claim 1 , wherein identifying the one or more content items that corresponds to the first topic comprises determining, from metadata associated with the one or more content items, that each content item of the one or more content items corresponds to the first topic.

11. The system of claim 10 , wherein the metadata comprises one or more tags associated with the one or more content items specified by an author entity of said each content item.

12. The system of claim 1 , wherein the value that indicates sentiment of said each entity relative to the first topic is one of at least a positive, a neutral, or a negative sentiment.

13. The system of claim 1 , wherein none of the entities of the second plurality of entities is a member of the first plurality of entities.

14. A method comprising:
receiving a selection of a first topic to which a content item may pertain;
for each entity of a first plurality of entities:
identifying one or more content items that were authored by said each entity and that corresponds to the first topic;
for each content item in the one or more content items:
generating a value that indicates sentiment of said each entity relative to the first topic;
determining a level of engagement of said each content item by a second plurality of entities;

based on the value and the level of engagement, generating an ambassador score for said each entity in the first plurality of entities;

wherein the method is performed by one or more computing devices.

15. The method of claim 14 , wherein determining the level of engagement comprises:
for a plurality of feedback associated with each said each content item, determining the feedback comprises a text portion;
for each feedback of the plurality of feedback, analyzing the text portion of said feedback to determine whether the text portion corresponds to at least one of a positive feedback indicator, a negative feedback indicator, or a neutral feedback indicator;
determining the level of engagement based at least in part on the determined positive feedback indicator, negative feedback indicator, or the neutral feedback indicator for each feedback of the plurality of feedback.

16. The method of claim 14 , wherein determining the level of engagement comprises:
for a plurality of feedback associated with each said each content item, determining the level of engagement based at least in part on a number of feedback of the plurality of feedback.

17. One or more storage media storing instructions which, when executed by one or more processors, cause:
receiving a selection of a first topic to which a content item may pertain;
for each entity of a first plurality of entities:
identifying one or more content items that were authored by said each entity and that corresponds to the first topic;
for each content item in the one or more content items:
generating a value that indicates sentiment of said each entity relative to the first topic;
determining a level of engagement of said each content item by a second plurality of entities;

based on the value and the level of engagement, generating an ambassador score for said each entity in the first plurality of entities.

18. The method of claim 14 , wherein identifying the one or more content items comprises, for a first entity of the first plurality of entities, identifying two or more content items that were authored by the first entity.

19. The one or more storage media storing instructions of claim 18 , wherein determining the level of engagement comprises:
for a plurality of feedback associated

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Zheng Yi
• Kuan Chi-Yi
• Wang Hu
• Zhao Rui
• Zhang Yongzheng

Classifications

• G06F16/353 Primary

  into predefined classes · CPC title

• G06F16/36

  Creation of semantic tools, e.g. ontology or thesauri · CPC title