Systems and methods for sentiment detection, measurement, and normalization over social networks

• US 9,189,797 B2
• Filed: 10/25/2012
• Issued: 11/17/2015
• Est. Priority Date: 10/26/2011
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Ghosh, Rishab Aiyer, Manley, Scott Park
• Primary Examiner(s): Nguyen, Tu
• Application Number:
  US13/660,533
• Publication Number:
  US 20130110928A1
• Time in Patent Office: 1,118 Days
• Field of Search: 709/204
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A new approach is proposed that contemplates systems and methods to provide the ability to detect, measure, aggregate, and normalize sentiments expressed by a group of users on a certain event or topic on a social network so that the normalized sentiments truly reflect the sentiments of the general public on that specific event or topic. Additionally, the collected and measured sentiments of an individual user expressed on a social network can also be normalized against a baseline sentiment that reflects in order to truly reflect the individual user'"'"'s sentiment at the time of his/her expression.

Claims

1. A system, comprising:

a data collection engine, which in operation, collects data on activities of a plurality of users on a social network, wherein each of the activities includes content regarding those activities;

a sentiment analysis engine with a processor, which in operation,

detects and measures sentiment of each of the plurality of users toward an event as expressed in the collected data of their activities on the social network;

aggregates the detected sentiments of the plurality of users toward the event;

normalizes the aggregated sentiments of the users towards the event against a baseline sentiment for that event, so that the normalized sentiments reflect the sentiments of the general public toward the event, wherein the baseline sentiment and aggregated sentiments is based on the content of the activities.

2. The system of claim 1, wherein:

the social network is a publicly accessible web-based platform or community that enables its users/members to post, share, communicate, and interact with each other.

3. The system of claim 1, wherein:

the social network is one of Facebook, Google+, Tweeter, Linkedln, blogs, forums, or any other web-based communities.

4. The system of claim 1, wherein:

activities of the user on the social media network include one or more of tweets, replies and/or re-tweets to the tweets, posts, comments to other users'"'"' posts, opinions, feeds, connections, references, links to other websites or applications, or any other activities on the social network.

5. The system of claim 1, wherein:

the data collection engine collects the data on the activities of the users on the social network by periodically crawling the social network to collect the latest activity data from the users.

6. The system of claim 1, wherein:

the data collection engine collects the data on the activities of the users on the social network by utilizing an application programming interface (API) provided by the social network.

7. The system of claim 1, wherein:

the sentiment analysis engine detects and identifies the sentiments expressed by the users in the collected data of their activities on the social network via a number of sentiment text scoring schemes that take into consideration the ways people express themselves on the social media network.

8. The system of claim 7, wherein:

the number of sentiment text scoring schemes utilize specific characteristics of sentiment expressions identified in the collected data for detecting the sentiments expressed by the users on the social network.

9. The system of claim 1, wherein:

the sentiment analysis engine normalizes the aggregated sentiments of the users against the baseline sentiment for that event that takes into account the natural bias of the social network on which the opinions of the users are expressed.

10. The system of claim 1, wherein:

the sentiment analysis engine normalizes the aggregated sentiments of the users against the baseline sentiment for that event that takes into account nature of the event.

11. The system of claim 1, wherein:

the sentiment analysis engine normalizes the aggregated sentiments of the users against the baseline sentiment for that event that takes into account timing of the activities of the users on the social network.

12. The system of claim 1, wherein:

the sentiment analysis engine calculates a social sentiment score for the event based on normalized measurement of the sentiments of the users.

13. A system, comprising:

a data collection engine with a processor, which in operation, collects data on activities of a user on a social network, wherein each of the activities includes content regarding those activities;

a sentiment analysis engine with a processor, which in operation,

detects and measures sentiment of the user toward an event as expressed in the collected data of the activities of the user on the social network;

normalizes the measured sentiment of the user towards the event against a baseline sentiment for the event so that the normalized sentiment reflects the real sentiment of the user toward the event, wherein the baseline sentiment and measured sentiment is based on the content of the activities.

14. The system of claim 13, wherein:

the data collection engine selectively collects the data from the user based on an activity collection schedule for the user.

15. The system of claim 13, wherein:

the data collection engine establishes an activity distribution pattern for the user over time based on the timestamps associated with the activities of the user on the social network.

16. The system of claim 13, wherein:

the data collection engine determines whether or when the user will be most active upon the occurrence of certain events.

17. The system of claim 13, wherein:

the sentiment analysis engine normalizes the measured sentiment of the user against sentiments expressed in other content linked to the individual user.

18. The system of claim 13, wherein:

the sentiment analysis engine normalizes the measured sentiments of the user against the baseline sentiment for that event that takes into account natural tendency of the user.

19. A method, comprising:

collecting data on activities of a plurality of users on a social network, wherein each of the activities includes content regarding those activities;

detecting and measuring sentiment of each of the plurality of users toward an event as expressed in the collected data of their activities on the social network;

aggregating the detected sentiments of the plurality of users toward the event;

normalizing, with a sentiment detection system, the aggregated sentiments of the users towards the event against a baseline sentiment for that event so that the normalized sentiments reflect the sentiments of the general public toward the event, wherein the baseline sentiment and aggregated sentiments is based on the content of the activities.

20. The method of claim 19, further comprising:

collecting the data on the activities of the users on the social network by periodically crawling the social network to collect the latest activity data from the users.

21. The method of claim 19, further comprising:

collecting the data on the activities of the users on the social network by utilizing an application programming interface (API) provided by the social network.

22. The method of claim 19, further comprising:

detecting and identifying the sentiments expressed by the users in the collected data of their activities on the social network via a number of sentiment text scoring schemes that take into consideration the ways people express themselves on the social media network.

23. The method of claim 19, further comprising:

utilizing specific characteristics of sentiment expressions identified in the collected data for detecting the sentiments expressed by the users on the social network.

24. The method of claim 19, further comprising:

normalizing the aggregated sentiments of the users against the baseline sentiment for that event that takes into account the natural bias of the social network on which the opinions of the users are expressed.

25. The method of claim 19, further comprising:

normalizing the aggregated sentiments of the users against the baseline sentiment for that event that takes into account nature of the event.

26. The method of claim 19, further comprising:

normalizing the aggregated sentiments of the users against the baseline sentiment for that event that takes into account timing of the activities of the users on the social network.

27. The method of claim 19, further comprising:

calculating a social sentiment score for the event or topic based on normalized measurement of the sentiments of the users.

28. The method, comprising:

collecting data on activities of a user on a social network, wherein each of the activities includes content regarding those activities;

detecting and measuring sentiment of the user toward an event as expressed in the collected data of the activities of the user on the social network;

normalizing, with a sentiment detection system, the measured sentiment of the user towards the event against a baseline sentiment for that event so that the normalized sentiment reflects the real sentiment of the user toward the event, wherein the baseline sentiment and measured sentiment is based on the content of the activities.

29. The method of claim 28, further comprising:

selectively collecting the data from the user based on an activity collection schedule for the user.

30. The method of claim 28, further comprising:

establishing an activity distribution pattern for the user over time based on the timestamps associated with the activities of the user on the social network.

31. The method of claim 28, further comprising:

determining whether or when the user will be most active upon the occurrence of certain events.

32. The method of claim 28, further comprising:

normalizing the measured sentiment of the user against sentiments expressed in other content linked to the individual user.

33. The method of claim 28, further comprising:

normalizing the measured sentiments of the user against the baseline sentiment for that event that takes into account natural tendency of the user.