METHODS AND SYSTEMS FOR MONITORING AND ANALYZING SOCIAL MEDIA DATA

• US 20150058344A1
• Filed: 08/22/2013
• Published: 02/26/2015
• Est. Priority Date: 08/22/2013
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Li, Jingxuan, Peng, Wei, Sun, Tong, Bhatia, Sumit
• Granted Patent: US 9,256,663 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06F 16/285 Clustering or classification

Abstract

A system and method for analyzing social media data by obtaining social media data from a social media platform, where the social media data includes documents from multiple users of the social media platform; classifying the documents using a sentiment classifier; tokenizing the documents into terms; associating a sentiment with each term; detecting a first event based on a number of occurrences of a first term in the documents; and providing information associated with the event to a user, where the information includes the first term and a sentiment associated with the first term.

Claims

1. A method for analyzing social media data, the method comprising:

obtaining, using one or more processors, social media data from a social media platform, wherein the social media data comprises documents from a plurality of users of the social media platform;

classifying the documents using a sentiment classifier;

tokenizing the documents into terms;

associating a sentiment classification with each term;

detecting a first event based on a number of occurrences of a first term in the documents; and

providing information associated with the event to a user, wherein the information comprises the first term and a sentiment classification associated with the first term.

2. The method of claim 1, further comprising calculating a term frequency-inverse document frequency (“

TFIDF”

) metric for the first term, wherein the information associated with the event further comprises the TFIDF metric.

3. The method of claim 2, wherein the TFIDF metric is a time normalized TFIDF metric.

4. The method of claim 3, wherein the TFIDF metric is calculated using the formula:

5. The method of claim 4, wherein “

decay”

is calculated using the formula;

decay=e<sup>−

(current time-document time)</sup>

wherein “

document time”

is determined based on the timestamp associated with each document.

6. The method of claim 1, wherein the social media data is obtained in batch format.

7. The method of claim 1, wherein the social media data is obtained in streaming format.

8. The method of claim 1, wherein detecting the first event is further based on the sentiment classification associated with the first term.

9. The method of claim 8, wherein the first event is only detected when the first term is associated with a negative sentiment classification.

10. The method of claim 1, wherein the information is only provided to the user when the first term is associated with a negative sentiment classification.

11. A system for analyzing social media data, the system comprising:

a processing system comprising one or more processors; and

a memory system comprising one or more computer-readable media, wherein the one or more computer-readable media contain instructions that, when executed by the processing system, cause the processing system to perform operations comprising;

obtaining, using one or more processors, social media data from a social media platform, wherein the social media data comprises documents from a plurality of users of the social media platform;

classifying the documents using a sentiment classifier,

tokenizing the documents into terms;

associating a sentiment classification with each term;

detecting a first event based on a number of occurrences of a first term in the documents; and

providing information associated with the event to a user, wherein the information comprises the first term and a sentiment classification associated with the first term.

12. The system of claim 11, the operations further comprising calculating a term frequency-inverse document frequency (“

TFIDF”

) metric for the first term, wherein the information associated with the event further comprises the TFIDF metric.

13. The system of claim 12, wherein the TFIDF metric is a time normalized TFIDF metric.

14. The system of claim 13, wherein the TFIDF metric is calculated using the formula:

15. The system of claim 14, wherein “

decay”

is calculated using the formula;

decay=e<sup>−

(current time-document time)</sup>

wherein “

document time”

is determined based on the timestamp associated with each document.

16. The system of claim 11, wherein the social media data is obtained in batch format.

17. The system of claim 11, wherein the social media data is obtained in streaming format.

18. The system of claim 11, wherein detecting the first event is further based on the sentiment classification associated with the first term.

19. The system of claim 18, wherein the first event is only detected when the first term is associated with a negative sentiment classification.

20. The system of claim 11, wherein the information is only provided to the user when the first term is associated with a negative sentiment classification.