Analyzing messages in social networks

Patent metadata

Field	Value
Publication number	US-10389677-B2
Application number	US-201615389536-A
Country	US
Kind code	B2
Filing date	Dec 23, 2016
Priority date	Dec 23, 2016
Publication date	Aug 20, 2019
Grant date	Aug 20, 2019

Abstract

Embodiments of the invention provide a computer-implemented method, computing system and computer program product for analyzing a message in a social network. The method comprises identifying an entity from the message; detecting historical popularity of the entity in a social network; identifying a topic from the message; detecting historical popularity of the topic in the social network; and generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic. Results obtained with embodiments of the invention may be provided to popularity prediction tools for improving popularity prediction of messages in social networks.

First claim

The invention claimed is:

1. A computer-implemented method for predicting popularity of a message in a social network, comprising:
identifying an entity from the message;
detecting historical popularity of the entity in social network;
identifying a topic from the message;
detecting historical popularity of the topic in the social network;
generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic by:
computing a popularity mean and a popularity variance for the entity;
computing a popularity mean and a popularity variance for the topic; and
calculating the entity-topic correlation factor based on the popularity mean and the popularity variance for the entity and the popularity mean and the popularity variance for the topic; and

marketing goods to a user of the social network based on the entity-topic correlation factor.

2. The method according to claim 1 , further comprising:
generating an average popularity mean and an average popularity variance of a number of normal distributions for the entity.

3. The method according to claim 2 , wherein said generating average popularity mean and average popularity variance of a number of normal distributions for the entity comprises:
modeling the number of normal distributions of the entity based on the historical popularity of the entity.

4. The method according to claim 1 , further comprising:
generating an average popularity mean and an average popularity variance of a number of normal distributions for the topic.

5. The method according to claim 1 , further comprising:
identifying a social attribute of the entity
detecting historical popularity for the social attribute in the social network; and
generating average popularity mean and average popularity variance of a number of normal distributions for the social attribute based on the historical popularity for the social attribute in the social network.

6. The method of claim 1 , further comprising:
using the entity-topic correlation factor for at least one of risk alarming or real-world outcome prediction.

7. A computing system comprising a computer processor coupled to a computer-readable memory unit, the memory unit comprising instructions that when executed by the computer processor implements a method for predicting popularity of a message in a social network, the method comprising:
identifying an entity from the message;
detecting historical popularity of the entity in the social network;
identifying a topic from the message;
detecting historical popularity of the topic in the social network; and
generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic by:
computing a popularity mean and a popularity variance for the entity;
computing a popularity mean and a popularity variance for the topic; and
calculating the entity-topic correlation factor based on the popularity mean and the popularity variance for the entity and the popularity mean and the popularity variance for the topic; and

marketing goods to a user of the social network based on the entity-topic correlation factor.

8. The computing system according to claim 7 , wherein the method further comprises:
generating average popularity mean and average popularity variance of a number of normal distributions for the topic.

9. The computing system according to claim 7 , wherein the method further comprises:
generating average popularity mean and average popularity variance of a number of normal distributions for the entity.

10. The computing system according to claim 9 , wherein said generating average popularity mean and average popularity variance of a number of normal distributions for the entity comprises:
modeling the number of normal distributions of the entity based on the historical popularity of the entity.

11. The computing system according to claim 7 , wherein the method further comprises:
identifying a social attribute of the entity;
detecting historical popularity for the social attribute in social networks; and
generating average popularity mean and average popularity variance of a number of normal distributions for the social attribute based on the historical popularity for the social attribute in social network.

12. The computer system of claim 7 , wherein the method further comprises:
using the entity-topic correlation factor for at least one of risk alarming or real-world outcome prediction.

13. A computer program product being tangibly stored on a non-transient machine-readable medium and comprising machine-executable instructions for predicting popularity of a message in a social network, the instructions, when executed on an electronic device, causing the electronic device to perform the following:
identifying an entity from the message;
detecting historical popularity of the entity in the social network;
identifying a topic from the message;
detecting historical popularity of the topic in social networks; and
generating an entity-topic correlation factor for the entity and the topic based on the historical popularity of the entity and the historical popularity of the topic by:
computing a popularity mean and a popularity variance for the entity;
computing a popularity mean and a popularity variance for the topic; and
calculating the entity-topic correlation factor based on the popularity mean and the popularity variance for the entity and the popularity mean and the popularity variance for the topic; and

marketing goods to a user of the social network based on the entity-topic correlation factor.

14. The computer program product according to claim 13 , the instructions further causing the electronic device to perform the following:
generating average popularity mean and average popularity variance of a number of normal distributions for the entity.

15. The computer program product according to claim 13 , the instructions further causing the electronic device to perform the following:
generating average popularity mean and average popularity variance of a number of normal distributions for the topic.

16. The computer program product according to claim 15 , wherein said generating average popularity mean and average popularity variance of a number of normal distributions for the entity comprises:
modeling the number of normal distributions of the entity based on the historical popularity of the entity.

17. The computer program product according to claim 13 , the instructions further causing the electronic device to perform the following:
identifying a social attribute of the entity;
detecting historical popularity for the social attribute in the social network; and
generating average popularity mean and average popularity variance of a number of normal distributions for the social attribute based on the historical popularity for the social attribute in the social network.

18. The computer program product according to claim 13 , wherein the method further comprises:
using the entity-topic correlation factor for at least one of risk alarming or real-world outcome prediction.

Assignees

• IBM

Inventors

• Cai ke ke
• Guo Hong Lei
• Jiang Jian Min
• Su Zhong
• Sun Chang Hua
• Tang Guo Yu

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F40/295

  Named entity recognition · CPC title

• G06F17/278

  Physics · mapped topic

• H04L51/32 Primary

  Electricity · mapped topic