# US 2012/0254184 A1 · Methods And Systems For Analyzing Data Of An Online Social Network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2012/0254184 A1
- Document ID: US20120254184A1
- Status: Published application
- Kind: A1
- Application number: 13/438,382
- Filed: 2012-04-03
- Published: 2012-10-04
- Earliest claimed: 2011-04-04
- Assignees: Northwestern University
- Inventors: Alok Choudhary; Ramanathan Narayanan
- Web page: https://patentgrep.com/patent/US20120254184A1

## CPC

- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 10/42: Determination of affinities or common interests between users
- G06Q 10/44: Identification of trends within social networks, e.g. identification of trending topics
- G06Q 10/46: Determination of level of influence of users within social networking services
- G06Q 10/48: using social graphs
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Method of analyzing data from an online social network having a set of network users. The method includes obtaining topic-specific messages sent by the network users. The messages have social content provided by the networks users, wherein the messages include a marker of interest in the social content. The marker of interest is associated with a topic of the social network. The method also includes identifying the network users that sent the messages having the marker of interest in the social content as interested users of the topic. The interested users are a subset of the set of network users. The method also includes determining a topic-specific influence (TSI) value of a designated user from the interested users in the subset. The TSI value of the designated user is based on a number of the interested users that are registered to receive the messages from the designated user.

## Claims

### Claim 1

A method of analyzing data from an online social network having a set of network users, the network users being capable of communicating with one another through the social network, the method comprising:
obtaining messages sent by the network users, the messages having social content that includes at least one of textual terms or images provided by the network users, wherein the messages include a marker of interest in the social content, the marker of interest being associated with a topic of the social network;
identifying the network users that sent the messages having the marker of interest in the social content as interested users of the topic, the interested users being a subset of the set of network users; and
determining a topic-specific influence (TSI) value of a designated user from the interested users in the subset, wherein the TSI value of the designated user is based on a number of the interested users that are registered to receive the messages from the designated user.

### Claim 2 (depends on 1)

The method of claim 1, wherein the interested users that are registered to receive the messages from the designated user are primary users, the interested users also including secondary users that are registered to receive the messages from at least one of the primary users, wherein the TSI value is also based on a number of secondary users.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the TSI value includes determining the TSI values of other interested users in the subset.

### Claim 4 (depends on 3)

The method of claim 3, further comprising ranking the interested users based on the TSI values to generate a topic-specific ranking.

### Claim 5 (depends on 3)

The method of claim 3, further comprising identifying influential users from the interested users of the subset, the TSI values of the influential users being at least one of (a) greater than a designated cut-off value or (b) within a designated range of values; or (c) within a top group ranking of interested users.

### Claim 6 (depends on 3)

The method of claim 3, further comprising identifying the interested users that send an abnormal number of messages to network users as spam users, the TSI values of spam users being diminished relative to interested users that are not spam users.

### Claim 7 (depends on 1)

The method of claim 1, wherein the marker of interest includes a plurality of marker of interests and wherein the determining whether the messages include the marker of interest includes identifying the messages that include at least two of the marker of interests.

### Claim 8 (depends on 1)

The method of claim 1, wherein the marker of interest is a textual term that is actively tagged by the network user as the topic of the corresponding message.

### Claim 9

A system configured to analyze data from an online social network having a set of network users, the network users being capable of communicating with one another through the social network, the system comprising:
an analysis module configured to analyze messages sent by the network users, the messages having social content that includes at least one of textual terms or images provided by the networks users, the messages including a marker of interest in the social content, the marker of interest being associated with a topic of the social network;
an identification module configured to identify the network users that sent the messages having the marker of interest in the social content as interested users of the topic, the interested users being a subset of the set of network users; and
a value-generating module configured to determine a topic-specific influence (TSI) value of a designated user from the interested users in the subset, wherein the TSI value of the designated user is based on a number of the interested users that are registered to receive the messages from the designated user.

### Claim 10 (depends on 9)

The system of claim 9, wherein the interested users that are registered to receive the messages from the designated user are primary users, the interested users also including secondary users that are registered to receive the messages from at least one of the primary users, wherein the TSI value is also based on a number of secondary users.

### Claim 11 (depends on 9)

The system of claim 9, wherein the value-generating module is configured to determine the TSI value of other interested users in the subset.

### Claim 12 (depends on 11)

The system of claim 11, wherein the value-generating module is configured to rank the interested users based on the TSI values to generate a topic-specific ranking.

### Claim 13 (depends on 11)

The system of claim 11, wherein the value-generating module is configured to identify influential users from the interested users of the subset, the TSI values of the influential users being at least one of (a) greater than a designated cut-off value or (b) within a designated range of values; or (c) within a top group ranking of interested users.

### Claim 14 (depends on 9)

The system of claim 9, wherein the marker of interest includes a plurality of marker of interests and wherein the analysis module determines whether the messages include at least two of the marker of interests.

### Claim 15 (depends on 9)

The system of claim 9, wherein the marker of interest is a textual term that is actively tagged by the network user as the topic of the corresponding message.

### Claim 16

A method of analyzing data from an online social network having a set of network users, the network users being capable of communicating with one another through the social network, the method comprising:
obtaining a plurality of topic documents that are associated with different social topics, each of the topic documents having a plurality of messages from the network users of the social network, the messages having social content that includes at least one of textual terms or images provided by the networks users, wherein the messages of each topic document are identified as relating to the social topic of the topic document; and
assigning the topic documents to corresponding cluster groups, wherein the assigning operation for each of the topic documents is based on a user similarity of said topic document with the other topic documents, the user similarity being determined by a number of influential users that are shared by at least two topic documents.

### Claim 17 (depends on 16)

The method of claim 16, further comprising determining a cluster representative of each of the cluster groups, the cluster representative being one of the topic documents.

### Claim 18 (depends on 16)

The method of claim 16, wherein the topic documents include at least 1000 topic documents.

### Claim 19

A system configured to analyze data from an online social network having a set of network users, the network users being capable of communicating with one another through the social network, the method comprising:
a data-collection module configured to obtain a plurality of topic documents that are associated with different social topics, each of the topic documents having a plurality of messages from the network users of the social network, the messages having social content that includes at least one of textual terms or images provided by the networks users, wherein the messages of each topic document are identified as relating to the social topic of the topic document; and
a clustering module configured to assign the topic documents to corresponding cluster groups, wherein an assignment for each of the topic documents is based on a user similarity of said topic document with the other topic documents, the user similarity being determined by a number of influential users that are shared by at least two topic documents.

### Claim 20 (depends on 19)

The system of claim 19, wherein the clustering module determines a cluster representative of each of the cluster groups, the cluster representative being one of the topic documents.
