System and method for collection analysis of electronic discussion methods

• US 7,197,470 B1
• Filed: 10/11/2000
• Issued: 03/27/2007
• Est. Priority Date: 10/11/2000
• Status: Active Grant

• Current Assignee: Buzzmetrics, Ltd. (Nielsen Holdings plc)
• Original Assignee: Buzzmetrics, Ltd. (Nielsen Holdings plc)
• Inventors: Holtzman, David, Arnett, Nicholas D., Pool, David
• Primary Examiner(s): MEINECKE DIAZ, SUSANNA M
• Application Number:
  US09/686,516
• Time in Patent Office: 2,358 Days
• Field of Search: 705/10
• US Class Current: 705/7.29
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/6254 by anonymising data, e.g. decorrelating personal data from the owner's identification
• CPC Class Codes: G06F 2221/2117 User registration
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: H04L 51/216 Handling conversation history, e.g. grouping of messages in sessions or threads
• CPC Class Codes: H04L 63/0407 wherein the identity of one or more communicating identities is hidden cryptographic mechanisms or cryptographic arrangements for anonymous credentials or for identity based cryptographic systems H04L9/00
• CPC Class Codes: H04L 65/1101 Session protocols
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A system and method for collecting and analyzing electronic discussion messages to categorize the message communications and the identify trends and patterns in pre-determined markets. The system comprises an electronic data discussion system wherein electronic messages are collected and analyzed according to characteristics and data inherent in the messages. The system further comprises a data store for storing the message information and results of any analyses performed. Objective data is collected by the system for use in analyzing the electronic discussion data against real-world events to facilitate trend analysis and event forecasting based on the volume, nature and content of messages posted to electronic discussion forums.

Claims

1. A method for collecting and analyzing electronic discussion messages;

wherein the method comprises the computer-implemented steps of;

(a) collecting a plurality of message information from a plurality of pre-determined electronic discussion forums;

(b) storing the plurality of message information in a central data store;

(c) categorizing the message information, with respect to at least one topic, according to a plurality of pre-determined rules;

(d) assigning an opinion rating to the plurality of message information based on sentence-level analysis using a plurality of pre-determined linguistic patterns and associative rules, the opinion rating indicating at least one of a positive, negative and neutral opinion associated with the at least one topic;

(e) collecting a plurality of objective data from a plurality of objective data sources;

(f) analyzing the message information, opinion rating and the objective data to identify trends in the pattern of behavior in pre-determined markets and the roles of individual participants in electronic discussion forums over time; and

(g) generating reports for end-users based on the results of the analyses performed by the present invention.

2. The method of claim 1, wherein the roles of individual participants are classified by correlating their postings with objective data relating to events external to the electronic discussion forum.

3. The method of claim 1, wherein the analyzing step (f) comprises analyzing a time series comprising the message information and the objective data to identify trends in the pattern of behavior in pre-determined markets and the roles of individual participants over time in electronic discussion forums.

4. A system for processing message traffic in a plurality of electronic discussion forums, comprising:

a computer-implemented message collector for collecting messages from the plurality of electronic discussion forums;

a computer-implemented message categorizer for processing the messages based on a series of topics;

a computer-implemented data analyzer for tracking message content posted by a plurality of pseudonyms and the roles of individual participants using the pseudonyms posting in the plurality of electronic discussion forums over time based on the processing of the messages;

a storage device containing a database storing configuration information for the plurality of electronic discussion forums; and

a computer-implemented report generator for generating a report based upon the analysis of the data analyzer;

wherein the computer-implemented message collector communicates with the database, thereby enabling the computer-implemented message collector to collect messages corresponding to a plurality of message formats or communications protocols.

5. The system of claim 4, wherein the computer-implemented message categorizer computes at least one relevance score for a message, the relevance score providing a measure of the relevance of the message to at least one topic for the series of topics, the relevance score being a numerical value on a numerical scale, and the computer-implemented data analyzer utilizing the relevance score in tracking message content.

6. The system of claim 5, wherein the relevance score is computed based on a set of predetermined rules for each topic;

and wherein the predetermined rules for each topic comprise a set of conditions defining information relevant to the topic.

7. The system of claim 4, wherein the roles of individual participants are classified by correlating their postings with objective data relating to events external to the electronic discussion forum.

8. A system for processing message traffic in a plurality of electronic discussion forums, comprising:

a computer-implemented message collector for collecting messages from the plurality of electronic discussion forums;

a computer-implemented message processor for processing the messages according to a series of topics, wherein the message processor processes a message to compute a numerical relevance score of the message to at least one topic from the series of topics on a numerical scale;

a computer-implemented data analyzer for tracking message content posted by a plurality of pseudonyms posting in the plurality of electronic discussion forums over time based on the processing of the messages;

a storage device for storing the messages; and

a computer-implemented report generator for generating a market report on the at least one topic based upon the analysis of the data analyzer;

wherein the message processor processes the messages to compute an opinion rating associated with the at least one topic for the message based on sentence-level analysis using a plurality of pre-determined linguistic patterns and associative rules;

wherein the computed opinion rating indicates at least one of a positive, negative and neutral opinion associated with the at least one topic;

whereby the numerical relevance score and opinion rating are reflected, at least in part, in the market report on the at least one topic.

9. The system of claim 8, wherein the opinion rating is computed based on a textual analysis of the message.

10. The system of claim 8, wherein a relevance score is computed based on a set of predetermined rules for each topic;

and wherein the predetermined rules for each topic comprise a set of conditions defining information relevant to the topic.

11. A method for processing message traffic in a plurality of electronic discussion forums, comprising the steps of:

collecting messages from the plurality of electronic discussion forums;

processing the messages based on a series of topics;

tracking message content posted by a plurality of pseudonyms and the roles of individual participants using the pseudonyms posting in the plurality of electronic discussion forums over time based on the processing of the messages;

storing configuration information for the plurality of electronic discussion forums in a database, and wherein the step of collecting messages comprises collecting messages corresponding to a plurality of message formats or communications protocols;

assigning opinion ratings in the message content posted by the plurality of pseudonyms; and

generating a market report from, at least in part, the message content and the opinion ratings.

12. The method of claim 11, further comprising the computer-implemented step of computing at least one relevance score for a message, the relevance score providing a measure of the relevance of the message to at least one topic from the series of topics, wherein the step of generating the market report also uses the relevance score.

13. The method of claim 12, wherein the relevance score is computed based on a set of predetermined rules for each topic;

and wherein the predetermined rules for each topic comprise a set of conditions defining information relevant to the topic.

14. The method of claim 11, wherein the roles of individual participants are classified by correlating their postings with objective data relating to events external to the electronic discussion forum.

15. A method for processing message traffic in a plurality of electronic discussion forums, comprising the computer-implemented steps of:

collecting messages from the plurality of electronic discussion forums;

processing the messages according to a series of topics and computing a numerical relevance score of the messages to at least one topic from the series of topics on a numerical scale; and

tracking message content posted by a plurality of pseudonyms posting in the plurality of electronic discussion forums over time based on the processing of the messages;

wherein

the processing step further comprises the computer-implemented step of computing an opinion rating for the message based on sentence-level analysis using a plurality of pre-determined linguistic patterns and associative rules according to the at least one topic;

wherein the computed opinion rating indicates at least one of a positive, negative and neutral opinion associated with the at least one topic;

the method further comprising the step of generating a market report on the at least one topic from, at least in part, the numerical relevance score and opinion rating from the processing step.

16. The method of claim 15, wherein the step of computing an opinion rating comprises the step of performing a textual analysis of the message.

17. The method of claim 15, wherein a relevance score is computed based on a set of predetermined rules for each topic;

and wherein the predetermined rules for each topic comprise a set of conditions defining information relevant to the topic.