Method and system for qualifying user engagement with a website

• US 7,925,743 B2
• Filed: 02/29/2008
• Issued: 04/12/2011
• Est. Priority Date: 02/29/2008
• Status: Active Grant

• Current Assignee: Networked Insights LLC
• Original Assignee: Networked Insights LLC
• Inventors: Mitchell, Michael, Jenkins, Glenn, Neely, Daniel, Wulff, Matthew
• Primary Examiner(s): Park; Jeong S
• Application Number:
  US12/040,087
• Publication Number:
  US 20090222551A1
• Time in Patent Office: 1,138 Days
• Field of Search: 709/203, 709/224, 707/3, 707/5
• US Class Current: 709/224
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A system and a method of identifying information characterizing use of a website is provided. A plurality of user profiles are analyzed. A user profile includes information associated with an interaction by a user with the website. A plurality of user comments associated with the website are analyzed. Characteristic information associated with use of the website is determined based on the analyzed user profiles and the analyzed user comments. The determined characteristic information is presented to a user.

Claims

1. A device for identifying information characterizing use of a website, the device comprising:

a processor; and

a non-transitory computer-readable medium operably coupled to the processor, the non-transitory computer-readable medium comprising computer-executable instructions that when executed by the processor cause the device to perform operations comprising

analyzing a plurality of user profiles, wherein a user profile includes information associated with an interaction by a user with a website, and wherein the information is selected from a group consisting of a search term entered at the website by the user, a data entry item entered at the website by the user, a click stream generated at the website by the user, an entry point to the website, a time since the user accessed the website, an Internet service provider used to access the website, a login name entered by the user, an exit point from the website, a number of comments posted to the website by the user, a frequency that the comments are posted to the website by the user, and a user information associated with the login name;

identifying a set of words from a plurality of user comments associated with the website;

identifying a part of speech for each word of the identified set of words;

identifying a second set of words from the plurality of user comments based on the identified part of speech, wherein the second set of words are identified as a noun;

calculating a value for each word of the identified second set of words, wherein the value is associated with a probability that the word indicates a topic of the plurality of user comments;

identifying a topic of the plurality of user comments based on the calculated value for each word of the identified second set of words;

determining characteristic information associated with use of the website based on the analyzed user profiles and the identified topic; and

presenting the determined characteristic information.

2. A non-transitory computer-readable medium comprising computer-readable instructions stored thereon that when executed by a processor, cause a computing device to:

analyze a plurality of user profiles, wherein a user profile includes information associated with an interaction by a user with a website, and wherein the information is selected from a group consisting of a search term entered at the website by the user, a data entry item entered at the website by the user, a click stream generated at the website by the user, an entry point to the website, a time since the user accessed the website, an Internet service provider used to access the website, a login name entered by the user, an exit point from the website, a number of comments posted to the website by the user, a frequency that the comments are posted to the website by the user, and a user information associated with the login name;

identify a set of words from a plurality of user comments associated with the website;

identify a part of speech for each word of the identified set of words;

identify a second set of words from the plurality of user comments based on the identified part of speech, wherein the second set of words are identified as a noun;

calculate a value for each word of the identified second set of words, wherein the value is associated with a probability that the word indicates a topic of the plurality of user comments;

identify a topic of the plurality of user comments based on the calculated value for each word of the identified second set of words;

determine characteristic information associated with use of the website based on the analyzed user profiles and the identified topic; and

present the determined characteristic information.

3. A method for identifying information characterizing use of a website, the method comprising:

analyzing a plurality of user profiles by a processor, wherein a user profile includes information associated with an interaction by a user with a website, and wherein the information is selected from a group consisting of a search term entered at the website by the user, a data entry item entered at the website by the user, a click stream generated at the website by the user, an entry point to the website, a time since the user accessed the website, an Internet service provider used to access the website, a login name entered by the user, an exit point from the website, a number of comments posted to the website by the user, a frequency that the comments are posted to the website by the user, and a user information associated with the login name;

identifying, by the processor, a set of words from a plurality of user comments associated with the website;

identifying, by the processor, a part of speech for each word of the identified set of words;

identifying, by the processor, a second set of words from the plurality of user comments based on the identified part of speech, wherein the second set of words are identified as a noun;

calculating, by the processor, a value for each word of the identified second set of words, wherein the value is associated with a probability that the word indicates a topic of the plurality of user comments;

identifying, by the processor, a topic of the plurality of user comments based on the calculated value for each word of the identified second set of words;

determining, by the processor, characteristic information associated with use of the website based on the analyzed user profiles and the identified topic; and

presenting, by the processor, the determined characteristic information.

4. The method of claim 3, wherein the identified topic is the determined characteristic information.

5. The method of claim 4, further comprising grammatically correcting the plurality of user comments before identifying the set of words.

6. The method of claim 3, further comprising:

identifying a third set of words from the plurality of user comments;

identifying a second part of speech for each word of the identified third set of words;

identifying a fourth set of words from the plurality of user comments based on the identified second part of speech; and

determining a sentiment associated with the plurality of user comments based on the identified second set of words, wherein the determined sentiment is the determined characteristic information.

7. The method of claim 6, wherein the fourth set of words are identified as an adjective or an adverb.

8. The method of claim 6, further comprising identifying a root form of each word of the identified fourth set of words before identifying the sentiment.

9. The method of claim 6, wherein determining the sentiment comprises:

comparing each word of the identified fourth set of words to known positive words and known negative words;

assigning a value to each word of the identified fourth set of words based on the comparison;

calculating a total value for each sentence of the plurality of user comments based on the value assigned to each word of the sentence; and

calculating a sentiment value based on the calculated total value for the plurality of user comments; and

determining the sentiment based on the calculated sentiment value.

10. The method of claim 9, further comprising identifying a root form of each word of the identified fourth set of words before comparing each word.

11. The method of claim 9, wherein assigning the value to each word based on the comparison comprises:

if a word of the identified fourth set of words is included in the known positive words and the known negative words, assigning the value;

if a word of the identified fourth set of words is not included in the known positive words and the known negative words, identifying a synonym of the word;

comparing the identified synonym to the known positive words and the known negative words; and

if the identified synonym is included in the known positive words and the known negative words, assigning a second value to the word, wherein the second value is different from the value.

12. The method of claim 3, wherein the characteristic information is selected from a group consisting of a sentiment indicator, an engagement indicator, a topic indicator, an insight indicator, an influence indicator, a website activity level, a category indicator, and an interaction indicator.

13. The method of claim 3, wherein the user comments associated with the website are part of an electronic discussion conducted using an application selected from a group consisting of a text messaging application, an instant messaging application, a chat session application, an e-mail application, a short messaging service application, and a multimedia messaging service application.

14. The method of claim 13, wherein the electronic discussion is initiated with an agent, wherein the agent is a computer generated entity.

15. The method of claim 3, further comprising:

receiving a filter parameter; and

filtering a second plurality of user profiles based on the received filter parameter to identify the plurality of user profiles before analyzing the plurality of user profiles.

16. The method of claim 3, further comprising:

receiving a filter parameter; and

filtering a second plurality of user comments based on the received filter parameter to identify the plurality of user comments before identifying the set of words.

17. The method of claim 3, further comprising:

identifying a third set of words from the plurality of user comments;

identifying a second part of speech for each word of the identified third set of words;

identifying a fourth set of words from the plurality of user comments based on the identified second part of speech;

identifying a root form of each word of the identified fourth set of words; and

associating an occurrence value with the identified root form of each word of the identified fourth set of words for each user comment of the plurality of user comments to form a plurality of tag clouds.

18. The method of claim 17, wherein the fourth set of words are identified as a noun or a verb.

19. The method of claim 17, wherein the plurality of tag clouds are organized by an association with the user.

20. The method of claim 17, wherein the plurality of tag clouds are organized by the identified topic.

21. The method of claim 17, further comprising:

receiving a search term; and

searching the plurality of tag clouds to determine each user comment of the plurality of user comments that includes the received search term, wherein the identified user comments are the determined characteristic information.

22. The method of claim 21, further comprising ranking the identified user comments based on the associated occurrence value of the received search term, wherein the identified user comments are presented based on the ranking.

23. The method of claim 21, further comprising:

before searching the plurality of tag clouds, identifying a synonym of the received search term; and

searching the plurality of tag clouds to determine each user comment of the plurality of user comments that includes the identified synonym.