Measuring web site satisfaction of information needs using page traffic profile

• US 8,041,652 B2
• Filed: 01/10/2011
• Issued: 10/18/2011
• Est. Priority Date: 06/13/2007
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Carmel, David, Konopnicki, David, Roitman, Haggai, Barkai, Gilad
• Primary Examiner(s): Vincent; David R
• Assistant Examiner(s): Chang; Li-Wu
• Application Number:
  US12/987,181
• Publication Number:
  US 20110106799A1
• Time in Patent Office: 281 Days
• Field of Search: 706/12
• US Class Current: 706/12
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0671 In-line storage system
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A method, system, and computer program product for measuring web site satisfaction of information needs are provided. The method includes: selecting a page for analysis; generating a page profile in the form of a list of keywords representing the page; generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page; determining the success of users'"'"' visits to the page; and analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords.

Claims

1. A computer-implemented method for measuring web site satisfaction of information needs, performed by a processor, comprising:

selecting a page for analysis;

generating a page profile in the form of a list of keywords representing the page;

generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords,

wherein generating a page traffic profile includes;

clustering keywords used to visit the page of multiple users to generate a list of keywords representing a group of users'"'"' information needs; and

computing a relative success rate of a cluster of keywords.

2. The method as claimed in claim 1, wherein the distance measure and the success rate are measured relative to other pages on the web site of the selected page.

3. The method as claimed in claim 1, wherein determining the success of users'"'"' visits to the page is carried out by determining if a visit meets an internal success criterion based on one or more of:

time spent on page, business logic rules, goals.

4. The method as claimed in claim 1, wherein generating a page profile uses a text feature selection method to determine the keywords representing the page.

5. The method as claimed in claim 1, wherein generating a page traffic profile considers direct traffic to a page including one or more of the group of:

query keywords used to reach the page;

in-links anchor text used to reach the page.

6. The method as claimed in claim 1, wherein generating a page traffic profile considers indirect traffic to a page wherein indirect traffic follows a path through multiple steps in the form of pages or in-links to a page.

7. The method as claimed in claim 6, wherein the page traffic profile includes one or more of the group of:

concatenation of anchor text of hyperlinks used to reach the page and/or query keywords used in an initial query resulting in a browsing session reaching the page, smoothing of relative contributions of each session step, relative boosting of results closer to the end page.

8. The method as claimed in claim 1, wherein analyzing whether a page satisfies users'"'"' information needs considers a distance measurement between the list of keywords of the page profile and the list of keywords of a cluster, and the success of the cluster relative to other pages.

9. The method as claimed in claim 1, including:

displaying a visualization of the analysis including;

displaying a first tag cloud of the list of keywords of the page profile with a scaled representation of how representative the keyword is of the page content;

displaying a second tag cloud of the list of keywords of the page traffic profile with a scaled representation of how well satisfied the keyword is in the page content.

10. The method as claimed in claim 9, wherein in the first tag cloud different colors are used to represent scales of well represented keywords and scales of poorly represented keywords.

11. The method as claimed in claim 9, wherein in the second tag cloud different colors are used to represent scales of well satisfied the keywords in the page content and scales of poorly satisfied keywords in the page content.

12. A computer-implemented method for measuring web site satisfaction of information needs, performed by a processor, comprising:

selecting a page for analysis;

generating a page profile in the form of a list of keywords representing the page;

generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords, wherein;

if the distance measure is relatively low and the success rate is relatively high it is determined that the page satisfies the information need for a keyword; and

the method includes returning a ranked list of keywords in this category for the page.

13. A computer-implemented method for measuring web site satisfaction of information needs, performed by a processor, comprising:

selecting a page for analysis;

generating a page profile in the form of a list of keywords representing the page;

generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords, wherein;

if the distance measure is relatively low and the success rate is relatively low it is determined that the page does not satisfy the information need for a keyword; and

the method includes returning a ranked list of keywords in this category for the page.

14. A computer-implemented method for measuring web site satisfaction of information needs, performed by a processor, comprising:

selecting a page for analysis;

generating a page profile in the form of a list of keywords representing the page;

generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords, wherein;

if the distance measure is relatively high and the success rate is relatively high it is determined that the page presents an interest drift for an information need for a keyword; and

the method includes returning a ranked list of keywords in this category for the page.

15. A computer-implemented method for measuring web site satisfaction of information needs, performed by a processor, comprising:

selecting a page for analysis;

generating a page profile in the form of a list of keywords representing the page;

generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords, wherein;

if the distance measure is relatively high and the success rate is relatively low it is determined that the page does not satisfy the information need for a keyword; and

the method includes returning a ranked list of keywords in this category for the page.

16. A computer-implemented method for measuring web site satisfaction of information needs, performed by a processor, comprising:

selecting a page for analysis;

generating a page profile in the form of a list of keywords representing the page;

generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determining the success of users'"'"' visits to the page using keywords of the page traffic profile;

analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords; and

displaying a visualization of the analysis including;

displaying a first tag cloud of the list of keywords of the page profile with a scaled representation of how representative the keyword is of the page content;

displaying a second tag cloud of the list of keywords of the page traffic profile with a scaled representation of how well satisfied the keyword is in the page content; and

displaying arrows between the first and second tag clouds that represent the traffic, the traffic success, and traffic satisfaction.

17. A computer program product for measuring web site satisfaction of information needs, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to;

select a page for analysis;

generate a page profile in the form of a list of keywords representing the page;

generate a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

determine the success of users'"'"' visits to the page using keywords of the page traffic profile; and

analyze whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords,

wherein generating a page traffic profile includes;

clustering keywords used to visit the page of multiple users to generate a list of keywords representing a group of users'"'"' information needs; and

computing a relative success rate of a cluster of keywords.

18. A system for measuring web site satisfaction of information needs comprising:

a processor;

a page selection component for selecting a page for analysis;

a page profile component for generating a page profile in the form of a list of keywords representing the page;

a page traffic profile component for generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

a success component for determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

an analysis component for analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords,

wherein the page traffic profile component includes;

a clustering component for clustering keywords used to visit the page of multiple users to generate a list of keywords representing a group of users'"'"' information needs; and

a cluster success component for computing a success rate of a cluster.

19. The system as claimed in claim 18, including:

a visualization component for displaying a visualization of the analysis including;

displaying a first tag cloud of the list of keywords of the page profile with a scaled representation of how representative the keyword is of the page content;

displaying a second tag cloud of the list of keywords of the page traffic profile with a scaled representation of how well satisfied the keyword is in the page content.

20. The system as claimed in claim 19, wherein in the first tag cloud different colors are used to represent scales of well represented keywords and scales of poorly represented keywords.

21. The system as claimed in claim 19, wherein in the second tag cloud different colors are used to represent scales of well satisfied the keywords in the page content and scales of poorly satisfied keywords in the page content.

22. A system for measuring web site satisfaction of information needs comprising:

a processor;

a page selection component for selecting a page for analysis;

a page profile component for generating a page profile in the form of a list of keywords representing the page;

a page traffic profile component for generating a page traffic profile in the form of lists of keywords representing information needs of users, wherein the page traffic profile is generated from keywords used by users to visit the page;

a success component for determining the success of users'"'"' visits to the page using keywords of the page traffic profile; and

an analysis component for analyzing whether a page satisfies users'"'"' information needs by applying a distance measure between the keywords of the page profile and the keywords of the page traffic profile and combining the distance measure result with a success rate of the keywords,

wherein the page traffic profile component includes;

a clustering component for clustering keywords used to visit the page of multiple users to generate a list of keywords representing a group of users'"'"' information needs, and

wherein the analysis component includes;

a distance measuring component for measuring a distance between the list of keywords of the page profile and the list of keywords of a cluster generated by the clustering component.