Content Analysis Techniques to Ease Browsing with Handhelds

1
Content Analysis Techniques to Ease Browsing with
Handhelds
Jalal Mahmud Yevgen Borodin I.V. Ramakrishnan
Department of Computer Science State University
of New York at Stony Brook Stony Brook, NY 11794
2
Outline

• Browsing with Handhelds
• Content Analysis Techniques
• - Model-directed Web Transaction
• - Merchant-Side Web Transaction
• - Context Browsing with Mobile
• - Context-directed Web Transaction
• Evaluation
• Future Work

3
Browsing with Handheld
User needs to do a lot of scrolling to get to the
relevant content
Relevant Content
4
Problems

• Small Screens Offer Narrow Interaction Bandwidth.
• Unable to convey the Richness of the Web content.
  
• Involves a Lot of Horizontal and Vertical
  Scrolling.
• Tedious to Get to the Pertinent Content in a
  Page.
• This is worse when one is interested in Web
  transactions (e.g. buying books, paying utility
  bills).

5
Our Approach

• Filter Away Irrelevant Content and Only Present
• Relevant Content
• First Present the Relevant Content.

6
Model-directed Web Transaction

• Web Transaction Examples
• - Buying a CD Player from
  Bestbuy
• - Paying Utility Bills
  Online
• Web Transaction Characteristics
• - A Sequence of Steps
• - Each Step is Based on User-Selected
  Operation
• Two aspects of a Web transaction
• - Semantic Concept
• - Process Model

7
Semantic Concepts
8
Process Model
SEARCH FORM CONCEPT
submit_searchform
1
item_select
TAXONOMY CONCEPT
9
Process Model
item_select
select_item_category
1
submit_searchform
10
Process Model
SEARCH FORM CONCEPT
submit_searchform
item_select
SEARCH RESULT CONCEPT
11
Process Model
item_select
item_select
1
submit_searchform
add_to_cart
select_item_category
2
submit_searchform
12
Process Model
1 - START STATE
add_to_cart
6 - FINAL STATE
show_item_detail
add_to_cart
check_out
3
4
item_select
item_select
view_shoppingcart
item_select
select_item_category
submit_searchform
Submit_searchform
1
6
check_out
add_to_cart
submit_searchform
check_out
select_item_category
2
5
submit_searchform
view_shoppingcart,
update_shoppingcart
continue_shopping
Model-driven transaction
13
Process Model
1 - START STATE
add_to_cart
6 - FINAL STATE
show_item_detail
add_to_cart
check_out
3
4
item_select
item_select
view_shoppingcart
item_select
select_item_category
submit_searchform
Submit_searchform
1
6
check_out
submit_searchform
add_to_cart
check_out
select_item_category
2
5
submit_searchform
view_shoppingcart,
update_shoppingcart
continue_shopping
Model-driven transaction
14
Evaluation Results
Process Model

• Built using Automata Learning Techniques
• Training Data
• Over 200 Transaction Sequences Collected from
  over 30 Sites
• Recall / Precision
• 90 / 96 for Books domain
• 86 / 88 for Consumer Electronics domain
• 84 / 92 for Office Supplies domain

15
Concept Extraction
16
Evaluation Results
Concept Extraction

• Developed a Statistical Model for Each Concept
  using Machine Learning Techniques
• Training Data
• Used Labeled Concepts from Over 100 Pages
  Collected from Two Dozen Sites

17
Evaluation Results
18
Model-directed Web Transaction on Handheld
Guide-O-Mobile
19
Outline

• Browsing with Handhelds
• Content Analysis Techniques
• - Model-directed Web transaction
• - Merchant-Side Process Modeling
• - Context-Browsing with Mobile
• - Context-Directed Web Transaction
• Evaluation
• Future Work

20
Client-Side Process Modeling Problems

• Client-Side Process Modeling in Guide-O-Mobile.
• Process Model is Stored in Client Side.
• Separate Process Model Needed for Each Domain.
• Performance Largely Depends on Concept
  Extraction.

21
Merchant-Side Process Modeling

• Labeled Web Content with Semantic Annotations.
• Content Providers will Label their Web Content.
• XHTML will be Used to
• Label Relevant Content in the Web Sites
• Describe Process Models Specific to the Sites.
• Mobile Users will Use the System to
• Easily Identify Relevant Information.
• Perform On-Line Transactions.

22
Prototype Implementation

• XHTML tags
• , , ,
  , , ,
  , , , detail, , and .

23
Outline

• Browsing with Handhelds
• Content Analysis Techniques
• - Model-directed Web Transaction
• - Merchant-side Web Transaction
• - Context-Browsing with Mobile
• - Context-Directed Web Transaction
• Evaluation
• Future Work

24
Context Browsing with Mobile

• On Following a Link
• Collect Context of the Link
• Identify the Relevant Section on the Next Page
• Using the Context
• Present the Relevant Section.
• Context Browsing
• Reduces Information Overload
• Makes Mobile Browsing Faster.

25
Context-directed Browsing
26
Context-directed Browsing
27
How Do We Find Relevant Content?

• Finding What is Important on a Web Page
• Is Subjective on Any Distinct Page
• Can be Inferred in a Sequence of Pages

28
(No Transcript)
29
(No Transcript)
30
(No Transcript)
31
Context Browsing with Mobile CMo Prototype
32
Product Search Using CMo
33
Outline

• Browsing with Handhelds
• Content Analysis Techniques
• - Model-directed Web transaction
• - Merchant-side Web transaction
• - Context-Browsing with Mobile
• - Context-directed Web Transaction
• Evaluation
• Future Work

34
Context-directed Web Transaction

• No Process Model
• Contextual Browsing with a Domain-Dependent
  Knowledge-Base
• Relevant Segment Identification Using Contextual
• Browsing
• Concept Segment Identification Using
  Knowledge-Base and Heuristics Algorithms

35
Context-directed Web Transaction Prototype
System

• The Online Shopping Knowledge-Base Consists of
  the Following Few Concepts
• SearchForm, AddToCart, Taxonomy,
  ShoppingCart, Checkout, etc.
• Implementing the Prototype is a Work in Progress.

36
Evaluation Guide-O-Mobile Experimental Set-Up

• Guide-O-Mobile
• 1.2 GHz desktop with 256 MB RAM
• Client-Server Model
• Client 400 MHz iPaq with 64 MB RAM
• Server Core Guide-O System
• Evaluation
• Over two dozen CS graduate students
• Over 30 web sites spanning Books, Consumer
  Electronics and Office Supplies domains

37
Evaluation Guide-O Mobile
Guide-O-Mobile Overall Time Performance
38
Evaluation Guide-O Mobile
Guide-O-Mobile Overall Time Performance with
standard deviation
39
Evaluation Guide-O Mobile
Guide-O-Mobile Interaction Time
40
Evaluation Guide-O Mobile
Guide-O-Mobile Interaction Time Performance with
standard deviation
Standard Deviation
41
EvaluationCMo Experimental Set-Up

• Client-Server Model
• Client IPAQ Pocket PC equipped with Microsoft
  Pocket PC operating system with wireless Internet
  connectivity.
• Server Core CMo System
• Evaluation
• 8 CS graduate students completing 8 tasks (8
  times each) on 8 Web sites from News and Shopping
  Domain.

42
EvaluationCMoPerformance of Context
Identification
43
Evaluation CMoRelevant Information
Identification
44
Browsing Efficiency with CMo
45
Conclusion and Future Work

• Port all the Server Steps to the Handheld.
• Extend the Mozilla's Minimo Mobile Browser with
  CMo Functionalities.
• Mining Transactional Models from Contextual
  Information.

46

• Questions?