An Automatic Personalized ContextAware Event Notification System for Mobile Users

1
An Automatic Personalized Context-Aware Event
Notification System for Mobile Users

• George Lee
• User Context-based Service Control Group
• Network Laboratories
• NTT DoCoMo RD

2
Overview

• The Problem Mobile users cannot easily get
  desired information
• Proposed solution automatic, personalized,
  context-aware event notification approach
• Matching Engine to match users and events
• User Agent to learn user interests

3
Mobile users cant easily get relevant information

• Relevant information is
• Appropriate for their context
• Personalized based on individual interests
• Current and up-to-date
• Static menu is inadequate
• Too many choices
• Difficult to navigate
• Not personalized or context-aware
• Information retrieval has drawbacks
• Requires queries
• Not good for new or changing information

4
Automatic, personalized, context-aware event
notification

• MIT News
• CSAIL News
• The Tech
• Boston Dining News
• Italian Restaurants
• Central Sq.
• Sports
• Red Sox Scores

Mobile Handset
Context Going to lab
CSAIL News Talk at 3pm G825 Central Sq.
Dining New café opening Red Sox vs.
Yankees 4-3 (6th inning)

• Automatic
• Personalized
• Context-aware

5
Matching events and learning user interests
User Agent automatically learns user interests
for the current context based on user input
Matching Engine decides which users match an
event based on event descriptions and user
preferences
Event
User
User input
Event description
User interests
Matching Engine
User Agent
User
Event
User
Event
6
Describing events and user interests using an
event model
Events and user interests are described and
matched according to an Event Model
matches
Problem existing event notification systems do
not work well with complex event models
7
Choosing an appropriate event model
expressiveness vs. efficiency
Can we improve the matching efficiency
of graph-structured event models?
Flat (e.g. Mailing lists)
Hierarchical (e.g. Newsgroups)
Matching Speed
Graph-structured (e.g. Yahoo!)
Content-based (e.g. XPath)
Expressiveness
8
Regular matching
Event Topic Red Sox

• Event topic Red Sox
• Matches all users with Red Sox as a subtopic in
  their interests
• (Red Sox, Boston Sports, Baseball, Sports, and
  All)

All

Sports

Baseball
Boston Sports
Must search graph to find related topics

Red Sox
Yankees
9
Optimized matching
Event Topic Red Sox

• Compute a table of all supertopics of each topic
  (transitive closure)

All

Sports

Baseball
Boston Sports
Gets all related topics in one table lookup

Red Sox
Yankees
10
Evaluation of efficient matching

• Objective Evaluate optimized matching with many
  users and a complex event model
• Event Model
• Topic Open Directory Project (ODP)
• Location Getty Thesaurus of Geographic Names
  (TGN)
• 44,506 topics, 6905 locations
• Simulated users
• 100 to 100,000 users
• Interests include 5 topics and 3 locations
• Simulated events
• Contain 3 random topics and 2 random locations

11

• Efficient Optimized matching is 30 times faster
  than unoptimized matching
• Expressive Works well with complex event models
  with 45,000 topics and 7000 locations
• Scalable Can match 10,000 users in less than 10
  seconds

12
A user agent for learning user interests
User Agent automatically learns user interests
for the current context based on user input
Context Server
Event
User
User input
Event description
User interests
Matching Engine
User Agent
User
Event
User

• Challenges
• Implicitly learning user interests
• Recommending topics in new contexts

Event
13
Learning and automatically updating user interests
Context Server
Automatically recommends new topics based on
ratings of past topics
Implicitly learns user ratings for topics based
on user selections
User Agent
Mobile Handset
Selected Topics
User Interests
Topic Rating Learner
Topic Recommender
Matching Engine

• Event List
• Topic 1
• Topic 2
• Topic 3

Matched events
14
Recommending topics

• Recommendations needed for new topics and
  contexts
• Possible approaches
• Popularity not personalized
• Rating History recommendations based on previous
  topic ratings
• Collaborative Filtering (CF) recommendations
  based on interests of users with similar interests

15
Context-aware Collaborative Filtering
Is User X interested in MIT News for context
Go to lab?

• To calculate a recommendation for topic T in
  context C
• Find users who have rated topic T under context C
• Find users with similar interests
• Decide whether to recommend topic T based on
  ratings of similar users

User A
User B
User X
User C
User D
16
Enhanced Context-aware Collaborative Filtering
Is User X interested in MIT News for context
Go to lab?

• Model relationships between topics and contexts
  when calculating user similarity
• Give greater weight to similar topics and
  contexts (e.g. give greater weight to same topic
  and same context)

User A
Yes
Yes
User X
Yes
Yes
User D
Yes
17
Recommender Evaluation

• Evaluate ability of Enhanced CF to provide
  relevant information in a new context
• User Interface app on mobile handset
• 16 test subjects
• 8 for data collection
• 8 for evaluation
• 50 topics based on i-mode services
• 2 contexts
• Going to see a movie in Tokyo
• Going to Tokyo Disneyland
• 10 topics per recommender
• Interleave topics from two recommenders and
  observe which topics users selected
• vs. Random
• vs. Rating History
• vs. Regular CF

Recommender A
Recommender B
18

• Effective Enhanced CF can recommend relevant
  topics in new contexts
• Compared to other approaches, enhanced CF topics
  selected
• 413 more than Random topics
• 49.7 more than Rating History topics
• 24.8 more than Regular CF topics
• More studies needed to increase confidence

19
Conclusion

• I proposed an event notification system for
  mobile users
• Automatic
• Personalized
• Context-aware
• Research contributions
• Optimized content-graph event matching algorithm
• Enhanced context-aware collaborative filtering
  topic recommender
• Future work
• Distributed architectures
• Learning and recommendation algorithms
• Context models
• User studies