Transcript 로그 수집 - Soft Computing Lab.

2006 지식기반시스템 응용
인지구조기반 마이닝
2006. 11. 7
소프트컴퓨팅 연구실 박사 2학기
박한샘
Learning Predictive Models of
Memory Landmarks
E. Horvitz, S. Dumais, and P. Koch,
26th Annual Meeting of Cognitive Science Society, Chicago, 2004
Introduction
 Episodic memory
Memories are considered to be organized by episodes of
significant events
 Automated inference of memory landmark
Could provide the basis for new kinds of personalized computer
applications & services
 Focus of this paper
The construction, testing and application of predictive models of
memory landmarks
Based on events drawn from users’ online calendars
Events
 Calendar event crawler
Works with the MS Outlook messaging and appointment management
system & MS Active Directory Service
Extracts approximately 30 properties for each event
 Properties
From Outlook
Time of day, day of week, event duration, subject, location, organizer,
number of invitees, relationships between the user and invitees, the
role of the user, response status, recurrent, inviting email alias …
From Active Directory Service
(attendees) organizational peers, managers, managers of the user’s
manager …
 Rare contexts
Atypical attendee, atypical location, atypical duration …
Building Models: Data
 5 participants are asked to
Review all the appointments, holidays and other annotations in the
calendars
Identify the subset of memory landmarks
 Predictive models of memory landmarks
Constructed using BN learning methods (Chickering et al.)
 Data partitioning
Training : test = 80 : 20
Building Models: BN Structure
 BN structure from S1
 Key influencing variables
Subject, location string, meeting sender, meeting organizer, attendees,
and recurrent
 Landmark events
Atypically long durations, non-recurrence of events, a user flagging a
meeting as busy
Out of office and
atypical locations
Special locations
Classification Accuracy & ROC Curve
 Classification accuracies
 ROC curves
Show the relationship of false
negatives and false positives
for 5 subjects
MemoryLens: Characteristics
 As a prototype
Demonstrates how the predictive models might be used
Focuses on providing users with a timeline of landmark events to assist
them to find content across their computer store
 Predictive model
Allows users to train models on a portion of events from their calendar
Constructed model predicts each event if it is a landmark
MemoryLens: Screen Shot
By threshold
Memory landmarks
Summary & Future Research
 Summary
This paper
Construct predictive models of memory landmarks
Provided a prototype application
 Future research
Generalization of models
Beyond calendar events
New classes of evocative features
Learning models of forgetting
Milestones in Time:
The Value of Landmarks in Retrieving Information
from Personal Stores
M. Ringel, E. Cutrell, S. Dumais, and E. Horvitz,
Proceedings of Interact 2003: Ninth International Conference on HumanComputer Interaction, Zurich, 2003.
Introduction
 Searching
People employ various strategies
when searching personal e-mails, files, or web bookmarks
Though exact dates may not be remembered,
people recall the relative times of important events in their lives
 SIS (Stuff I’ve Seen)
Provides timeline-based presentation of search results
Provides results represented by public and personal landmark events
Indexes the full text and metadata of all the documents,
web pages and email that a user has seen
Visualization Interface
 Provides an interactive visualization of SIS results
backbone
date & landmark
overview
timeline
Public Landmarks
 Public landmarks
Drawn from events that users typically be aware of
All public landmarks have given priorities
In this prototype, all users saw the same public landmarks
 Holidays
US holidays occurred from 1994 - 2004
Priorities are manually assigned based on American culture
 News headlines
News headlines from 1994 - 2001 are extracted from the world history
timeline from MS Encarta, a multimedia encyclopedia
10 MS employees rate a set of news headlines on a scale of 1 - 10
Personal Landmarks
 Personal landmarks
These are unique for each user
In this prototype, all landmarks are automatically generated
 Calendar appointments
Dates, times, and titles of appointments stored in MS Outlook calendar
were automatically extracted as personal landmarks
Each appointment has priority according to heuristics
 Digital photographs
Crawled the users’ digital photographs
The first photo of the day is selected as a landmark for that day
Similarly, the first one of the month and year also have high priority
User Study




12 MS employees (male, 25-60) participated
Each participant completed a series of tasks using 2 interfaces
All subjects performed the same 30 search tasks
After completing all tasks, subjects filled out a second questionnaire
Result: Search Time
 Median search time comparison
Neutralize skewing
 The difference is significant (p<0.05)
Result: Questionnaire
 7-point scale (1: strongly disagree, 7: strongly agree)
Conclusions & Future Work
 Conclusions
A timeline-based visualization of search results
An interface with public and personal landmark events
aid people in locating the target of their search
A user study found there was a significant time savings for searching
 Future work
Extending the type of events (personal & public, now)
Refining heuristics in selecting and ranking landmarks