Shifting ICT to ICA - Towards I nformation and C ommunication A ctivity N avigation -
description
Transcript of Shifting ICT to ICA - Towards I nformation and C ommunication A ctivity N avigation -
Hideaki Takeda / National Institute of Informatics
Shifting ICT to ICA- Towards Information and Communication Activity Navigation -
Hideaki TakedaNational Institute of Informatics
&The Graduate University for Advanced Studies
[email protected]://www-kasm.nii.ac.jp/~takeda/
Hideaki Takeda / National Institute of Informatics
Table of Contents
NMM:Re-configuration of personal human network
Kmedia: Finding relationship via WWW bookmarks
TelMeA: Expressive Media for Online Communities
Community Navigator: Collaborative Scheduling Support System for Conferences
Social Scheduler: Collaborative Scheduler for Personal Resources
TelMeA for e-Kyoshitsu: Application to Distance Learning
Introduction: Shifting ICT to ICA
Our Research Topics
Summary
H. Takeda
Shifting ICT to ICA- Towards Information and Communication Activity Navigation -
Hideaki Takeda / National Institute of Informatics
From “old computing” to “new computing”“The old computing was about what computers could do; the new
computing is about what users can do. Successful technologies are those that are in harmony with users’ needs. They must support relationships and activities that enrich the users’ experiences.” Ben Shneiderman, Leonardo's Laptop: Human Needs and the New Computing Technologies, MIT Press, 2002
Paradigm shift is needed Technology-centered approach Human-centered approach
Hideaki Takeda / National Institute of Informatics
ART(Activity-Relationship-Table)
COLLECT(Information)
RELATE(Communication)
CREATE(Innovation)
DONATE(Dissemination)
Self
Family and friends(2-50 intimates)
Colleagues and neighbors(50-5,000 regular encounters)
Citizens and markets(5,000+)
Ben Shneiderman, Leonardo's Laptop: Human Needs and the New Computing Technologies, MIT Press, 2002
Hideaki Takeda / National Institute of Informatics
Communication Layer
RelateCollaborate
Present
Communication layer concerns potential information. Potential information can be revealed through communication among people.
Information and Communication Activities Two layers for our activities
Create
Information Layer
Collect Donate
Information layer only concerns explicitly represented and processed information.
Hideaki Takeda / National Institute of Informatics
Information Activities A cycle of information exploitation
Collect Find and retrieve information
Create Process (classify, extract, combine, mix, …) information Generate new information
Donate Publish and distribute information
Create
Information Layer
Collect Donate
Hideaki Takeda / National Institute of Informatics
Communication Layer
RelateCollaborate
Present
Communication Activities A cycle of human relationship exploitation
Relate Find and contact people
Collaborate Work with other people (organized work, teamwork, cooperation, …)
Present Identify and contribute ourselves to communities
Hideaki Takeda / National Institute of Informatics
RelateCollaborate
Present
Information and Communication Activity Navigation (ICAN)
Support by computers for six categories of ICA
CreateCollect Donate
NMM:Re-configuration of personal human network
Kmedia: Finding relationship via WWW bookmarks
TelMeA: Expressive Media for Online Communities
Community Navigator: Collaborative Scheduling Support System for Conferences
Social Scheduler: Collaborative Scheduler for Personal Resources
TelMeA for e-kyoshitsu
H. Takeda, M. Hamasaki, T. Matsuzuka, Y. Taniguchi
Discovery of Shared Topics Networks among People
A Simple Approach to Find Community Knowledge from WWW Bookmarks
Hideaki Takeda / National Institute of Informatics
Purpose Generation of human network guiding individual information
activities An example
I want to watch sports programs on TV. What your recommendation?
Who and What Shared Topics Network among Users (STN)
Hideaki Takeda / National Institute of Informatics
Bookmarks as Knowledge
A bookmark folder= A topic interested by the user
URLs in a bookmark folder= Examples of the topic
21
4 3e
a b
f c
dz
x
User
y
WWW page (information on the topic)
Folder (topic)
Bookmark (person’s interest)
5
g Shared Topics Network
Hideaki Takeda / National Institute of Informatics
A
C
B
Discovery of topic relations
computer-relatedresearch-related
search
Informationretrieval
academia
Common relations (search, IR), (academia, research-related) similar but words themselves are different
Un-common relations …(Unix, academia)
Speciality of thecommunity
Hideaki Takeda / National Institute of Informatics
A
C
B
Discovery of relationship among people
computer-relatedresearch-related
search
Informationretrieval
academia
What are common topics with others? Who is good at this topic?
unix
research
research
Hideaki Takeda / National Institute of Informatics
Category Resemblance (1)Categorization Is Human Relation?
Human relation can be measured by resemblance of folder structure
Folder structure is similar Not similar
Cij =Nfij × Rfij
NpijCij : Category resemblanceNfij : No. of recommended folders Rfij : Folder relevanceNpij : No. of recommended pages
Hideaki Takeda / National Institute of Informatics
Better page recommendation results for new group made from category resemblance (CR)
22.12.22.32.42.52.62.72.8
In-community
Cross-community
New groups
All
Page RecommendationScore
Effects of Category Resemblance (4) for Page Recommendation
Hideaki Takeda / National Institute of Informatics
Summary Proposal of shared topic network to enhance user’s
communication Proposal of algorithm of discovery of shared topic networks with
WWW bookmark files Validity of our approach by an experiment Proposal of category resemblance as measurement for community
effects
M. Hamasaki, H. Takeda
Re-configuration of personal networks by the neighborhood matchmaker method
Hideaki Takeda / National Institute of Informatics
Purpose Personal network is usually “ad hoc”
We may miss better friends nearby We need better network One Solution:
Collect data for all people, then generate the “best” networkDisadvantage:
Scalability Privacy
Our approach: Neighborhood Matchmaker Method (NMM)
Hideaki Takeda / National Institute of Informatics
Neighborhood Matchmaker Method (NMM)
A iterative approach to optimize the network Every node works as a matchmaker for neighborhood nodes to
improve the network The basic idea
In our real life, introducing new friends by the current friends is a practical way to optimize personal networks
We can know persons who you have not known before Your friend can filter people for you
Advantages No need for central servers Applicable to any size of community Less computational cost
Hideaki Takeda / National Institute of Informatics
Algorithm 1. A node calculates connection values between its neighbor nodes
We call that node “matchmaker” 2. If the matchmaker finds a pair of nodes which has a good enough connection
value, it selects this pair for recommendation. The matchmaker introduces both nodes of recommended pair to each other
3. The node that receives recommendation decides whether it accepts or not. If it accepts, it adds a path to the recommended node
!?
Calculating connection values
matchmaker
matchmakerGood !!
Introducing each nodes
OKOK
Adding a new path
matchmaker
Hideaki Takeda / National Institute of Informatics
Results: Cover-Rate w.r.t. Nodes The path size is fixed as three times as the node size All cases were converged The average of cover-rate and the turn of convergence vary with the node size
00.10.20.30.40.50.60.70.80.9
1
0 50 100 150 200 250 300 350 400 450 500
20node40node60node80node100node
Cov
er-R
ate
Turn
100node
80node
20node
40node
60node
Hideaki Takeda / National Institute of Informatics
Results: Average of Convergence Turn The number of convergence turn is linearly increased with the
node size Computational cost
NMM: O(N) Central Server Model: O(N2)
0
100
200
300
400
500
600
10 20 30 40 50 60 70 80 90 100
1p/node2p/node3p/node4p/node5p/node
Con
verg
ence
Tur
n
The node size
1path/node
5path/node
2path/node
4path/node
3path/node
Hideaki Takeda / National Institute of Informatics
Conclusion Proposal of optimization of “ad hoc” network Good news for the Internet communities
No need for central servers Applicable to any size of community Anytime Algorithm
H. Takeda, M. HamasakiIn cooperation with Yutaka Matsuo and Takuichi Nishimura
Community Navigator:Collaborative Scheduling Support System for Conferences
Hideaki Takeda / National Institute of Informatics
Purpose System Aim: Support people to find their friends in a specific group Research Theme: Investigate different human networks in the same group Three human networks
Human network in the activity: I worked with him Human network by communication: I know him Human network by behavior: I meet him
Scheduling on conferences Plan and Action
“I know him”“I worked with him” “I meet him”
Planning action
Hideaki Takeda / National Institute of Informatics
System Functions Easy-to-use scheduling system for the conference
Just add presentations what you want to watch Can refer schedules of other people
Manually collaborative scheduling Can only see schedules of who know you
Can recommend schedules collaborative scheduling
On-site support of schedules Small communication device with sensors
Takuichi Nishimura, Hideo Itoh, Yoshinobu Yamamoto and Hideyuki Nakashima. ``A compact battery-less information terminal (CoBIT) for location-based support systems," In Proceeding of SPIE, number 4863B-12, 2002.
Cobit
Hideaki Takeda / National Institute of Informatics
Outlook
Hideaki Takeda / National Institute of Informatics
Recommendation Recommendation by pattern similarity
Naïve collaborative filtering Paper recommendation Person recommendation
Recommendation by personal networkReply on selection by friends Paper recommendation Person recommendation
Paper1
Paper2
Paper3
Paper4
Paper5
Person A 1 0 1 1 1Person B 0 1 0 1 0Person C 1 1 1 1 0Person D 0 0 1 1 1
Hideaki Takeda / National Institute of Informatics
Recommendation
Ikki Ohmukai, H. Takeda
Social Scheduler: Collaborative Personal Task Scheduler
Hideaki Takeda / National Institute of Informatics
Social Scheduler: Collaborative Personal Task Scheduler
Mobile Task Scheduler for Daily Life Everyone belongs several groups and communities Some groups were built emergently and have ambiguous
boundaries No one cannot manage “my” schedule
Collaborative Model of Personal Scheduling Based on information sharing with one’s friends Access control and filtering according to each group Cell-phone application
Hideaki Takeda / National Institute of Informatics
Social SchedulerCollaborative Personal Task Scheduler
Create friends network by authorization Task conditions become viewable and updatable by each other
Server merges all friends network into alliance network The system considers partial complete graphs as emerging gro
ups (unit of information sharing/filtering)
Hideaki Takeda / National Institute of Informatics
Social Scheduler: Collaborative Personal Task Scheduler
Experiment12 subjects from various
communities3 weeks in use41.9 tasks/person76 collaborative tasks
Social NetworkThe system can find multiple
communities around the user
Distance of each friend can be measured by the number of groups they share
Toru Takahashi, Yasuhiro Katagiri, H. Takeda
TelMeAShow Me What You Mean -
Expressive Media for Online Communities
Hideaki Takeda / National Institute of Informatics
TelMeA2002
Hideaki Takeda / National Institute of Informatics
Conversation Process in TelMeA2002
3. The massage is accumulated in the conversation log
Personified Media
Participant of a TelMeA Community
2. Submit the message to the community server
Hello!
Other Participants of the Community
6. The message is asynchronously enacted
1. Edit a message in terms of a script language
EditorScreen Shot of TelMeA2003
4. Request for seeing the message from others
Conversation Log of the TelMeA Community
5. The required message is downloaded
Hello!
Hideaki Takeda / National Institute of Informatics
Our Goal
Find pragmatic rules of social and nonverbal interactions Supporting social and nonverbal interactions Archiving the logs of long-term community activities Analyzing usages and effects of nonverbal expressivity
Make a model of multimodal social interaction Calculate social evaluations for involved information Summarize or make reutilize the involved information
Toru Takahashi, Yasuhiro Katagiri, H. Takeda
e-kyoshitu(e-classroom) Project
Hideaki Takeda / National Institute of Informatics
Trial Use: e- 教室 (e-classroom) Project e- 教室 (e-classroom) Project:
Run by NPO Distance learning for children (mainly junior-high school, 12-15y
rs) Several classrooms (math, economics, CG, etc)
TelMeA for e- 教室 Experimental use of TelMeA Classroom for
Leaning “agent” as new technologies by usingCommunicating to each other (“BBS” for participants)
(demo)
Hideaki Takeda / National Institute of Informatics
TelMeA for e- 教室
Hideaki Takeda / National Institute of Informatics
The current status of “TelMeA for e- 教室” Period: c.a. 4 month (2003.1.16-) Login users: 64 Posted users: 24 Post No.: 297, Post thread No.: 22
Hideaki Takeda / National Institute of Informatics
Summary Information technologies, in particular AI can offer new
opportunities for communities Reducing constraints of the real world
Time, space, etc new communication ways
Knowing new related people, communication via agents etc They will change meaning or roles of communities
e.g, Very weak communitiesQuick life cycle of communitiesBelonging so many communities
Hideaki Takeda / National Institute of Informatics
Summary Challenges
Support of life cycle of communitiesCreate, maintain, diverse, merge, disappear
TrustTrust is very difficult Trust may be more complicated than the real world…