Search and Browsing Cycle for Knowledge Discovery and Learning

Post on 12-May-2015

2.469 views 0 download

Tags:

description

Slides from the presentation I gave at 5th Annual Conference on Teaching & Learning: Learning Technologies, June 7/8, 2007

Transcript of Search and Browsing Cycle for Knowledge Discovery and Learning

Search and Browsing Cycle for Knowledge

Discovery and LearningSebastian Ryszard Kruksebastian.kruk@deri.org

DERI, NUI Galway

1

Search and Browsing Cycle for Knowledge

Discovery and LearningSebastian Ryszard Kruksebastian.kruk@deri.org

DERI, NUI Galway

1

2

Take away message

2

2

Take away message

• We search in different ways for different things

2

2

Take away message

• We search in different ways for different things

• Keyword search is not enough

2

2

Take away message

• We search in different ways for different things

• Keyword search is not enough

• We create the knowledge by sharing our (search) experience

2

3

Outline

• Motivation

• How do people search

• Search and Browsing life-cycle

• Applying semantics and making use of social networks:

• Keyword-based search

• Faceted Navigation

• Collaborative Filtering

• Conclusions

3

Motivation

4

Motivation

How to discover and integrate knowledge coming from both formal and informal sources?

4

Motivation

How to share and interconnect knowledge among people?

4

5

How do people search?

• Different user goals:

5

5

How do people search?

• Different user goals:

– Resource Seeking - the user wants to find a specific resource (e.g. lyrics of a song, a program to download, a map service etc.)

5

5

How do people search?

• Different user goals:

– Resource Seeking - the user wants to find a specific resource (e.g. lyrics of a song, a program to download, a map service etc.)

– Navigational - the user is searching for a specific web site whose URL s/he forgot

5

5

How do people search?

• Different user goals:

– Resource Seeking - the user wants to find a specific resource (e.g. lyrics of a song, a program to download, a map service etc.)

– Navigational - the user is searching for a specific web site whose URL s/he forgot

– Informational - the user is looking for information about a topic s/he is interested in

5

6

Search and browsing

6

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

6

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

• How? (Search and browsing actions)

6

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

• How? (Search and browsing actions)

– [REUSE] keyword-based search (resource seeking)

6

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

• How? (Search and browsing actions)

– [REUSE] keyword-based search (resource seeking)

– [REDUCE] faceted navigation (navigational)

6

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

• How? (Search and browsing actions)

– [REUSE] keyword-based search (resource seeking)

– [REDUCE] faceted navigation (navigational)

– [RECYCLE] collaborative filtering (informational)

6

7

Keyword-based search

Why is it not enough?

7

7

Keyword-based search

Why is it not enough?

• Too many results (low precision)

• One needs to specify the exact keyword (low recall)

• How to distinguish between: Python and python? (high fall-out)

7

8

Keyword-based search

How we can improve?

8

8

Keyword-based search

How we can improve?

• Disambiguation through a context

• Long-term: user’s interests, engine type

• Short-term: user’s goal, location, time

• Query

• Query refinement

8

9

Keyword-based search

What’s next?

9

9

Keyword-based search

What’s next?

• “Tell me why” button and the transcript of refinement process

• Continue to faceted navigation

9

10

Faceted navigation

Why we need that?

10

10

Faceted navigation

Why we need that?

• The search does not end on a (long) list of results

• The results are not a list (!) but a graph

• „Lost in hyper-space”

• A need for unified UI and services for filter/narrow and browse/expand services

• Share browsing experience – navigate collaboratively

10

11

Faceted navigation

How we do better?

11

11

Faceted navigation

How we do better?

• A set of navigation services: access, search, filter, similar, browse, and combine

• Auxiliary services: meta, context, and statistics

• Zoom-able, adaptable, and accessible user interface

• Engage users in collaborative browsing

11

12

Browsing the data graph

12

12

Browsing the data graph

MultiBeeBrowse exploits interconnected data ...

12

13

Browsing the data graph

13

13

Browsing the data graph

... to allow faceted navigation

13

14

Social Semantic Collaborative Filtering

14

14

Social Semantic Collaborative Filtering

Why do we need collaboration?

• The bottom-line of acquiring knowledge: informal communication (“word of mouth”)

14

15

Social Semantic Collaborative Filtering

15

15

Social Semantic Collaborative Filtering

How can that help?

• Everyone classifies (filters) the information in bookmark folders (user-oriented taxonomy)

• Peers share (collaborate over) the information (community-driven taxonomy)

15

16

Social Semantic Collaborative Filtering

16

16

Social Semantic Collaborative Filtering

What do we got?

• Knowledge “flows“ from the expert through the social network to the user

• Systems amass a lot of information on user/community profile (context)

16

17

Social Semantic Collaborative Filtering

17

17

Social Semantic Collaborative Filtering

What problems can we encounter?

• The horizon of a social network (2-3 degrees of separation)

• How to handle fine-grained information (blogs, wikis, etc.)

17

18

Social Semantic Collaborative Filtering

18

18

Social Semantic Collaborative Filtering

How to solve them?

• Inference engine to suggest knowledge from the outskirts of the social network

• Support for Semantically Interlinked Online Communities (SIOC) metadata

18

19

Social Semantic Collaborative Filtering

19

19

knows

include

bookmark

Social Semantic Collaborative Filtering

19

19

knows

include

bookmark

Social Semantic Collaborative Filtering

19

20

Putting it all together

20

20

Putting it all together

20

20

Putting it all together

refinesearch results

filter, record, annotate, and share results and actions

user profile:user’s interests

20

20

Putting it all together

user profile:recent actions

refinesearch results

filter, record, annotate, and share results and actions

re-call shared actions

user profile:user’s interests

filter, record, annotate,

and share results

20

21

Search and Browsing in e-Learning space

21

21

Search and Browsing in e-Learning space

21

21

Search and Browsing in e-Learning space

21

21

Search and Browsing in e-Learning space

21

21

Search and Browsing in e-Learning space

Sebastian Ryszard KrukeLearning Cluster

DERI, NUI Galway

sebastian.kruk@deri.org

http://elite.deri.org/http://www.corrib.org/

21