56
Search and Browsing Cycle for Knowledge Discovery and Learning Sebastian Ryszard Kruk [email protected] DERI, NUI Galway 1

Search and Browsing Cycle for Knowledge Discovery and Learning

Embed Size (px)

DESCRIPTION

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

Citation preview

Page 1: Search and Browsing Cycle for Knowledge Discovery and Learning

Search and Browsing Cycle for Knowledge

Discovery and LearningSebastian Ryszard [email protected]

DERI, NUI Galway

1

Page 2: Search and Browsing Cycle for Knowledge Discovery and Learning

Search and Browsing Cycle for Knowledge

Discovery and LearningSebastian Ryszard [email protected]

DERI, NUI Galway

1

Page 3: Search and Browsing Cycle for Knowledge Discovery and Learning

2

Take away message

2

Page 4: Search and Browsing Cycle for Knowledge Discovery and Learning

2

Take away message

• We search in different ways for different things

2

Page 5: Search and Browsing Cycle for Knowledge Discovery and Learning

2

Take away message

• We search in different ways for different things

• Keyword search is not enough

2

Page 6: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 7: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 8: Search and Browsing Cycle for Knowledge Discovery and Learning

Motivation

4

Page 9: Search and Browsing Cycle for Knowledge Discovery and Learning

Motivation

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

4

Page 10: Search and Browsing Cycle for Knowledge Discovery and Learning

Motivation

How to share and interconnect knowledge among people?

4

Page 11: Search and Browsing Cycle for Knowledge Discovery and Learning

5

How do people search?

• Different user goals:

5

Page 12: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 13: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 14: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 15: Search and Browsing Cycle for Knowledge Discovery and Learning

6

Search and browsing

6

Page 16: Search and Browsing Cycle for Knowledge Discovery and Learning

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

6

Page 17: Search and Browsing Cycle for Knowledge Discovery and Learning

6

Search and browsing

• Why?

• Knowledge can be useful

• Not everything is a useful knowledge

• How? (Search and browsing actions)

6

Page 18: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 19: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 20: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 21: Search and Browsing Cycle for Knowledge Discovery and Learning

7

Keyword-based search

Why is it not enough?

7

Page 22: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 23: Search and Browsing Cycle for Knowledge Discovery and Learning

8

Keyword-based search

How we can improve?

8

Page 24: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 25: Search and Browsing Cycle for Knowledge Discovery and Learning

9

Keyword-based search

What’s next?

9

Page 26: Search and Browsing Cycle for Knowledge Discovery and Learning

9

Keyword-based search

What’s next?

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

• Continue to faceted navigation

9

Page 27: Search and Browsing Cycle for Knowledge Discovery and Learning

10

Faceted navigation

Why we need that?

10

Page 28: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 29: Search and Browsing Cycle for Knowledge Discovery and Learning

11

Faceted navigation

How we do better?

11

Page 30: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 31: Search and Browsing Cycle for Knowledge Discovery and Learning

12

Browsing the data graph

12

Page 32: Search and Browsing Cycle for Knowledge Discovery and Learning

12

Browsing the data graph

MultiBeeBrowse exploits interconnected data ...

12

Page 33: Search and Browsing Cycle for Knowledge Discovery and Learning

13

Browsing the data graph

13

Page 34: Search and Browsing Cycle for Knowledge Discovery and Learning

13

Browsing the data graph

... to allow faceted navigation

13

Page 35: Search and Browsing Cycle for Knowledge Discovery and Learning

14

Social Semantic Collaborative Filtering

14

Page 36: Search and Browsing Cycle for Knowledge Discovery and Learning

14

Social Semantic Collaborative Filtering

Why do we need collaboration?

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

14

Page 37: Search and Browsing Cycle for Knowledge Discovery and Learning

15

Social Semantic Collaborative Filtering

15

Page 38: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 39: Search and Browsing Cycle for Knowledge Discovery and Learning

16

Social Semantic Collaborative Filtering

16

Page 40: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 41: Search and Browsing Cycle for Knowledge Discovery and Learning

17

Social Semantic Collaborative Filtering

17

Page 42: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 43: Search and Browsing Cycle for Knowledge Discovery and Learning

18

Social Semantic Collaborative Filtering

18

Page 44: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 45: Search and Browsing Cycle for Knowledge Discovery and Learning

19

Social Semantic Collaborative Filtering

19

Page 46: Search and Browsing Cycle for Knowledge Discovery and Learning

19

knows

include

bookmark

Social Semantic Collaborative Filtering

19

Page 47: Search and Browsing Cycle for Knowledge Discovery and Learning

19

knows

include

bookmark

Social Semantic Collaborative Filtering

19

Page 48: Search and Browsing Cycle for Knowledge Discovery and Learning

20

Putting it all together

20

Page 49: Search and Browsing Cycle for Knowledge Discovery and Learning

20

Putting it all together

20

Page 50: Search and Browsing Cycle for Knowledge Discovery and Learning

20

Putting it all together

refinesearch results

filter, record, annotate, and share results and actions

user profile:user’s interests

20

Page 51: Search and Browsing Cycle for Knowledge Discovery and Learning

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

Page 52: Search and Browsing Cycle for Knowledge Discovery and Learning

21

Search and Browsing in e-Learning space

21

Page 53: Search and Browsing Cycle for Knowledge Discovery and Learning

21

Search and Browsing in e-Learning space

21

Page 54: Search and Browsing Cycle for Knowledge Discovery and Learning

21

Search and Browsing in e-Learning space

21

Page 55: Search and Browsing Cycle for Knowledge Discovery and Learning

21

Search and Browsing in e-Learning space

21

Page 56: Search and Browsing Cycle for Knowledge Discovery and Learning

21

Search and Browsing in e-Learning space

Sebastian Ryszard KrukeLearning Cluster

DERI, NUI Galway

[email protected]

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

21