The power of the modern Web, which is frequently called the Social Web or Web 2.0, is frequently traced to the power of users as contributors of various kinds of contents through Wikis, blogs, and resource sharing sites. However, the community power impacts not only the production of Web content, but also the access to all kinds of Web content. A number of research groups worldwide explore what we call social information access techniques that help users get to the right information using “collective wisdom” distilled from actions of those who worked with this information earlier. Social information access can be formally defined as a stream of research that explores methods for organizing users' past interaction with an information system (known as explicit and implicit feedback), in order to provide better access to information to the future users of the system. It covers a range of rather different systems and technologies from social navigation to collaborative filtering. An important feature of all social information access systems is self-organization. Social information access systems are able to work with little or no involvement of human indexers, organizers, or other kinds of experts. They are truly powered by a community of users. Due to this feature, social information access technologies are frequently considered as an alternative to the traditional (content-oriented) technologies. The goal of this tutorial is to provide an overview of the emerging social information access research stream and to provide some practical guidelines for building social information access systems.

1. Social Information Access
Peter Brusilovsky
with Rosta Farzan, Jaewook Ahn, Sharon
Hsiao, Denis Parra, Michael Yudelson,
Chirayu Wongchokprasitti, Sherry Sahebi
School of Information Sciences
University of Pittsburgh
http://www.sis.pitt.edu/~peterb

2. Personalized and Adaptive Web
Systems Lab (at UMAP 2012)

3. The New Web: the Web of People
http://www.veryweb.it/?page_id=27

4. Web 2.0: Fast Start, Broad Spread
• Term was introduced following the first O'Reilly
Media Web 2.0 conference in 2004
• By September 2005, a Google search for Web 2.0
returned more than 9.5 million results
• In 2013 similar search returned over 1390 million
results

5. Social Web Web 2.0
Social Web of Web 2.0?

6. The Social Web

7. Key Elements
• The Users’ Web
• Collective
Intelligence:
Wisdom of Crowds
• The power of the
user
• Applications
powered by user
community
• Stigmergy
• User as a first-class
participant,
contributor, author
http://www.masternewmedia.org/news/2006/12/01/social_bookmarking_services_and_tools.htm

8. Amazon: Reviews and ratings

9. eBay: Driving a marketplace

10. Wikipedia: Providing content

11. Delicious: Sharing + Organization

12. Social Linking: Identity + Links

13. Publish Your Self: [Micro]Blogs

14. The Other Side of the Social Web
User content
User interaction
Which wisdom of crowds?

15. Social Information Access
Methods for organizing users’
past interaction with an
information system (known as
explicit and implicit feedback),
in order to provide better access
to information to the future
users of the system

16. Critical Questions
• What kind of past interaction to
take into account?
• How to process it to produce
“wisdom of crowds” ?
• In which context to reveal it to
end users?
• How to make wisdom of crowds
useful in this context?

17. Social Information Access: Contexts
Social Navigation
– Social support of user browsing
Social Recommendation (Collaborative Filtering)
– Proactive information access
Social Search
– Social support of search
Social Visualization
– Social support for visualization-based access to information
Social Bookmarking
– Access to bookmarked/shared information facilitated with tags

18. What is Social Search?
- Social Information Access in Search
context
- A set of techniques focusing on:
• collecting, processing, and organizing
traces of users’ past interactions
• applying this “community wisdom” in
order to improve search-based access to
information

19. Variables Defining Social Search I
Which users?
• Creators
• Consumers
What kind of interaction is
considered?
• Browsing
• Searching
• Annotation
• Tagging

20. Variables Defining Social Search II
Which subset of the interactions is
used to assist the current user?
• All
• Group
• Selected Peers (similar, socially connected,
etc)
What kind of search process
improvement?
• Off-line improvement of search engine
performance
• On-line user assistance

21. The Case of Google PageRank
Which users?
Which activity?
What is affected?
How it is affected?
How it improves search?
http://www.labnol.org/internet/google-pagerank-drop-stop-worrying/4835/

22. How Search Could be Changed?
Let’s classify potential impact by stages
Before search During search After search

23. Improving Search Engine Work
Search Engine =
Crawling + Indexing + Ranking
Can we improve crawling?
Can we improving indexing?
Can we improve ranking?

24. Improving Indexing
What is the problem with the classic
approach to indexing?
How indexing can be improved?

25. Social Indexing: Improve Finding
Use social data to expand document index
(document expansion)
What we can get from page authors?
Anchor text provided on a link to the page
What we can get from searchers?
Page selection in response to the query (Scholer,
2002)
Query sequences (Amitay, 2005)
What we can get from other page visitors?
Page annotations (Dmitriev et al., 2006)
Page tags (Yanbe, 2007)

26. Search Engines: Improve Ranking
What we can get from page authors?
Links (Page Rank)
What we can get from searchers?
Page selection in response to the query
(DirectHit)
What we can get from page visitors beyond
seatch context?
Page visit count
Page tags (Yanbe, 2007; Bao, 2007)
Page annotations
Combined approaches
PageRate (Zhu, 2001), (Agichtein, 2006)

27. Using Social Wisdom Before Search
Can be done by both search engines and
external interfaces
Query checking - now standard
Suggesting improved/related queries
Example: query networks (Glance, 2001)
Automatic query refinement and query
expansion
Using past queries and query sequences - what the user is
really looking for (Fitzpatrick, 1997; Billerbeck, 2003;
Huang, 2003)
Using anchors (Kraft, 2004)
Using annotations, tags

28. Using Social Wisdom After Search
Better ranking, link promotion
• Link re-ordering using social wisdom (based
on the result selection traces by earlier
searchers)
Suggesting additional results
• Suggest results (or sites!) found by earlier
searchers (link generation)
Providing social annotations of search
results
• Link popularity
• Past link selection by socially connected users

29. Challenges of Social Search
• Matching similar users
• Number of page hits is not reliable (DirectHit failure)
• Using “everyone” social data is a bad idea – need not
good pages overall, but those that match a query
• Even matching with users who issue the same query is
not reliable enough – same query, very different goals!
• Reliability of social feedback
• A click on a result link is not a reliable evidence of
quality and relevance
• Need to do a wise mining of search sessions and
sequences
• Fusing query relevance and social wisdom
• Single ranking is not the best way to express two
dimensions of relevance

30. Some Advanced Approaches
Improving precision by considering more
similar users
“Quest” approach
Community-based search
Combining community-based search and
navigation
Adjusting the precision to the quality of data
Site-level recommendation

31. AntWorld: Quest-Based Approach
– Quests establish similarities between users
– Relevance between documents and quests is provided
by explicit feedback

32. Quest Approach to Social Search
Quests establish similarities between users
Relevance between documents and quests is
provided by explicit feedback
Search is enhanced by cross-recommending
or stressing good documents

33. Evaluation of Quest approach
SERF (Jung, 2004)
– Results with recommendations were shown on over
40% searches.
– In about 40% of cases the users clicked and 71.6% of
these clicks were on recommended links! If only
Google results are shown users clicked in only 24.4%
of cases
– The length of the session is significantly shorter (1.6
vs 2.2) when recommendations are shown
– Ratings of the first visited document are higher if it
was recommended (so, appeal and quality both
better)

34. Quest-Based Approach
What is good/important?
Critique?

35. I-SPY: Community-Based Search

36. I-SPY: Mechanism
Community-query-hit matrix
User similarity defined by communities and
queries
Result selection provide implicit feedback

37. I-Spy: Proxy Version

38. I-Spy Approach
What is good/important?
Critique?

39. From iSpy to Heystaks: Folders
http://www.heystaks.com/

40. Site-level Social Search
• Moving from single query to query sequences
• What the user selected at the end
• Moving from page recommendation to site recommendation
White, R., Bilenko, M., and Cucerzan, S. (2007) Studying the use of popular
destinations to enhance web search interaction. In: SIGIR '07, Amsterdam, The
Netherlands, July 23 - 27, 2007, ACM Press, pp. 159-166

41. Site-level search
What Kinds of Social Wisdom?
How Social Wisdom is Used?

42. What is Social Navigation?
- Social Information Access in
Web/hyperspace browsing context
- A set of techniques focusing on:
• collecting, processing, and organizing
traces of users’ past interactions
• applying this “community wisdom” in
order to help future users to navigate
hyperspace

43. You are in Japan and its lunchtime. There are many food
places around, but you do not know how good they are or
what these places are actually offering. All signs are in
Japanese
Social Navigation in Real World
“…without knowing much, we joined the longest existing queue formed for a sushi
restaurant. looking at faces of people (both young and old) filled with
expectations despite the long wait in the cold weather, we were sure that the
food would be worth every minute of waiting time. well, it was”. (A comment on
Flickr image, used in Rosta Farzan’s Thesis)

44. Social Navigation in Real World
What would you do…?
• Walking by the cinema you feel like watching a
movie, but none of the movies seems familiar
• You missed a lecture and want to do your
readings. You have a textbook and 100 assigned
pages to read, but do not know what was most
important in the lecture and what can be skipped
• You are hiking along a trail to a famous waterfall.
You reached an unmarked road split and you
have no map

45. Social Navigation: The Motivation
• Natural tendency of people to follow
each other
Making use of “direct” and “indirect
cues about the activities of others
Following trails
Footsteps in sand or snow
Worn-out carpet
Using dogears and annotations
Giving direction or guidance
• Navigation driven by the actions
from one or more “advice
providers”

46. Navigation Support: Predefined of
Social
Walking down a path in forest
Walking down a road in a city
Reading a sign at the airport to find the
baggage claim
Talking to a person at the airport help desk
to find the baggage claim

47. The Lost Interaction History
What is the difference between walking in a
real world and browsing the Web?
– Footprints
– Worn-out carpet
– People presence
What is the difference between buying and
borrowing a book?
– Notes in the margins
– Highlights & underlines
– Dog-eared pages
– Opens more easily to more used places

48. Edit Wear and Read Wear (1992)
The pioneer idea of
asynchronous indirect
social navigation
Developed for collaborating
writing and editing
Indicated read/edited
places in a large document

49. Footprints (1997)
Wexelblat & Maes, 1997
Allowing users to create
history-rich objects
Providing history-rich
navigation in complex
information space
Showing what
percentage of users
have followed each link

50. Juggler (1998)
Dieberger, 1998
Textual virtual environment (MOO)
History-enriched environment
Showing access-counter for rooms
Recognizing URLs in the output of a communication
tool
Hiding it from user
Popping out the page
Integrating with social navigation
Supporting interaction between teachers and
students

51. Ideas for Social Navigation on WWW
Awareness of presence of other users
– Discussion of an article
– Location attracting large crowds of users
Relevant objects
– Links visited by similar users
– Items appreciated by similar users
Recency
– How long ago the page was created/visited
Attitude
– What other users did/thought about an item

52. Example: CoWeb

53. SN in Information Space:The History
History-enriched environments
– Edit Wear and Read Wear (1992)
– Social navigation systems
• Footprints, Juggler, Kalas
Collaborative filtering
– Manual push and pull
• Tapestry, LN Recommender
– Modern automatic CF recommender systems
Social bookmarking
– Collaborative tagging systems
Social Search

54. Social Navigation in Information Space
Synchronous
Communication in real time
Asynchronous
Using the Interaction of past
users
Direct
Direct communication
between people
Indirect
Relying on user presence
and traces of user behavior
Chats
Recommenders
Q/A Systems
Presence of other people
History-enriched
environments
Direct
Indirect
Synchronous Asynchronous

55. EDUCO: Synchronous, Indirect SN

56. Direct Asynchronous SN
Asynchronous discussion forums
Recommending information to friends and
community
Directly asking questions for getting
information
Sharing bookmarks with others

57. Umtella: Direct Asynchronous SN

59. CourseAgent: Direct, Asynchronous
• Adaptive community-based course planning system
– Provides personalized access to course information
– Provides social recommendation about courses
• Recommendation in the form of in-context adaptive
annotation
– Visual cues
• Expected course workload
• Expected relevance to students’ career goals
– Course Schedule
– Course Catalog

60. CourseAgent: Direct, Asynchronous
• Adaptive community-based course planning system
–Provides social navigation through visual cues
http://halley.exp.sis.pitt.edu/courseagent/

61. Ratings: Raw Social Data

62. 62
Generating Social Navigation
Overall workload
Averaging over all ratings of the community
Overall Relevance
Average does not work
Irrelevant to many but very relevant to one
Goal-centered algorithm
16 rules

63. Trade-offs for Direct Approach
• Reasonably reliable
• Feedback directly provided
• No need to deduce and guess
• Explicit feedback is hard to obtain
• Takes time to provide and requires
commitment
• “One out of a hundred”
• Social system, which extensively relies on
explicit feedback need either large
community of users or special approaches
to motivate direct contributions

64. Direct Asynchronous SN
Asynchronous discussion forums
Recommending information to friends and
community
Directly asking questions for getting
information
Sharing bookmarks with others

65. Motivation for Direct SN
Extrinsic Motivation
Adding some external reasons to contribute
Recognition (badges, status – busy bee)
Social comparison, social gaming
Incentives (more power, functions)
Intrinsic Motivation
Encouraging natural reasons to contribute
Personal values
Engineering the system to turn contribution in
user-beneficial actions

66. Comtella Stars Extrinsic

67. 67
Career Planning: Intrinsic
Motivation:

68. 68
The Intrinsic Motivation Works
•Career Planning was not advertised and was not
noticed and used by half of the students
•Contribution of experimental users who did not use
Career planning (experimental group I) is close to
control group
•Significant increase of all contributions for those who
had and used Career planning (experimental group II)

69. More about CourseAgent
Farzan, R. and Brusilovsky, P. (2006) Social
navigation support in a course recommendation
system. In: V. Wade, H. Ashman and B. Smyth
(eds.) Proceedings of 4th International Conference
on Adaptive Hypermedia and Adaptive Web-Based
Systems (AH'2006), Dublin, Ireland, June 21-23,
2006, Springer Verlag, pp. 91-100.
Farzan, R. and Brusilovsky, P. (2011)
Encouraging User Participation in a Course
Recommender System: An Impact on User
Behavior. Computers in Human Behavior 27 (1),
276-284.

70. Amazon: Asynchronous, Indirect
•Compare with direct SN in
Amazon ratings or reviews: “the
remake of this movie is horrible,
I recommend to watch the
original version instead”
Traces of viewing and purchasing decisions is a valuable collective wisdom!

71. Knowledge Sea II: Asynchronous, Indirect
•Social Navigation to support course readings

72. Knowledge Sea II (+ AnnotatEd)

73. Trade-off for indirect approach
• Feedback is easy to get
• Users provide feedback simply by navigating and doing
other regular actions
• It works quite well
• Most useful pages tend to rise as socially important
• Social navigation cues attract users
• Indirect feedback might not be reliable
• A click or other action in the interface is a small
commitment, may be a result of error
• “Tar pits”
• Main challenge of systems based on indirect
approach: increase the reliability of indirect
feedback
• Better processing of unreliable events (time, scrolling)
• Use more reliable events (cf. browsing vs. purchase)

74. Knowledge See II: Beyond clicks
• Make better use of existing feedback
• Switched from click-based calculation of user
traffic to time based
• Time and patterns can provide more reliable
evidence
• Added annotation-based social navigation
• Annotations are more reliable
• Users are eager to provide annotations and
even categorize them into positive/regular

75. Spatial Annotation Interface
A Spatial Annotation Interface adds social
navigation on the page level
Staking a space
Commenting
75BooksOnline'08

76. Page-level Navigation Support
Visual Cues - annotation background and border
Background Style
•Background filling
Ownership
•Background color
Owner’s attitude
Border style
•Border color
Positiveness
•Border thickness
# of comments
•Border stroke
Public or personal
76BooksOnline'08

77. Annotation-based SN does work
• Usage
• With additional navigation
support map-based and
browsing-based access
emerged as the primary
access way
• Effect on navigation
• Significant increase of link
following (pro-rated
normalized access)
• Impact
• Annotation leads students
to valuable pages

78. Back to Motivation Issue
BooksOnline'08
Annotations are explicit actions used for implicit feedback and as
with all explicit actions, it come with motivation problems.

79. More on KS-II and AnnotatEd
Farzan, R. and Brusilovsky, P. (2005) Social navigation
support through annotation-based group modeling. In: L.
Ardissono, P. Brna and A. Mitrovic (eds.) Proceedings of
10th International User Modeling Conference, Berlin, July
24-29, 2005, Springer Verlag, pp. 463-472
Farzan, R. and Brusilovsky, P. (2008) AnnotatEd: A social
navigation and annotation service for web-based
educational resources. New Review in Hypermedia and
Multimedia 14 (1), 3-32.
Brusilovsky, P. and Kim, J. (2009) Enhancing Electronic
Books with Spatial Annotation and Social Navigation
Support. In: Proceedings of the 5th International
Conference on Universal Digital Library (ICUDL 2009),
Pittsburgh, PA, November 6-8, 2009

80. CoMeT: Asynchronous, Indirect
http://pittcomet.info

81. Fighting for SN reliability in CoMeT
• Broader set of evidences
• View, annotate, tag, schedule talks, send to
friends, connect to peers
• Declare affiliations (similarity!)
• Join and post links to a set of communities
• Combining in-context (visual cues) and
out-of context (ranking) guidance
• Exploring the power of “top N”
• Powerful, but dangerous!
• Handling of Top N in Conference Navigator

82. Known Problems and Challenges
Concept drift
Snowball effects
Bootstrapping

83. Concept Drift
Old history information becomes less
relevant
History decay
different for a very popular and a less popular
information
Shift of Interest

84. Snowball effect
Just one visit before the
current visit can turn the
page into ‘hot’
The page could be useful
or useless
Next users follow the
same path
Snowball gets bigger and
bigger

85. Conference Navigator Project
• Social conference support system – combining
social and personalized guidance
• Fighting snowball effect in top 20 page

86. Bootstrapping
Social navigation works with many users
What if there are very few users?
How to match a new user against already
populated system?
How to encourage users to leave their trails
(commenting, …)?
How to make the new information visible in
already populated system?

87. Social Visualization
• Using social wisdom in visualization-
based access
• Visualization provide “big picture” of the
information space in 2-3D and use
topology and visual cues to direct
attention to right information
• Share many aspects with social
navigation, but focus on visual wholistic
interface

88. Social Visualization with VIBE

89. Social Visualization in CN3
TalkExplorer: Integrating recommendations and SNS visually

90. Social Visualization in E-learning
• Progressor and Progressor+ projects
• Problem: guide students to most
appropriate educational content –
examples, problems, etc.
• Using reliable indicators of student
progress (problem solving success)
• Provide visualization to better support
guidance
• Explore peer-based and community-
based SNS

91. Parallel Introspective Views
91Hsiao, I.-H., Bakalov, F., Brusilovsky, P., and König-Ries, B. (2011) Open Social Student Modeling:
Visualizing Student Models with Parallel Introspective Views. Proceedings of 19th International Conference on
User Modeling, Adaptation, and Personalization, Girona, Spain, July 11-15, 2011, Springer-Verlag, pp. 171-182.

92. Progressor
92Hsiao, I. H., Bakalov, F., Brusilovsky, P., and König-Ries, B. (2013) Progressor: social navigation support
through open social student modeling. New Review of Hypermedia and Multimedia 19 (2), 112-131.

93. Students spent more time in Progressor+
Quiz =: 5 hours
Example : 5 hours 20 mins
93
60.04
150.19
224.7
296.9
69.52
121.23
110.66
321.1
0
50
100
150
200
250
300
350
400
QuizJET JavaGuide Progressor Progressor+
Total time spent (minutes)
Quiz
Example

94. Students achieved higher Success Rate
94
42.63%
58.31%
68.39%
71.20%
0.00%
20.00%
40.00%
60.00%
80.00%
QuizJET JavaGuide Progressor Progressor+
Success Rate
p<.01

95. 95
Non-adaptive adaptive
Social, adaptive, single content Progressor+
How Social Guidance Works

96. Advancing SN: Beyond Click
Clicks are not reliable signs of interest!
What other kinds of user activities can be
tracked?
– Annotation
– Bookmarking
– Sending e-mail
– Solving a problem
– Downloading
– Purchasing
– Rating and liking

97. Advancing SN: One Size Fits All?
Which users’ actions are taken into account
for social navigation?
– All users
– Coherent, like-minded group of users
Group-level social navigation
– KnowledgeSea II, Progressor – a class
– CourseAgent – users with similar goals
– CoFIND
– Facebook – social network
– Amazon - context

98. SIA Challenges across Contexts
• Increasing reliability of indirect sources
• Time spent reading vs. simple click
• Query sequences vs. simple result access
• Adding more reliable evidences of
relevance/quality/interests
• Annotation vs. browsing
• Purchasing/downloading vs. viewing
• May add the problem of motivation!
• Basis for user similarity (not “all for all”)
• Co-rating in recommender systems (sparsity!)
• Users with similar goals (CourseAgent)
• Single class in Knowledge Sea II (still topic drift!)
• Quest or community in AntWorld and iSpy

99. More Challenges:Merging the Technologies
• Different branches of SIA have little connections to
each other
• Social navigation use navigation data to assist navigation
• Social search use search traces to assist future searchers
• Many opportunities to merge two or more SIA
technologies
• Social Web system with broader SIA
• Use several kinds of user traces to support a specific SIA
technology
• Offer several kinds of SIA
• Earlier work: Social Navigation + Social Search
– ASSIST ACM
– ASSIST YouTube
• Social Navigation + Recommendation
• Adding Social Visualization

100. Social Search with Visual Cues
General annotation
Question
Praise
Negative
Positive
Similarity score
Document with high traffic (higher rank)
Document with positive annotation
(higher rank)
Query relevance and social relevance shown separately: rank/annotation

101. Annotation-Based Search: Impact
Acceptance
– Users noticed and applied social visual cues
• Frequency of usage - viewed more documents per query with
social visual cues
– Users agreed with the need for social search
• Survey results
Performance
– Social Visual Cues are taken into account for navigation
• Social Navigation cues are twice as more influential in affecting
user navigation decision than high rank
– Social visual Cues provide higher prediction for page quality
that high rank
More information
– Ahn, J.-w., Farzan, R., and Brusilovsky, P. (2006) Social
search in the context of social navigation. Journal of the
Korean Society for Information Management 23 (2), 147-
165.

102. ASSIST-ACM: Social Search + Nav
Re-ranking result-list
based on search and
browsing history
information
Augmenting the links
based on search and
browsing history
information
Farzan, R., et al. (2007) ASSIST: adaptive social support for information space traversal.
In: Proceedings of 18th conference on Hypertext and hypermedia, HT '07,, pp. 199-208