Social Media Recommendation based on People and Tags

1
Social Media Recommendation based on People and
Tags

• Ido Guy, Naama Zwerdling, Inbal Ronen,
• David Carmel, Erel Uziel
• SIGIR10

Firat Onur Alsaran
2
Outline

• Introduction
• Recommender system
• Recommender Widget
• Social Media Platform
• Relationship Aggregation
• User Profile
• Recommendation Algorithm
• Experiments
• Conclusion

3
Introduction
4
Introduction

• Users are flooded with content
• How to judge the validity of so much content?
• As social media grows larger everyday, these web
  sites are increasingly challenged to attract new
  users and retain existing ones.
• Contribution Study personalized recommendation
  of social media items

5
Recommender system

• Recommender Widget

6
Recommender System

• Lotus Connections
• A social software application suite
• profiles, activities, bookmarks, blogs,
  communities, files, and wikis.
• Recommendation platform for the system

7
Recommender system

• Relationship Aggregation
• SaND
• Models relationships through data collected
  across all LC applications.
• Aggregates any kind of relationships between
  people, items, and tags.
• For each user, weighted lists of PEOPLE, ITEMS
  and TAGS are extracted

8
Recommender system

• Relationship Aggregation
• SaND
• builds an entity-entity relationship matrix
• direct relations
• indirect relations

9
Recommender system

• User Profile
• P(u) an input to the recommender engine once the
  user u logs into the system.
• N(u) 30 related people
• T(u) 30 related tags

10
Recommender system

• User Profile
• Person-person relations
• Aggregate direct and indirect people-people
  relations into a single person-person
  relationship.
• Each direct relation adds a sore of 1.
• Each indirect relation adds a score in the range
  of (0,1.

11
Recommender system

• User Profile
• User-tag relations
• used tags
• direct relation based on tags the user has used
• incoming tags
• direct relation based on tags applied on the user
• indirect tags
• indirect relation based on tags applied on items
  related on the user

12
Recommender system

• Tag Profile Survey participants are asked to
  evaluate tags as indicators of topic of interest
• Combination of used and incoming tags is the best
  indicator to generate T(U) from SaND system

13
Recommender system

• Recommendation Algorithm
• d(i) number of days since the creation date of i
• w(u,v) and w(u,t) relationship strengths of u to
  user v and tag t
• w(v,i) and w(t,i) relationship strengths between
  v and t, respectively, to item i

14
Recommender system

• Recommendation Algorithm
• User-item relation authorship (0.6), membership
  (0.4), commenting (0.3), and tagging (0.3)
• Tag-item relation number of users who applied
  the tag on the item, normalized by the overall
  popularity of the tag.

15
Evaluation

• 5 recommenders
• PBR ß1
• TBR ß0
• or-PTBR ß0.5
• and-PTBR ß0.5
• POPBR popular item recommendation.
• Each participant is assigned to one recommender

16
Evaluation

• Recommended Items Survey

17
Evaluation

• Recommended Items Survey

18
Conclusion

• The combination of directly used tags and
  incoming tags produces an effective tag-based
  user profile.
• Using tags for social media recommendation can be
  highly beneficial.
• Combining tag and person based recommendations
  perform better.
• Future Work
• Large scale evaluation
• Computationally intensive algorithm may be used.