Content, Connections, and Context

This presentation was a keynote at the Workshop on Recommender Systems and the Social Web, held as part of the 6th ACM International Conference on Recommender Systems (RecSys 2012).

Transcript

1. Recruiting Solutions Recruiting Solutions Recruiting Solutions Content, Connections, and Context Daniel Tunkelang Principal Data Scientist at LinkedIn Daniel 1
2. Recommendation Products at LinkedIn 2 Similar Profiles Events You May Be Interested In News Network updates Connections
3. More than 50% 3 Recommendations drive: > 50% of connections > 50% of job applications > 50% of group joins
4. Inputs for Recommender Systems 4 Content Social Graph … Behavior Page Views Actions Queries
5. Take-Aways 5 Content is king. Connections provide social dimension. Context determines where and when a recommendation is appropriate.
6. What is the goal of recommendations? O  Growth O  Engagement O  Revenue 6
7. What is the goal of recommendations? O  Growth O  Engagement O  Revenue 7
8. Provide relevant content and establish social connections in appropriate context. 8 Users First!
9. Content is King 9
10. Goal-Seeking is about Content 10
11. Content (Ir)relevance §  No right answer, but many wrong answers. 11 %no [Voorhees, 2004] WTF! @k http://bit.ly/wtfatk http://bit.ly/percentno
12. Example: Related Searches 12
13. Collaborative Filtering as Content Signal §  Use temporal locality within sessions. §  Find queries with clicks on similar results. §  Look for query overlap. §  Learn more at CIKM! [Reda et al, 2012] 13
14. Example: Jobs You Might Be Interested In 14
15. Content Signals Dominate Social Signals 15 Corpus Stats Job User Base Filtered title geo company industry description functional area … Candidate General expertise specialties education headline geo experience Current Position title summary tenure length industry functional area … Similarity (candidate expertise, job description) 0.56 Similarity (candidate specialties, job description) 0.2 Transition probability (candidate industry, job industry) 0.43 Title Similarity 0.8 Similarity (headline, title) 0.7 . . . derived Matching Binary Exact matches: geo, industry, … Soft transition probabilities, similarity, … Text Transition probabilities Connectivity yrs of experience to reach title education needed for this title …
16. Provide relevant content and establish social connections in appropriate context. 16 Summary
17. Connections 17
18. Connections are Social Dimensions 18
19. Example: People You May Know 19
20. Relationships are Social 20
21. Shared Connections as a Signal 21
22. The Power of Social Proof 22
23. Beyond Triadic Closure §  Triads suggest and affect relationships. [Simmel, 1908], [Granovetter, 1973] §  Triangle closing is a Big Data problem. [Shah, 2011] §  Use machine learning to rank candidates. 23
24. Provide relevant content and establish social connections in appropriate context. 24 Summary
25. Context 25 "to every thing there is a season” [Ecclesiastes 3:1]
26. One Platform, Many Users, Many Needs 26 http://blog.lab42.com/the-linkedin-profile
27. No Weekend Meetings! 27 navigational queries exploratory queries Weekdays Weekends
28. Different Devices for Different Needs 28
29. Time and Place for a Career Change 29
30. Active vs. Passive Job Seekers 30 >10x more likely to reply if active [Rodriguez et al, 2012]
31. Provide relevant content and establish social connections in appropriate context. 31 Summary
32. Recap 32 Content is king. Connections provide social dimension. Context determines where and when a recommendation is appropriate.
33. 2 4 8 17 32 55 90 2004 2005 2006 2007 2008 2009 2010 2011 LinkedIn Members (Millions) 175M+ 25th Most visit website worldwide (Comscore 6-12) Company pages >2M 62% non U.S. 2/sec 85% Fortune 500 Companies use LinkedIn to hire Thank You! 33 We’re Hiring! Learn more at http://data.linkedin.com/