Follow My Friends This Friday! An Analysis of Human-generated Friendship Recommendations
1 like470 views
The study analyzes the impact of human-generated friendship recommendations, particularly focusing on the 'Follow Friday' (#FF) trend on social networks. It highlights the advantages of trust and acceptance in such recommendations, but also notes the challenges of visibility and spam. Key findings indicate that recommendation features and user relations play a significant role in acceptance rates, suggesting the need for further exploration into the longevity and effectiveness of social recommendations.
Follow My Friends This Friday! An Analysis of Human-generated Friendship Recommendations
- 1. FOLLOW MY FRIENDS THIS FRIDAY! An Analysis of Human-Generated Friendship Recommendations Ruth García Gavilanes Universitat Pompeu Fabra Neil O´Hare, Yahoo! Research Luca Maria Aiello, Yahoo! Research Alejandro Jaimes, Yahoo! Research
- 2. Twitter: Users tweet recommendations
- 3. Advantages Recommendations from friends • Trust • More acceptances( Amin et al., Recsys’12) • Features unknown for machines
- 4. Disadvantages • Noise • Commercial purpose and Spam • Not all recommendations are delivered to or seen by target users
- 5. Humans Who-to-Follow Recommendations We propose a way to measure the effect of recommendations from humans only
- 6. In 2010 • The most popular hashtag in 2010 was #followfriday or #ff in several countries • Recommending people became trendy • No personalized recommendations of who to follow
- 7. What is Follow Friday? TARGET USER SOCIAL NETWORK RECOMMENDS PEOPLE TO FOLLOW ON FRIDAYS. follows Tie Strength to follow or not to follow?
- 8. Objective • Analyze the dynamics of Follow Friday : impact, effect in time, repetitions and longevity. • Identify important features in each recommendation by using a classifier
- 9. Method 24 weeks 48 snapshots RECEIVER RECOMMENDER Follows ACCEPTED RECOMMENDATION RECOMMENDED USERS Who is new? Follows ? #followfriday THURSDAY FRIDAY SATURDAY SUNDAY MONDAY 93% of follow friday Tweets snapshot snapshot
- 10. Acceptance Total Initial set of users 55,000 Receivers 0.60% instance acceptance 21,270 Recommenders 589,844 Recommended Users 3,261,133 Recommendation Instances 59,055,205 Accepted Recommendation Instances 354,687 Most Follow Friday Recommendations are not taken into account right away
- 11. Interactions Mentions Acceptance Rate Recommender -> Recommendation 0.006 Recommendation <-> Recommender 0.009 Receiver -> Recommender 0.010 Recommender -> Receiver 0.011 Recommender <-> Recommendation 0.012 Receiver -> Recommendation 0.095 Recommendation -> Receiver 0.097 Receiver <-> Recommendation 0.145 Most Follow Friday Recommendations are not taken into account right away
- 12. IMPACT
- 13. Impact • We need to compare Follow Friday recommendations to other models: • Implicit : Mentions that were not Follow Friday recommendations • Unobserved : Follow Friday recommendations of the future only #FF
- 15. Acceptance after n weeks
- 18. Features USER-BASED (per user) RELATION-BASED (per pair) • • Attention • Followers vs Followees • Mentions by other users • Recommendations • Activity • Average tweets per • day • New followees • Accepted recommendations and recommenders • Mentions Tie Strength – Mentionss – Folllow Friday recommendations – Previous acceptances – Friendship longevity Similarity – Words, mentions, hashtags and urls – Geolocation RECOMMENDATION-BASED (per recommendation) • Repetitions • Format – Repeated recommendations – Different recommenders – Day of the week – Re-tweet or not – Same tweet recommendations – Urls
- 19. Methodology • Three methods: Rotation Forest, Linear combination and random • Training : week 1 to 16 • Test : week 17 to 23 • Up to 2 weeks to calculate acceptance rate • Recommendations accepted after two weeks were not considered in the classifier. • Balanced set for training • Goal : accepted recommendations towards the top of the ranking • Evaluation with Mean Average Precision
- 20. Results Ranking MAP Features MAP Rotation Forest 0.496 All 0.496 Linear Combination 0.057 User-based 0.074 Relation-based 0.398 Random 0.037 Recommendationbased 0.062 User + Relation 0.518 User + Format 0.079 Relation + Format 0.379
- 21. Lessons Learned • Recommendations derived from Social Networks have an impact on users decisions • Social accepted recommendations seems to last longer/ more relevant • Many broadcasted recommendations are not seen • Not accepted recommendations can be followed in the future • Relation and user based features are better predictors of tie formation
- 22. Future Work • Can we rate recommendations according to permanence/tenure? • When should we consider an accepted recommendation? (never vs. some day) • User study: Can we build an online recommender of social recommendations (and so promote recommendations not seen)? • Add cultural differences in features, is there an improvement?