[bids2015] when-to-post on social media
TRANSCRIPT
![Page 1: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/1.jpg)
When-To-Post On Social NetworksOctober 9, 2015 @ Berkeley Institute for Data Science
*Nemanja Spasojevic, Zhisheng Li, *Adithya Rao, Prantik Bhattacharyya
![Page 2: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/2.jpg)
● Klout is a social influence measurement tool.
● Users register on Klout.com and connect their social network accounts.
● Klout collects authorized/public information from connected networks.
● Klout derives influence scores and topics for users from collected data.
● Klout recommends:○ content to post○ times when to post.
What is Klout ?
![Page 3: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/3.jpg)
What is Klout ?
![Page 4: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/4.jpg)
What is Klout ?
![Page 5: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/5.jpg)
● Maximize audience engagements:○ Reach friends ○ Better targeting by brands ○ Schedule campaign
● Personalized schedules vs. infographics
Motivation
?
...
![Page 6: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/6.jpg)
Challenges● Data sparsity ● Lack of open data sets ● Unique audiences ● Specificity network dynamics
![Page 7: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/7.jpg)
Problem Setting
For a user on a social network, find the best time to post a message in order to maximize the probability of receiving audience reactions.
![Page 8: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/8.jpg)
Problem Setting
For a user on a social network, find the best time to post a message in order to maximize the probability of receiving audience reactions.
● Consider only: replies, retweets, favorites, likes, comments.● Weekly user behaviour cycle ● Observe only first 24hr of reactions● 15 min time bucket● Starting bucket is 00:00-00:15 Monday (relative to user’s timezone)
![Page 9: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/9.jpg)
System Overview
![Page 10: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/10.jpg)
Audience Behaviour
![Page 11: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/11.jpg)
● Inherent delay ● Different networks have different engagement dynamics● 50% of first 24h reactions Twitter in 24 min while Facebook in 1h 42min● Estimate anticipated reactions over time
Post To Reaction Analysis: Network
![Page 12: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/12.jpg)
● Reaction speed may depend on topic of the content
Post To Reaction Analysis: Topic
![Page 13: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/13.jpg)
● Depending on Actors in-degree they may react to posts faster or slower
Post To Reaction Analysis: Actor In-Degree
![Page 14: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/14.jpg)
Audience Behaviour - Network
![Page 15: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/15.jpg)
Audience Behaviour - Location
![Page 16: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/16.jpg)
Audience Behaviour - Location
![Page 17: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/17.jpg)
Audience Behaviour - Location
Same City Audience Behaviour Correlation and Similarity
![Page 18: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/18.jpg)
Audience Behaviour - Topics
![Page 19: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/19.jpg)
Personalized Schedules
![Page 20: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/20.jpg)
![Page 21: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/21.jpg)
Personalized SchedulesAuthor Audience
● When do the users ai create posts?
● When does a specific audience member b
0 react to the posts
created by ai?
● What is the probability that b0
reacts to post in a certain time bucket t
k?
1st Degree Schedule 2nd Degree Schedule
![Page 22: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/22.jpg)
Personalized Schedules
![Page 23: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/23.jpg)
First-Degree Reaction Schedule
![Page 24: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/24.jpg)
First-Degree Reaction Schedule
● When do the users ai create posts?
● When does a specific audience member b0
react to the posts created by ai?
![Page 25: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/25.jpg)
Second-Degree Reaction Schedule
![Page 26: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/26.jpg)
Second-Degree Reaction Schedule
● When do the users ai create posts?
● When does a specific audience member b0
react to the posts created by ai?
● What is the probability that b0
reacts to a post in a certain time bucket tk?
![Page 27: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/27.jpg)
Weighted Schedules
● Unweighted:○ All audience members treated the
same
● Weighted○ Audience members weighted by past
engagement.○ A close friend may respond to your
posts more often than an acquaintance.
![Page 28: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/28.jpg)
Personalized Schedules - Twitter Example
![Page 29: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/29.jpg)
Personalized Schedules - EvaluationEvaluate on:● 56 days of unseen data● 0.5M active users
Baselines for a timezone :● Most Frequently Used (MFU)● Aggregate First-Degree (AFD)
Reaction gain of:● 17% on Facebook ● 4% on Twitter
![Page 30: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/30.jpg)
Open Dataset
https://github.com/klout/opendatahttps://github.com/klout/opendata
● Anonymized Post-Reaction Timestamps ● 144+ million posts
○ Twitter 119M ○ Facebook 25M
● 1.1+ billion reactions○ Twitter 104M ○ Facebook 1B
● Anonymized user ID fingerprints map across networks
● Slightly perturbed timestamps
![Page 31: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/31.jpg)
Future Work
https://github.com/klout/opendata● Personalized Post To Reaction Filter Functions ● More Sophisticated 2nd degree Model ● Topical Awareness ● Content Analysis (text, photo, video)● More Networks and Signals
![Page 32: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/32.jpg)
Conclusion
https://github.com/klout/opendata● Reaction times are more than 4x faster on Twitter compared to other networks.● Audience behavior varies across different networks.● Users audiences across different cities exhibit different behavior patterns.● Using personalized schedules users can see reaction gain of up to :
○ 17% on Facebook ○ 4% on Twitter
● We hope open dataset can benefit future research on when-to-post problem.
KDD2015 http://arxiv.org/pdf/1506.02089v1
![Page 33: [BIDS2015] When-To-Post on Social Media](https://reader031.vdocuments.site/reader031/viewer/2022030302/587d15911a28abae148b68af/html5/thumbnails/33.jpg)
Q & A