Clustering users by slack reactions

Slack is a very useful tool to communicate with any people.
Especially "slack reaction" is one of the most useful function in Slack.

In order to improve communication with "slack reactions", I tried to cluster users by how they use "slack reactions" to react to a message.

Transcript

1. TryEnglishLT (2019/6/27) K-means clustering of users using Slack reactions @zawawahoge beBit
2. •@zawawahoge •beBit (joined in this April) •Software engineer • Infra engineer • Data analysis Love for Python!
4. Do you use slack?
5. Many emojis are available!
6. Custom emoji can be added!
7. Emoji is actually text! :sushi:
8. What is “Slack reaction”? Slack reactions make communication easier!
9. Motivation: Who uses emojis as like you use?
10. Slack API Is Useful When you want to... • Get a List of • emojis • reactions • posted messages • profiles of all members • Post messages • Upload files From Slack Web API
11. Slack API which I use TODAY Ø /api/users.list Ø To list team members Ø /api/reactions.list Ø To list reactions for a member Ø /api/emoji.list Ø To list all emojis
12. All reactions of all users are obtained • 90,000 reactions • 150 users • 2,000 types of emojis
14. K-means clustering 1. Data shaping Remove top3 emojis (all users use them) 2. Determine the number of clusters 4 clusters to get simple results Then... K-means clustering!
15. Results Use default emojis Use custom emojis Use emoji to praise 酒(sake) (60) (38) (11) (46)
16. Good English skill will Change your life