Basic Needs Basic Rights Kenya - Tech4MentalHealth
Classify text from university students in Kenya towards a mental health chatbot
$4 200 USD
Ended over 2 years ago
499 active · 1066 enrolled
End of The game
Connect · 6 Jul 2020, 02:04 · 18

i am happy to be in the TOP 3

Congratulations to the winners but what a shake up guys !!!

Discussion 18 answers

Congratulations to you. Can you please share with us, your approach ?

6 Jul 2020, 02:06
Upvotes 0

Congratulations to you and your team. what was your approach. I can’t wait to find out 😊

6 Jul 2020, 02:06
Upvotes 0

Congratulations to you and your team.

6 Jul 2020, 02:08
Upvotes 0


6 Jul 2020, 04:28
Upvotes 0


6 Jul 2020, 04:32
Upvotes 0


6 Jul 2020, 05:03
Upvotes 0

Many congratulations to all of the top finishers.

No doubt, the shake-up was expected because we were having very less dataset and there are several data points that can go into more than one category.

For example: "I am addicted" so this can be Alcohol addiction as well as Drug addiction.

Looking forward to learn from the winners :)

6 Jul 2020, 06:07
Upvotes 0

Shobhit aka asinglenueron. What was ur approach. you did very well on private LB.

First of all I want to know which of my submission did well.

I tried so many weird approaches :D

Do you know, how to check the submission score on a private dataset?

You can still submit now and get the score. LB will not get updated.

I got it. Now the submission scores got changed and they are reflecting the private leaderboard scores.

So the model did best on a private dataset is:-

single model roberta-base

Converting text to lowercase : False

OOF with 20 splits

CV Score: 0.3294175537361298

Public leaderboard SCORE: 0.33584687745369

Private leaderboard SCORE: 0.311455622610637

What preprocessing did you do on your dataset.. How did you clean your dataset ?

There was no text cleaning in this version.

I did the same thing but only for 400 rows, as i have a weird habit of always taking a holdout,and 10 splits

I tried both 10 and 20, but 20 CV score was in sync with the public leaderboard score. That's why I picked 20 splits for this competition.

@asingleneuron can you share your notebook on your solution I used

Congratulations guys

6 Jul 2020, 10:41
Upvotes 0