Zambian Language Trainer Window
Curate local language datasets and trigger asynchronous machine learning training
Multilingual
Select Target Zambian Dialect to Manage & Train:
🇿🇲
Unified (All)
🇿🇲
Chibemba
🇿🇲
Chinyanja
🇿🇲
Chitonga
🇿🇲
Silozi
🇬🇧
English
🌐
Mixed/General
Local Dataset Inspector: All
25504 Records| Phrase Text | Dialect | Category Label | Source |
|---|---|---|---|
| RT @taylorrDiane: When a sideline hoe gets mad, BITCH SHUT UP! You was okay with being second ALL this time, now all of sudden it's a probl… | Mixed | Abusive | User Added |
| RT @taylormrake: People beg to see women's bodies but the minute they're seen that woman is now a hoe oh okay | Mixed | Abusive | User Added |
| RT @taylorlopez96: “@harleighpurolla: You are the biggest two faced bitch I have ever met.” You won't @ her | Mixed | Abusive | User Added |
| RT @taylorcaniff: I'm having a date at Yankee Field then getting kiss cam.. #bucketlist | Mixed | Safe | User Added |
| RT @taylorcaniff: I wear beanies all winter long! So no bandanas till summer😍 | Mixed | Safe | User Added |
| RT @taylor_TM: @PacmanJonez @PhilWOTG you the whitest person on my TL but you always so ghetto. Im sick of it | Mixed | Hate Speech | User Added |
| RT @tanishalixpussy: no need to compete with other women there's only one of me, and shit... im that bitch | Mixed | Abusive | User Added |
| RT @tanaka_callen: @t_ndyy awwww my niggar thank you so much sure means a lot ♡♡ | Mixed | Abusive | User Added |
| RT @tanajiamonay_: i hate hype ass bitches, like ... it's too early for you to be all loud; sit tf down somewhere. | Mixed | Abusive | User Added |
| RT @takeyaah: when his hoes thought it was over: http://t.co/jhaOcX1MTd | Mixed | Abusive | User Added |
| RT @tailorlamar: yall niggas is hoes. | Mixed | Abusive | User Added |
| RT @taexchanae: momma dee ain't loyal. you ain't pose to tell his main bitch bout his side bitches 😂 | Mixed | Abusive | User Added |
Add Local Phrase
Batch Import CSV
CSV OnlyUpload a custom CSV file to bulk import training data across all languages. Required columns: phrase (or text), category (0=Hate, 1=Abusive, 2=Safe), and optionally language.
Model Training Control
20%
Evaluation Results
Trained Algorithm:
Decision Tree
ACCURACY
F1 SCORE
Confusion Matrix Grid
46
0
0
2
41
4
0
0
47
Columns: Predicted
Rows: Actual
Algorithm Accuracy Graph