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 @kristajayMFC: No mom. Im not "dramatic /immature" i just have fucking mental problems and youre a bitch and a cunt. | Mixed | Hate Speech | User Added |
| RT @krisinizu: I'm telling you, shaved pussy is ugly. | Mixed | Abusive | User Added |
| RT @kreptplaydirty: Jammer just said to me he thought "mustard on the beat ho" was saying "Abdullah on the beat" this whole time LOOOOOOOL | Mixed | Abusive | User Added |
| RT @kpips_forever: Nobody want no pussy 25 other niggas done had before | Mixed | Abusive | User Added |
| RT @kostaskarelis: Cincy fans talk trash about the city of #CLE and then root for the @Cavs like they belong. #stillCLE #CLEallday #GoBrowns | Mixed | Safe | User Added |
| RT @korsczurek: Got to hold a koala, take selfies with kangaroos, saw a bunch of bad ass birds of prey, and pet a fucking emu today... wtf … | Mixed | Abusive | User Added |
| RT @koreyona_unique: i hate messy females that live for mess... like go sit down somewhere . go get classy hoe 😘😴💁 | Mixed | Abusive | User Added |
| RT @kooleyCobain: You can't find what you lookin for cuz you too busy likin 2 or 3 bitches at a time and all the same. | Mixed | Abusive | User Added |
| RT @koolestbreeze: Thanks Charlie!! http://t.co/iw06cCEkND | Mixed | Safe | User Added |
| RT @koniikonn: “@_Weezy_Wee: If you ask me, every bitch gay” not me I'm all sexual | Mixed | Abusive | User Added |
| RT @koleworld4: every time i come out im never with newwww bitches | Mixed | Abusive | User Added |
| RT @koleworld4: but i don't fck with broke 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