Zambian Language Trainer Window
Curate local language datasets and trigger asynchronous machine learning training
Multilingual
Select Target Zambian Dialect to Manage & Train:
πΏπ²
Unified (All)
πΏπ²
Chibemba
πΏπ²
Chinyanja
πΏπ²
Chitonga
πΏπ²
Silozi
π¬π§
English
π
Mixed/General
Local Dataset Inspector: All
25504 Records| Phrase Text | Dialect | Category Label | Source |
|---|---|---|---|
| http://t.co/bPU86qzYFt Arial Rose – Athletic Asian babe plays with her pussy after exercising http://t.co/n3DnrsI352 | Mixed | Abusive | User Added |
| http://t.co/ARKGfY02pT”girl cheeks gone be cold than a bitch | Mixed | Abusive | User Added |
| http://t.co/AFR2NSpcpI. If those asshats at CAIR called ME an islamophobe I would say "guilty fuck you... Pass the bacon bitch"😆 #tcot | Mixed | Abusive | User Added |
| http://t.co/74uLxaf <--this bitch @vewxyz | Mixed | Abusive | User Added |
| http://t.co/4YyVxESnUR The far left looks the best if you ask me, bitches try too hard. Just be yourself, especially if you're thick | Mixed | Abusive | User Added |
| how you settin' trends when you're rappin about wearing the same shit everyone else is wearin and rappin about? This mixtape is trash yo | Mixed | Abusive | User Added |
| how you insecure but a hoe? TF | Mixed | Abusive | User Added |
| how the fuck do all these fucking faggot ass randos even find zoe's ask account???? | Mixed | Hate Speech | User Added |
| how much you wanna bet that a anti-government "black helicopter" teabagger was behind the Boston Marathon explosions? @TwitchyTeam #p2 #tcot | Mixed | Safe | User Added |
| how many of U hoes bad ass little kids dont their medication and cut up in school every week? | Mixed | Abusive | User Added |
| how many fingers does a bitch gotta break so mother fuckers will stop taking my god damn lighters | Mixed | Abusive | User Added |
| how ah yardie reach wyoming?? (live at http://t.co/8N9mI46CBU) | Mixed | Safe | 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