Zindi
CompeteJobsLearnChatLeaderboard
For BusinessPartnersMeet the teamPressCase studiesAI4EAC
Primary competition visual

AI4D iCompass Social Media Sentiment Analysis for Tunisian Arabizi

Helping Tunisia
$2 000 USD
Challenge completed over 4 years ago
Natural Language Processing
Classification
Sentiment Analysis
895 joined
309 active
InfoDataChatLeaderboard
Starti
Nov 20, 20
Closei
Mar 28, 21
Reveali
Mar 28, 21
User avatar
AMR-KELEG
Filtering stopwords using transliteration (Your feedback is needed)
Notebooks · 26 Feb 2021, 14:36 · edited 2 minutes later · 1

I am building a rule based transliteration method for Arabizi-Arabic:

https://github.com/AMR-KELEG/Franco-Arabic-Transliterator

and the notebook here:

https://gist.github.com/AMR-KELEG/3b63d5966087aee8b37cbf39c4c1830e

uses the method to filter away stopwords. I haven't tested the stopwords removal's effect on the classification model but I would appreciate if you can let me know if this notebook is useful or not.

All the best,

Amr

Discussion 1 answer
User avatar
MICADEE
LAHASCOM

okay. Great idea.

1 Mar 2021, 15:12 (edited less than a minute later)
Upvotes 0

Join the largest network for
data scientists and AI builders

AboutFAQs
Privacy PolicyTerms of UseRules
Status
© Zindi 2025