Widnew B.

Key Skills

Software

Other

Top Subject Matter

Low-resource language NLP

content moderation/hate speech detection for transliterated Amharic

Top Data Types

Text

Top Task Types

Classification

Freelancer Overview

AI project: Hate Speech Detection in Transliterated Amharic Text (content moderation / text classification). Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Master of Science, Bahir Dar University (2025). AI-training focus includes data types such as Text and labeling workflows including Classification.

Labeling Experience

AI project: Hate Speech Detection in Transliterated Amharic Text (content moderation / text classification)

OtherTextClassification

Built and trained a machine learning text classification pipeline for hate speech detection in transliterated Amharic (Amharic in Latin script). Gathered, normalized, and preprocessed raw social media datasets to address high linguistic variation and lack of standardized spelling. Evaluated the trained model using precision, recall, and F1-scores to measure classification performance. • Data preprocessing and normalization for noisy transliterated text • Supervised text classification pipeline construction from scratch • Performance evaluation using precision/recall/F1 metrics • Content moderation and online safety use case for low-resource language data

2023 - Present

Education

Work History