Teesa R.

Key Skills

Software

Other

Top Subject Matter

E-commerce product review sentiment analysis (NLP)

Business analytics dataset preparation for reporting

Top Data Types

Text

Image

Audio

Top Task Types

Classification

Data Collection

Segmentation

Object Detection

Text Generation

Question Answering

Text Summarization

Transcription

Evaluation/Rating

Freelancer Overview

Amazon Product Review Sentiment Analysis — NLP-based sentiment classification. Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Technology, Drs. Kiran and Pallavi Patel Global University (2025). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Classification and Data Collection.

Labeling Experience

Data Analyst Intern — Webmyne Systems Pvt. Ltd.

OtherData Collection

Cleaned, preprocessed, and transformed raw datasets to improve data consistency for reporting consumers. Applied Python and SQL workflows to prepare structured data used in downstream analytics and dashboarding. Ensured dataset quality improvements that supported more accurate stakeholder reporting. • Reduced dataset inconsistencies by ~30% through preprocessing and transformation. • Prepared cleaned datasets for analytics and Power BI reporting. • Used Python and SQL to validate and standardize raw inputs. • Supported 5+ stakeholders with improved downstream reporting accuracy.

2025 - 2025

Amazon Product Review Sentiment Analysis — NLP-based sentiment classification

OtherTextClassification

Performed sentiment labeling/modeling for Amazon product reviews by classifying texts into positive, negative, or neutral categories. Applied text preprocessing such as tokenization, stopword removal, and TF-IDF feature extraction. Trained and evaluated an ML sentiment classification model to support reliable categorization on unseen data. • Labeled target sentiment classes (positive/negative/neutral) for supervised modeling. • Implemented TF-IDF and other preprocessing steps to convert text into model-ready features. • Trained an ML model and validated accuracy on test data. • Derived outputs suitable for downstream analytics of review sentiment.

2024 - 2024

Education

Work History