AmirFARES/JUMIA-Sentiment-Analysis-ML-Olympiad

JUMIA Sentiment Analysis - ML Olympiad 🏆 Top 3 Finisher 🏆 Check the link below for more details about the challenge and how to analyze customer sentiments from their reviews. 🔗(kaggle.com) #MLOlympiad #SentimentAnalysis #MachineLearning # JUMIA Sentiment Analysis - ML Olympiad ## Introduction 🌟 Welcome to my Data Science and Machine Learning portfolio! This repository showcases my participation in the JUMIA Sentiment Analysis Challenge, where I achieved a top 3 finish. In this challenge, I developed a model to determine the sentiment of customer reviews on JUMIA Tunisia. ## About the Challenge 🌐 This competition was a part of the #MLOlympiad, organized by Kaggle and sponsored by Google Developers. The task involved performing sentiment analysis on textual customer reviews to categorize them as positive, negative, or neutral. ### Challenge Details 📝 - **Goal**: Perform sentiment analysis on customer reviews and classify them into 'Positive,' 'Negative,' or 'Neutral.' - **Dataset**: The training and test datasets were provided, containing customer reviews and their associated sentiments. - **Evaluation**: The evaluation metric for this competition was [CategorizationAccuracy]. ## Project Files 📂 Here are the key files related to this project: - **train.csv** - The training dataset containing customer reviews and sentiment labels. - **test.csv** - The test dataset for making predictions. - **sample_submission.csv** - A sample submission file with the required format. - **notebook in Kaggle** or **jumiasentimentanalysis.ipynb** - My Jupyter Notebook with code, analysis, and model implementation. ## My Approach 🚀 1. **Data Exploration**: I began by exploring the training dataset to understand the data's characteristics and distribution. 2. **Feature Engineering**: I performed text preprocessing and feature engineering to prepare the data for modeling. 3. **Model Selection**: I experimented with various machine learning and natural language processing (NLP) models to determine the best-performing one. 4. **Hyperparameter Tuning**: To optimize model performance, I fine-tuned hyperparameters. 5. **Validation**: I utilized cross-validation techniques to assess model accuracy and robustness. …