Projects

TWITTER TOPIC MODELLING

I scraped text data off Twitter using Tweepy to discover the hidden topics and relationships between each tweet with the use of Topic Modelling; an unsupervised algorithm. Once a topic a discovered, a suggested link is given to read more about it. Project link

SUPER BOWL ADS ANALYSIS

Loaded data was preprocessed by removing null & duplicates values , column renaming and data type conversion for the purpose of feature engineering and data analysis for the recommendation of companies with the lowest cost of investment. Project link

AMAZON TEXT CLASSIFICATION APP

Scraped data of Amazon reviews which was stored in a database and loaded using Python for purpose of classifying text reviews into different sentiments; positive, negative and neutral using SOTA machine learning algorithms. The best performing models was used for the app to be taken live into production using Streamlit.

Model-source-code App-source-code App-web-link

How-to-train-CNN-for-multi-label-text-classification.png