Climate Change Sentiment Classification(NLP)
Climate Change Sentiment Classification(NLP)
Embedded Files
Classifying twitter data based on climate change sentiments.
Description
Description
Many companies these days are built around reducing one’s environmental impact or carbon footprint. They offer products and services that are environmentally friendly and sustainable, in line with their values and ideals.
They would like to determine how people perceive climate change and whether or not they believe it is a real threat. This would add to their market research efforts in gauging how their product/service may be received.
This project is about creating Machine Learning models that are able to classify whether or not a person believes in climate change, based on their novel tweet data.
Providing an accurate and robust solution from this project can give companies access to a broad base of consumer sentiment, spanning multiple demographic and geographic categories - thus increasing their insights and informing future marketing strategies.
Methodology
Methodology
Twitter Data was gathered, analyzed, cleaned and engineered to ensure that there were no irregularities in the data that'll affect the Models. Imbalanced data was also addressed using Upsampling and Downsampling techniques.
Machine Learning Models(eg: "Naive Bayes", "Support Vector Machine" e.tc) were built using Python classify the tweets into Pro, Anti, News and Neutral.
Streamlit was used to integrate the classification models into an interactive web application where one can input tweets and texts and get results on the sentiment status of the tweet or text.
Amazon Web Services(AWS) was used to deploy the app on the internet to ensure web availability.
Key Output
Key Output
Climate Man®
A user-friendly interactive web application where users can input a body of texts and get results on the climate change sentiment status of the texts.
GitHub Repository
A Repository containing all the important components of the project, including a Jupyter Notebook that highlights the details of the project.
Presentation
A Presentation slide was put together to pitch the solutions from the project to a technical and non-technical crowd.
Page updated
Google Sites
Report abuse