Project ID: 17
This project is on sentiment analysis using Natural Language Processing in which people's sentiments are recognised. It determines positive or negative according to the sentiment sentence given.
In this project, we worked on applying Sentiment Analysis on Various Datasets for analyzing Domestic Violence going on at households during lockdown .
It refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. It can be widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine.
Done the web scrapping using beautiful soup which is a Python library for pulling data out of HTML and XML files.
This part includes quite a few steps :-
A. Contractions to Expansions
B. Tokenisation - Seperating a text into smaller units
C. Removing Stopwords
D. Lemmetisation - Process of grouping together the different inflected forms of a word so they can be analysed as a single item
Model building is done using the naive baeyes algorithm with training on around 20k datapoints and an accuracy of more than 85%.
The file has been run on the command prompt using streamlit - run filename.py . Streamlit is a effective way to create an Web App on Local Host.
Any web technology can be used but I am thinking about using Python ecosystem.
- Python
- Machine Learning
- Natural Language Processing
=> Fork 
=> Open your Git Bash command window and in the root directory type the following commands :
1) git init -initializes the git repository from the GitHub.
2) git clone -Clone the repository to your local machine
(git clone https://github.com/<your-github-username>/LetsUpgrade/REAL-TIME-SENTIMENT-ANALYSIS.git)