AI sentiment Analysis

About

Objective:

The primary goal of this project was to utilize web scraping techniques to extract valuable data and generate unique datasets.

Web Scraping with Python:

Using the Selenium library in Python, I successfully built a web scraper.

Over the course of one month, I scripted Twitter data related to Artificial Intelligence (AI).
This process involved extracting information from multiple sources.

Data Compilation:

To consolidate the extracted data, I employed the Pandas library in Python.
By appending all the separate CSV files into a single file, I ensured a comprehensive and organized dataset for further analysis.

Data Cleaning:

Once the data collection phase was completed, I utilized Python once again, this time leveraging the power of the Pandas library along with regular expressions to clean the dataset.

This crucial step ensured that the data was consistent and free from any inconsistencies or errors.

Sentiment Analysis:

To gain deeper insights into the data, I employed the Natural Language Toolkit (NLTK) to extract sentiment scores for each tweet.

By analyzing the sentiment, I was able to gauge the overall sentiment polarity associated with the AI-related tweets.
Additionally, I created a unique ID column to link the sentiment scores back to the respective tweet texts.

Data Visualization with Power BI:

After preparing the data and extracting sentiment scores, I utilized Power BI to create compelling visualizations.
These visual representations provided valuable insights into the sentiment patterns and trends observed within the AI-related tweets.

Click Here for the dataset and python scripts