Project: Social Media Analytics
Topic: Web Crawling and Scraping (Users & Keywords) using Python
Keywords: Twitter API, Web Crawling and Scraping, Data Analysis, NLP, Sentiment Analysis, Machine Learning, Classification, Python
- Use social media analytics to extract tweets from a user or by keywords and perform sentiment and text analysis to discover online text patterns shared between users on Twitter.
- Use the ipynb code to scrape the desired data into a dataset.
- Python is used to assist this project with Data Mining by extracting important insights using:
- Nowadays Twitter is used to disseminate general or scientific findings to the public.
- So it is important to understand tweet authors’ citation motivations and attitudes (or sentiments) towards the most discussed content or trends.
- Furthermore, Twitter allows businesses to engage personally with consumers.
- However, there’s so much data on Twitter that it can be hard for brands to prioritize which tweets or mentions to respond to first.
- Aim:
- To understand how the content users share on Twitter by analyzing which Tweets organically get the most impressions, engagement, and trends by users or via keywords.
- Objective:
- To determine the contents and trends shared by users.
- To analyze the sentiments and impressions shared between users or via topic/keywords.
- To create a Machine Learning model that classifies the tweets between users or topic/keywords based on the text sentiments, models evaluation, and assessment (i.e. Accuracy, Recall, AUC, etc.).
- The insights gained by analyzing the tweets data will aid in understanding the content, engagement, and trends between users.
(1) Twitter-API-ScrapeFromUser Folder
- Contains the Twitter API (scrape from users) Python implementation codes (along with explanations) for the project.
(2) Twitter-API-ScrapeUsingKeywords Folder
- Contains the Twitter API (scrape using keywords) Python implementation codes (along with explanations) for the project.
- None (for now)
- Took inspiration from Kaggle