LDA Topic Modelling and Sentiment Analysis on #AppleSupport tweets.

This project delves into the analysis of #AppleSupport tweets through two powerful natural language processing techniques: Latent Dirichlet Allocation (LDA) for topic modeling and Sentiment Analysis. By applying LDA, the aim is to identify underlying topics within the tweets, revealing the prevalent themes in user conversations. Simultaneously, Sentiment Analysis is employed to gauge the sentiment expressed in these tweets, providing valuable insights into the overall sentiment towards Apple's support on social media platform "Twitter".

Technologies Used : Python (Snscrape, Pandas, Numpy and Matplotlib).

Project Workflow:

1. Tweets Extraction: snscrape Python's package is used to gather tweets with the #AppleSupport tag from Twitter.
2. Data Cleanup.
3. Latent Dirichlet Allocation (LDA).
4. Uncoverring hidden topics within the tweets using LDA and Summarizing these topics into meaningful themes.
5. Using pyLDAvis to interpret the LDA topic modelling.
6. VADER Sentiment Analysis implemnetation of tweets into positive, negative, or neutral.

By integrating snscrape, LDA Topic Modeling, and VADER Sentiment Analysis, this project extracted, processed, and analyzed #AppleSupport tweets. The aim was to provide valuable insights into past user sentiments and prevalent themes in customer discussions related to Apple support on social media.