In this project, I analyzed thousands of tweets and Instagram captions mentioning a lifestyle brand to determine public sentiment and identify trending themes. The goal was to provide the marketing team with a deeper understanding of how their products and messaging were being received online.

Using Python libraries like Tweepy and BeautifulSoup, I collected and preprocessed text data. I applied natural language processing (NLP) techniques such as tokenization, sentiment scoring (VADER), and topic modeling (LDA) to extract patterns and measure sentiment polarity. Visualizations included word clouds, sentiment over time, and topic heatmaps.

Findings showed a significant drop in sentiment following a controversial campaign, while positive spikes correlated with limited-edition product launches. These insights were used to guide future campaigns and improve crisis response strategies. The final report included data-driven recommendations for messaging and product positioning.

Skills Gained:

• Data scraping & text preprocessing

• Natural Language Processing (NLP)

• Sentiment analysis (VADER) & topic modeling (LDA)

• Python data tools (NLTK, pandas, matplotlib)

Note - Photo credits go to HALO LAP. The use of cover photo is for template purposes only.