This project investigates the changing landscape of media consumption during the COVID-19 pandemic. It aims to identify trending genres and audience preferences between short-form and long-form content. The analysis combines sentiment analysis of IMDb reviews, viewership data analysis, and integration of additional datasets to provide a comprehensive view of media consumption trends.

Technical Approach:

1. Sentiment Analysis:

   • Conduct comprehensive sentiment analysis on IMDb reviews

   • Utilize natural language processing techniques to identify top-rated content

   • Implement machine learning models for sentiment classification

2. Viewership Pattern Analysis:

   • Process and analyze detailed viewership data

   • Identify trends in content consumption

   • Compare popularity metrics with sentiment analysis results

   • Utilize data visualization techniques to represent consumption patterns

3. Data Integration and Complex Analysis:

   • Incorporate additional datasets such as box office revenues and social media sentiment

   • Develop data integration pipelines to merge diverse data sources

   • Perform statistical analysis to identify correlations and trends across datasets

4. Insight Generation:

   • Develop algorithms to extract actionable insights from the analyzed data

   • Create predictive models for future content preferences

   • Generate reports and visualizations for stakeholders in the media industry

Tech Stack:

• Python for data processing and analysis

• Natural Language Processing libraries (e.g., NLTK, spaCy)

• Machine Learning frameworks (e.g., scikit-learn, TensorFlow)

• Data visualization libraries (e.g., Matplotlib, Seaborn, Plotly)

• Big Data tools for large-scale data processing (e.g., Apache Spark)

• SQL and NoSQL databases for data storage and retrieval

• Cloud computing platforms for scalable processing (e.g., AWS, Google Cloud)

Key Features:

1. Multi-dimensional analysis combining sentiment, viewership, and industry data

2. Utilization of natural language processing for sentiment analysis

3. Large-scale data processing and analysis of viewership patterns

4. Integration of diverse datasets including box office revenues and social media sentiment

5. Insights generation for production houses and media companies