Skip to main content

Credits & Attribution

Dissecting the Divide is built by a passionate team using open-source tools, public datasets, and state-of-the-art NLP models. Here is who and what makes it possible.

About the Project

Dissecting the Divide is an MIT xPRO AI/ML course project that investigates why professional film critics and general audiences sometimes disagree about a movie's quality. Using natural language processing, we analyze reviews to identify the specific aspects of a film that drive the largest critic-audience sentiment gaps.

The project spans the full AI/ML lifecycle — from data collection and conditioning through transformer-based modeling, explainability, and an interactive dashboard.

Team

We are Team 11 from the MIT xPRO Professional Certificate in AI/ML program.

ST

Shehzad Thamarath

RN

Reshmi Nair

JW

Jacqueline Wulwick

ME

Maddy Eda

RW

Ron Watkins

SB

Seth Bibler

RM

Robert Markel

ZS

Zachary Schaub

Open-Source Acknowledgements

This project is built on the shoulders of open-source software. We gratefully acknowledge the following projects and their contributors, grouped by license.

LGPL-2.1 / LGPL-3.0

  • Playwright — Browser automation for review crawling
  • chardet — Character encoding detection

MIT

  • Next.js — React framework for the web dashboard
  • Tailwind CSS — Utility-first CSS framework
  • Vitest — Unit and component testing
  • scikit-learn — ML utilities and cosine similarity

Apache-2.0

  • PyTorch — Deep learning framework for transformer models
  • Hugging Face Transformers — Pre-trained NLP model library

BSD

  • NumPy — Numerical computing and array operations
  • Pandas — Data manipulation and analysis
  • Matplotlib — Static chart generation

This product uses the TMDb API but is not endorsed or certified by TMDb. Film metadata, posters, and related content are provided courtesy of The Movie Database (TMDb) (opens in a new tab).