Summer 2017 opportunity!
NYC Media Lab is seeking a NYC-based university data science faculty member who can lead a group of 2-4 graduate students to complete a software engineering/data science project with Audible over the summer in 2017. The project budget is $25,000. The project will focus on experimenting with metadata extraction from a book’s manuscript. The goal will be to extract named entities such as location references, companies or characters. The expected final deliverable is a presentation from the project team, including demonstration of a prototype and documentation of the prototype.
Project research questions:
- How can we enhance the Audible customer’s experience with overlays of metadata and contextual information from the book he/she is listening to?
- Given a dataset from a single book, how can we experiment with different data science tools and methods to extract metadata and derive annotations that an Audible customer will enjoy? What current tools and technologies can we use to develop a prototype and demonstrate a use case for an Audible customer?
- Once the metadata is extracted and the annotations are derived, how can we relate this information to personalization and recommendation technologies?
Email Amy Chen at email@example.com for more details about this opportunity.