This project has a two-fold aim. First, we seek to determine what makes an idea seem novel versus ordinary and if there is an ideal mix of the two. Second, building on these findings, we build a generative model that suggests tweaks to an idea that enhance its perceived creativity and appeal. We will pursue these two aims using 69K recipes and reviews from allrecipes.com. We will use NLP approach to extract important features from the recipe such as ingredients, preparation instruction and review content.

We need support in the following tasks:

  • Extracting important features from recipe preparation instruction using NLP approach
  • Identifying sentiment and which ingredients are recommended as substitutes to which ingredients in the review texts
  • Efficiently designing an algorithm that runs in real-time and suggest additional ingredients or ingredient replacement that will increase the impact of a new recipe

This is an UNPAID research project.

Faculty Advisor

  • Professor: Oded Netzer
  • Department/School: Marketing/Columbia Business School

Project Timeline

  • Earliest starting date: 3/1/2021
  • End date: 8/31/2021
  • Number of hours per week of research expected during Spring 2021: ~8
  • Number of hours per week of research expected during Summer 2021: ~8

Candidate requirements

  • Skill sets: Strong programming skills in Python and R. We are seeking students with backgrounds in probabilistic models and NLP, ideally through a course and a research project. Prior experience working with recommendation models and word embeddings is a definite plus.
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: eligible
  • Academic Credit Possible: Yes