Student Research | Movie Recommender System Based on Natural Language Processing

By Kehan (Eric) Pan, Class of 2018

This excerpt is taken from an MSiA student research blog posting. Each month, students in our program submit original extracurricular research as part of our blog competition. The winner(s) are published to the MSiA Student Research Blog, our program website, and receive a chance to attend an analytics conference of their choice. Visit our blog to see more.

INTRODUCTION

Natural Language Processing (NLP) is rarely used in recommender systems, let alone in movie recommendations. The most relevant research on this topic is based on movie synopses and Latent Semantic Analysis (LSA) .However, the prediction power is far from satisfactory due to the relatively small average size of a recommendation. When applying Word to Vector (word2ec) methods on movie reviews, we witnessed a huge boost inperformance, and the results are mostly consistent with those of the Internet Movie Database (IMDB).

This article focuses on building a movie recommendation system (now deployed as web application). The following is a general view of the front end interface.

The website is now accessible through address is http://movienet.us-west-2.elasticbeanstalk.com/.

For the scope of the blog, we will be focusing primarily on the modeling aspect. For detailed code of the whole project refer to the Github folders, which includes code, documentation, and addendum instructions (additional tools for website building are available as well).

Github repository for website: https://github.com/pankh13/movienet

For model: https://github.com/pankh13/NLP_movie_recommender

Read More