Find Movie Similarity from Plot Summaries
Use NLP and clustering on movie plot summaries from IMDb and Wikipedia to quantify movie similarity.Start Project
12 Tasks1,500 XP
Loved by learners at thousands of companies
Natural Language Processing (NLP) is an exciting field of study for data scientists where they develop algorithms that can make sense out of conversational language used by humans. In this Project, you will use NLP to find the degree of similarity between movies based on their plots available on IMDb and Wikipedia.
The dataset contains the titles of the top 100 movies on IMDb as well as each movie's plot summary from both IMDb and Wikipedia.
- 1Import and observe dataset
- 2Combine Wikipedia and IMDb plot summaries
- 5Club together Tokenize & Stem
- 6Create TfidfVectorizer
- 7Fit transform TfidfVectorizer
- 8Import KMeans and create clusters
- 9Calculate similarity distance
- 10Import Matplotlib, Linkage, and Dendrograms
- 11Create merging and plot dendrogram
- 12Which movies are most similar?
Anubhav SinghSee More
CTO & Co-founder, Dynopii
A developer since the pre-Bootstrap era, Anubhav has over a decade of experience dealing with large-scale software complexities as a freelancer before embarking on his own AI startup venture - Dynopii Inc. He has authored two books, "Hands-on Python Deep Learning for Web” and “Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter”. He's also a Google Venkat Panchapakesan Memorial Scholar. Anubhav has been a contributor to several open-source projects and was a Google Summer of Code participant in 2019. He also leads the team at GDG Cloud Kolkata. You will often find him talking about System architecture, Machine Learning and the web.