Effect of Word Embedding Techniques on Clustering of Netflix Movies and TV Shows dataset
Pankaj R. Beldar, Rahul Rakhade, Vaibhav Khond, Mugdha Bhadak, Milind Bahiram, Prashant Kavale
clustering, word2vec, countvectorizer, TFIDF vectorizer, NLP, Stemming, and Bag of words
Netflix is one of the leading over-the-top (OTT) platforms because of its reputation for offering users a wide variety of high-quality streaming movies as well as TV Shows. The reason why Netflix's services are so popular worldwide is that the company uses recent technologies like machine learning, deep learning and Artificial Intelligence to provide consumers with more appropriate and intuitive recommendation. This paper is based on Unsupervised Clustering Analysis on Netflix Movies and TV Shows dataset. Aim of the Project is to form the Clusters based on K mean clustering, Agglomerative Clustering and Affinity Propagation Clustering. We have done Data Preprocessing, Text Cleaning, Exploratory Data Analysis, Vectorization, Implementing Clustering Models, Hyper parameter tuning. Dataset is analyzed with Word2Vec Word Embedding, CounVectorizer and TfidfVectorizer. Out of these Word2Vec has much better performance than other methods. I have Keep Silhouette Score , Elbow Method and Dendrogram as the Selection Criteria for Finding out optimum number of Clusters. We figure out Exploratory Data Analysis, Understanding what type content is available in different countries, Netflix has increasingly focused on TV rather than movies in recent years. Clustering similar content by matching text-based features
Article Details
Unique Paper ID: 157682

Publication Volume & Issue: Volume 9, Issue 7

Page(s): 716 - 725
Article Preview & Download

Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews