Skip to content

Movie Tag prediction from plot and reviews using Extractive neural Text summarization. Also Prediction of Genome scores prediction from Movie Lens dataset

Notifications You must be signed in to change notification settings

sanyam83/Movie_tag_prediction_using_text_summarization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

Movie_tag_prediction_using_text_summarization

Movie Tag prediction from plot and reviews using Extractive neural Text summarization. Also Prediction of Genome scores prediction from Movie Lens dataset

First Part of notebook is prediction of Movie Tags using Extractive Text summarization. In this Pre trained 100D Glove embedding and Bi-LSTM is used . Training Dataset Link Given below.

Second Part of Notebook is Prediction of Genome scores of Genome tags given in Movie Lens 20M Dataset. It takes Movie Plot and Reviews as input and predicts Genome Scores of all genome tags.

In Dataset of Movie Lens Genome Tags and Scores are features which contains how strongly movies exhibit particular properties represented by tags (atmospheric, thought-provoking, realistic, etc.). I have used 100D Glove embedding and Bi-LSTM RNN and Dense Layer for prediction of 1128 tags.

Architecture of Model

  • ac

Longest length sentence is more than 2000 words but I have used max length of sentence = 50 and can be taken till 1000 but more than that memory will run out or LSTM layer will be needed to reduce.

Dataset src:

Movie Lens 20M

plot data

reviews dataset

Text summarization dataset:

Text summarization dataset

About

Movie Tag prediction from plot and reviews using Extractive neural Text summarization. Also Prediction of Genome scores prediction from Movie Lens dataset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published