Skip to content

chihangs/IMDB

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 

Repository files navigation

IMDB

The problem to solve is sentiment analysis of the text. The dataset chosen for training is IMDB Review, as it has large amount of data - 50,000 labelled movie reviews with ambiguous sentiment removed (by removing those with middle ratings), which is ideal for training. The dataset was contributed by Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. (2011) Learning Word Vectors for Sentiment Analysis. The 49th Annual Meeting of the Association for Computational Linguistics (ACL 2011). We use csv version of data with train/validation/test ratio 80/10/10 from: https://www.kaggle.com/datasets/columbine/imdb-dataset-sentiment-analysis-in-csv-format. [note: it is too large to upload train.csv]

This task is interesting as it has potential to generalize to other domains, not just movie reviews. As an extra task, to test the generalization ability, a small dataset of 100 restaurant reviews is collected from opentable.com, also removing those with middle ratings.

Model parameter files are too large to upload to the folder "para"

About

Sequence Model - sentiment analysis

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published