Skip to content

Latest commit

 

History

History
19 lines (13 loc) · 1.56 KB

README.md

File metadata and controls

19 lines (13 loc) · 1.56 KB

Sentiment-Analysis-of-Tweets

This project has been done as an imperative part of my internship at Indian Institute of Technology Kanpur (2020).

Objective

To Develop a Natural Language Processing (NLP) model that will allow to do polarity classification of tweets.

Authors

  • Divya Gladys G
  • Yazhini K

A breif description of the project

This project has been done in participation with a Kaggle InClass competition. We have extracted the nature of the opinions to classify the given set of tweets based on their polarity as positive, negative or neutral. We have attempted to develop a number of skills such as – various techniques for pre-processing text, and for text vectorization using feature extraction. I have also compared the adequacy of various statistical models such as Naïve Bayes, Logistic Regression, Support Vector Machines for text classification.

For further details about the Exploratory data analysis, data pre-processing phase, word-embedding techniques, various machine learning algorithms used and the results of the models, refer to the project report.

Sentiment Analysis of tweets - Kaggle InClass Competition

Our group name is "The DY Duo" and we placed 14th place in the public leaderboard with a score 0.67207 and 12th place in the private leaderboard with a score of 0.66759 in the competition.