Skip to content

vibhamah05/NLP_SentimentAnalysisonTwitter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

CS 4993: Natural Language Processing and Sentiment analysis

Independent Study with Professor Basit

ABSTRACT:

During the course of this independent study, I researched the topics of Machine Learning and Natural language processing and its practical application to improve the accuracy of computer-based predictions and assist humans in decision making. We furthered our exploration in the subfield of Natural Language Processing where we looked at neural networks and logistics regression models and the application of semantic analysis of text based data input through these models. Our final project in the study is to conduct a semantic analysis on twitter texts with emoticons to see if the model can predict their right sentiment of the text based on context. Semantic analysis is a useful tool to understand the meanings of texts and extract critical information from unstructured data to understand users and improve the overall user experience.

A Sentiment Analysis of Emoji-based texts on Twitter

Natural Language processing (NLP) is used to understand the structure and meaning of human language like semantics, syntax, morphology into machine learning algorithms that can automate speech and help with various human interactions like conducting large scale analysis of unstructured data like social media comments. NLP also combines fields of computational linguistics and deep learning with neural networks to better understand languages and human conversion. NLP’s pre-processing techniques are the following- tokenization, stemming, lemmatization which break words and phrases into token through text vectorization processes and bring them to their root form so that they can go through sentiment and semantic analysis before being used to train the algorithm. Semantic analysis specifically classifies text by polarity of option and this can be done a wide range from positive, to neutral to negative, depending on how specific you want to be with your output data. Sentiments analysis allows you to classify data and capture underlying patterns to understand the voice of the customer and analyze sentiments for a particular project or product to better fit customer needs, as well as popular opinions on trending topics to get a clearer overview of the collective sentiments that are expressed. More recently, chatbots like ChatGPT are launched to understand user emotions and give relevant assistance from customer interactions and save business costs in customer service.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages