Human sentiment analysis using natural language processing

Abstract

"Emotion is something that roams with us, the vibrant tapestry of our human existence. People are frequently so emotionally motivated that we may get a peek of their emotions simply by observing them, listening to them, or reading their text messages/social status. For this reason it is hard sometimes to detect someone’s feelings. Therefore, we have devised a plan to examine and comprehend the sentiment of a person as determined via sentiment analysis which is a part of natural language processing (NLP). To determine various values from various data configurations, we used three hybrid models: CNN-LSTM, LSTM, and RNN. Six target variables made up the first smaller datasets we worked on, and then we moved on to some larger datasets. People today tend to frequently post their ideas on social media. They want the world to know about their suffering, hope, and joy. Our main objective is to build a program or project that uses sentiment analysis to analyze a person’s writing and generate a report about his or her emotion by that. We also intend to acquire useful real-world datasets. In a contemporary society where people are so emotionally motivated, we aim to recognize their sentiment digitally via natural language processing where we can help a lot of people by that"

Description

Cataloged from PDF version of thesis.
Includes bibliographical references (pages 33-36).
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.

Keywords

Sentiment, CNN-LSTM, LSTM, RNN, Emotion, NLP, Prediction, Token, Embedding

Citation

Endorsement

Review

Supplemented By

Referenced By