TWITTER SENTIMENT ANALYSIS TO CLASSIFY HATE SPEECH IN TWEETS PYTHON PROJECT

TWITTER SENTIMENT ANALYSIS TO CLASSIFY HATE SPEECH IN TWEETS PYTHON PROJECT

Download source code @ WWW.MICANSINFOTECH.COM ; WWW.SOFTWAREPROJECTSCODE.COM https://www.facebook.com/MICANSPROJECTS
Call: +91 90036 28940 ; +91 94435 11725

MICANS INFOTECH PVT LTD, pioneer in software application development, android apps, medical imaging , research applications , customized software applications, ERP systems .
IT Services | Android Apps | ERP Software | Web Development
E-Commerce | Engineering Services

TWITTER SENTIMENT ANALYSIS TO CLASSIFY HATE SPEECH IN TWEETS PYTHON PROJECT
Abstract:
The objective of this project is to detect hate speech in tweets. Tweet contains negative/hate sentiments as well as positive sentiments. So, the task is to classify negative tweets from other tweets. Given a training sample of tweets and labels, where label '0' denotes the tweet is negative and label '1' denotes the tweet is not negative. The objective is to predict the labels on the test dataset.

Sentiment Analysis:
Sentiment analysis and Opinion mining is the computational study of User opinion to analyze the social, psychological, philosophical, behavior and perception of an individual person or a group of people about a product, policy, services and specific situations using Machine learning technique. Sentiment analysis is an important research area that identifies the people’s sentiment underlying a text and helps in decision making about the product.
FLOW OF PROJECT
1. Data loading.
2. Checking Distribution of Data.
3. Data Preprocessing
Remove Punctuations,special symbols and special characters.
Tokenization
Stemming
WordCloud

Feature Extraction:
1. Bag Of Words
2. TF-IDF
3. Word2Vec

Model Building:
Building Logistic Regression
Support Vector Machine (SVM) on BOW,
TF-IDF & Word2Vec features.

Results:
Logistic Regression and SVM on Word2Vec features outperforms the other model.