Artificial Intelligence Mini-Project for Sem VI
This Twitter Sentiment Analyzer helps detect the Hate Speech using two of the different datasets that we found on surfing the web
-
Sentiment140 Dataset
-
It contains 1.6 million tweets extracted using the Twitter API
-
The tweets have been annotated (0 = negative, 4 = positive) and they can be used to detect sentiment
-
Sentiment Analysis is done by introducing Polarizing and Subjectivity to classify the data as positives and negatives and plaot them on a bar graph, to display the weightage of positive tweets, negative tweets and the neutral tweets
-
Original Source: https://www.kaggle.com/kazanova/sentiment140
-
-
Racist/Hate Speech Detection
-
32K tweets labeled as hatred (racist/sexist) or non hatred, provided by Analytics Vidhya
-
The task is to classify racist or sexist tweets from other tweets
-
Formally, given a training sample of tweets and labels, where label '1' denotes the tweet is racist/sexist and label '0' denotes the tweet is not racist/sexist, our objective was to predict the labels on the test dataset
-
Sentiment Analysis (Racist/Hate speech detection) is done using Bag of Words and TFIDF
-
Sentiment Analysis (Racist/Hate speech detection) is done using Bag of Words, TFIDF and Multinomial Naive Bayes
-
Original Source: https://www.kaggle.com/arkhoshghalb/twitter-sentiment-analysis-hatred-speech
-