Twitter Sentiment Analysis

Problem statement

This project aims to extract the features of tweets and analyze the opinion of tweets as positive, negative or neutral.

Input: Textual content of a tweet
Output: Label signifying if the sentiment of the tweet is positive/negative/neutral

Motivation

Tweets sometimes express opinions about different topics. These opinions are important in many business-related decisions and even political sentiments about a candidate.

Consumers can use sentiment analysis to research products or services before making a purchase. E.g. Kindle
Marketers can use this to research public opinion of their company and products, or to analyze customer satisfaction. E.g. Election Polls
Organizations can also use this to gather critical feedback about problems in newly released products. E.g. Brand Management (Nike, Adidas)

Challenges faced

Noisy text (Misspellings, lack of grammar)
Lack of context
Acronyms e.g: lol, brb, gr8
Emoticons e.g: :), :(
Negation

Pipeline for approach used

Tweet downloader

Download the tweets using twitter API (https://github.com/aritter/twitter_download).
9684 training and 8987 testing tweets are downloaded.

Parser

The parser removes all unavailable tweets from the downloaded data
After removing these we have 7612 tweets for training and 7868 tweets for testing

Pre-processing

Replace Emoticons by their polarity.
Remove URLs and Targets.
Expand acronyms. eg 'brb' to 'be right back'
Remove stop words
Tokenization
Stemming
Case-folding
Remove punctuation marks
Replace sequence of repeating characters eg. 'hellooooo' by 'helloo'

Feature Extraction

The pre-processed data file is fed to the feature extractor which creates the feature vector.
The basic (baseline) feature was the unigram model
A list of all unique unigrams across the training set was constructed and it formed the basic vector for each tweet.

Additional Features

Polarity scores of the tweets
Negation
Hashtags
Special characters (?,!,*)
Capitalized words
Bigrams

SVM Classification and Prediction

The features extracted are passed to the classifier
The model built is used to predict the sentiment of the new tweets

Results

Features	Accuracy	Precision	Recall	F1 score
Unigram	54.855%	0.5264	0.5061	0.5125
Unigram + Additional Features	57.079%	0.5524	0.5308	0.5385
Bigram	58.579%	0.5713	0.5172	0.5268
Bigram + Additional Features	60.739%	0.5930	0.5525	0.5637

Twitter-sentiment-analysis