Twitter sentiment analysis

Project Title

Twitter sentiment analysis

Project Area of Specialization Computer ScienceProject Summary

Sentiment analysis, also known as "opinion mining" or "emotion Artificial Intelligence," refers to the systematic recognition, extraction, evaluation, and examination of emotional states and subjective information using natural language processing (NLP), text mining, computational linguistics, and bio measurements. Sentiment analysis is concerned with the voice in client materials, such as surveys and reviews on the Internet and social media sites.

The internet's frontiers are expanding as it grows in size. Facebook, Twitter, and Tumblr are among the most popular social media and microblogging services for rapidly disseminating condensed news and trending topics around the world. When a growing number of people contribute their opinions and judgments to a topic, it becomes a valuable source of online perception.

Large organizations and firms take advantage of people's feedback to improve their products and services which further help in enhancing marketing strategies. One such example can be leaking the pictures of the upcoming iPhone to create a hype to extract people's emotions and market the product before its release. Thus, there is a huge potential of discovering and analyzing interesting patterns from the infinite social media data for business-driven applications.

Twitter Sentiment Analysis has a number of applications like Companies use Twitter Sentiment Analysis to develop their business strategies, to assess customers’ feelings towards products or brand, how people respond to their campaigns or product launches and also why consumers are not buying certain products. In politics Twitter Sentiment Analysis is used to keep track of political views, to detect consistency and inconsistency between statements and actions at the government level. Twitter Sentiment Analysis is also used for analyzing election results, monitoring and analyzing social phenomena, for predicting potentially dangerous situations and determining the general mood of the blogosphere.

Project Objectives

The goal of this project is to extract data from Twitter and utilise it to uncover real-time trends and public opinion in order to apply it in company goals, social campaigns, marketing, and other promotional techniques. It can be used during elections, movie premieres, promotions, and other events to gauge public opinion and take appropriate action.

Our goal is to give people a way to find out what the general public thinks about their product, idea, or value.

Project Implementation Method

We purposed a step by step approach for sentiment analysis for twitter data. The purposed approach include the following steps;

1.Dataset/twitter dataset

2.Data Preprocessing

-stemming

-stop words removal

-tokinization

3.Part-of-Speech (POS) tagging

4. Feature extraction

I. Lexicon based approach 

-Sentiment score calculation using SentiWordNet

5.Lexical approach result

II. Machine learing based approach.

common features;

unigram and N-gram,number of word postive negative sentiment lenght of message number of exclamtion marks etc.

6.Feature generation

7. Feature selection

-Training the model and classifier Naive Bayes and Support Vector Machine

8. Machine learning approach result

-presion and recall

5.

3.feature extraction

Benefits of the Project

Twitter Sentiment Analysis can be used for a variety of purposes, including Companies use Twitter Sentiment Analysis to create their business strategy, measure customers' feelings toward items or brands, see how people react to campaigns or new launches, and figure out why particular things aren't selling. Twitter Sentiment Analysis is used in politics to keep track of political viewpoints and to find consistency and discrepancy between speeches and government actions. Twitter Sentiment Analysis is also used to analyse election outcomes, track and analyse social phenomena, identify potentially harmful situations, and gauge the mood of the blogosphere.

Technical Details of Final Deliverable

Software Requirements

1. Python
2. Machine Learning
3. NLP

Hardware Requirements

1. Processor 2.0 GHz or above
2. RAM 8GB
3. CPU 1.70GHz
4. Android phone

Final Deliverable of the Project Software SystemCore Industry ITOther IndustriesCore Technology Big DataOther TechnologiesSustainable Development Goals Decent Work and Economic Growth, Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	60000
Smartphone	Equipment	1	40000	40000
Tablet	Equipment	1	20000	20000