Analysis of users behavior on twitter

Project Title

Analysis of users behavior on twitter

Project Area of Specialization Mechatronics EngineeringProject Summary

Great social interest network sites among internet users are growing exponentially on the rise of Global Technology. With the rapid growth of Social Media users in recent years, an online social media platform is a great way to express a person's behavior to a topic. Twitter is one of the most widely used social media platforms to express ideas where user posts and share messages called “tweets”. Every year millions of tweets have been posted on this site and this is leading to analyze user mood or behavior based upon his/her respective post. Analyzing tweets to determine user behavior is a challenging and exciting task for researchers and engineers especially in the field of information dissemination. In this analysis the system will the behavior of the user like passive, aggressive and passive-aggressive by considering the total number of positive, negative or neutral keywords or opinion of the user in all his/her posts. The abundance of social media data provides opportunities to understand criminal minded experiences, but also raise methodology difficulties in making sense of social media data for educational, business, and events purposes. Behavioral analysis was performed on a repository of tweet stored by considering a several algorithms and the classification are made between tweets. This method of operation is implemented using the Python programming language. The main aim is to avoid tweets that are viral or unwanted or scary tweets from the social media and this helps to provide the best a recommendation for positive users for their experience in the social site. Finally, the goal is to compare both the results of the implementation and to prove the best way for behavior analysis in social media data sources.

Project Objectives

It aims to analyze people's behaviors, attitudes, opinions, emotions, etc. about things like products, people, topics, organizations, and services. Behavioral text analysis that identify and releases specific information from the source, and help the business understand the social behavior of its product, product or service while monitoring online conversations and tweets. It helps you determine how much of your particular audience is invested in any emerging trends. And what, really, do they feel about the styles mentioned again.

Project Implementation Method

We apply a supervised machine learning to classify user behavior categories such as (passive, aggressive or passive-aggressive). We use Naive Bayes algorithm for our project as it has highest accuracy rate. The tweets data are classified into the suitable class or category such as passive, aggressive or passive-aggressive. The identification requires a long process step by step which are as follow:

• Tweets data (User input)
• CSV file
• Feature extraction
• Applying classification algorithms
• Data validation

Benefits of the Project

Behavioral analysis primarily looks at factors such as: emotions, thinking, emotions, communication, and interaction with people. This analysis is used to design dividers to identify positive, negative and neutral users.

Technical Details of Final Deliverable

All code shall be fully documented. Each function shall be commented with pre- and post-conditions. All program files shall include comments concerning authorship and date of last change. The code shall be modular to permit future modifications

Final Deliverable of the Project Software SystemCore Industry ITOther Industries Others Core Technology Artificial Intelligence(AI)Other Technologies OthersSustainable Development Goals Quality EducationRequired Resources