Event Detection System

Twitter is one of the fastest growing microblogging and online social networking platform. Analysis of these huge mounds of user-generated content could provide unprecedentedly valuable information to detect real-life events. Such an analysis can be immensely valuable if it is discovered timely

Project Title

Event Detection System

Project Area of Specialization

Artificial Intelligence

Project Summary

Twitter is one of the fastest growing microblogging and online social networking platform. Analysis of these huge mounds of user-generated content could provide unprecedentedly valuable information to detect real-life events. Such an analysis can be immensely valuable if it is discovered timely and made available. Thus, exploiting such data is useful to detect meaningful information successfully. Visualization is the means by which humans understand complex analytics and is often the most crucial and overlooked step in the analytics process. Data presented in graphical form enables decision-makers to take in large amounts of data and gain an understanding of what it means very quickly. The huge volume of dynamic content, publishing rapidly on Twitter, brings a great opportunity for designing an exploratory/faceted visual interface to exploit the micro-blogs in real-time for detecting and visualizing events related to trending topics. This project will analyze the tweets to identify and visualize the events happening around the world in real-time. The project will not only detect events, but will also provide interfaces to get insights of the event.

Project Objectives

Aware people related to current events and issues all over the world. Some of the services are below:

• People can view events.
• People can search for events.
• Send notification to user related latest news.
• Process big data in minutes.
• Researchers can also use this system to check the performance or efficiency of their event detection algorithm with the same parameters.
• User can visualize event with different kind of graphs like timeline chart, network graph and word cloud.

Project Implementation Method

Tools and techniques:

Following are the tools and techniques that will be used in implementation:

• PyCharm (as IDE).
• Twitters filter API.
• Google map API for the location to get longitude and latitude values.
• Event Detection algorithm.
• Different graphs API for visualization.

Implementation Methodology:

1. First of all, I divided my project into three parts (1)  Crawler (2) Event Detection (3)  Visualization(Master system).
2. I design and implement all three parts step by step, in the first step, I will design and implement a form for crawler parameters those will be passed to Twitter through Twitter's filter API and the system will be able to fetch tweets.
3. In the second step, these tweets pass to the EDA(Event Detection Algorithm) and the algorithm detects events from the Twitter filter stream fastly, and at the end provide some results related to events.
4. In the third step, we will use those parameters for visualisation and display an event in the form of graphs and charts mentioned in the above section.

As the project involves retrieval and processing of tweets in real time and huge volume, it requires computational resources like huge RAM, GPU, and SSD. Although a computer is not requested by the project, but project funding will be used to upgrade existing resources of the university to make the execution of this project possible.

Benefits of the Project

1. This system focuses on detecting events in real time using EDA by analyzing the contents published on Twitter.
2. It is quite meaningful and valuable to detect events from different locations.
3. Can help government and non-government organization in policymaking. E.g. Traffic jams, security threat, natural events, and epidemics.
4. Wisdom of crowds will be used to detect events.
5. It will be helpful in natural disasters to provide facility/help in those areas. Like USGS ( U.S Geological Survey ) uses Twitter data to track earthquakes.

Technical Details of Final Deliverable

Following are the technical details of the final deliverable:

1. The system will be able to crawl tweets from Twitter using its filter API as I described earlier it will be the first part/deliverable of the system.
2. Pass that data to the Event detection algorithm.
3. After detecting the event that details will be passed to the visualizer(similarly 2 & 3 points will be the second part/deliverable of the project).
4. Visualizer will make graphs from that details of an event that will be humanly understandable and this will be the last part/deliverable of the project.

System Architecture Diagram:

Final Deliverable of the Project

Software System

Type of Industry

IT , Security , Telecommunication

Technologies

Big Data

Sustainable Development Goals

Decent Work and Economic Growth, Sustainable Cities and Communities

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com