Veracity: A Visual Exploration of Misinformation

Overview of Keywords in Articles
Real / Fake Media Ratio Based on Location and Topics
Sentiment analysis of Articles
NORPs. People and Topics

About Veracity

The goal of this project is to extract key information such as entities, sentiment, and topics from the news articles and present them in an interactive visualization for further analysis.

The story we tell through data

Misinformation is rampant in today's media, causing confusion and mistrust among the public. With the widespread use of social media and the internet, it has become increasingly difficult to distinguish between real and fake news. In this story, we will explore the extent of misinformation in media articles, the entities involved, and the impact it has on society.

Tableau Dashboard

This data story highlights the severity of the problem of misinformation in media articles. We have seen the entities involved, the sentiment of the articles, the countries most affected, and the connections between organizations and countries. By understanding the extent of the problem, we can take steps to combat misinformation and promote accurate reporting.

How was it built?

To achieve the goal of the project, we will be using Python and several libraries such as pandas and spaCy for cleaning the data and extracting new information from the Articles. The pandas library is used to load and manipulate the news articles dataset, while spaCy is used for natural language processing to extract entities from the articles. The entities include location, organization, and people involved in the articles, which are essential for understanding the context and identifying key players in the news articles. The tools i have implemented can be used to identify patterns in the language used in the articles.

Technologies used:

Python 3.x: A high-level programming language used for general-purpose programming
pandas: A library used for data manipulation and analysis

python -m pip install pandas

spaCy: A library used for natural language processing

python -m pip install spacy

python -m spacy download en_core_web_md

subprocess: A module used for spawning new processes and executing commands
Git and GitHub: A version control system used for collaboration and code management
Tableau: For visualizing the resulting Dataset

Kaggle dataset used.