2023 IDIR Data Visualization Challenges

Challenge designed by Dr. Chengkai Li

Visualizing Fact-checks using the provided file. The schema of the file is as follows:

• Publisher: the organization that published the fact-check
• Claim: the statement or information that was fact-checked
• Summary: a brief summary of the fact-checking review
• Review: a more detailed description of the evidence and reasoning used to evaluate the claim
• Verdict: the conclusion or verdict reached by the fact-checker (e.g., true, false, misleading, etc.)
• Author: the name of the author or authors who conducted the fact-check
• Date: the date on which the original claim was published
• Factcheck Published Date: the date when the fact-check was published
• Thumbnail URL: a link to a thumbnail image associated with the fact-check
• URL: the URL of the fact-check
• Tags: any relevant tags or categories associated with the fact-check, such as the topic or subject matter


It is important to note that not all publishers have all the fields mentioned above. We highly recommend using Pandas to read data instead of Excel or Numbers as it is easier for data preprocessing and subsequent use. Submissions should offer meaningful visualizations, such as analyzing health-related conversations on social media, understanding public perception about health topics, and developing machine learning models to classify tweets based on their relevance to health. Data preprocessing may be required, such as cleaning the text data, removing stopwords, tokenizing the text, and performing sentiment analysis, among others. The preprocessing is aimed at making the data more suitable for analysis and extracting meaningful insights from it.