Task

The internet is inundated with false rumors and fake news. Hoarding as a result of misinformation during times of disaster should still be fresh in your memory. In order to see through such misinformation, the objective of the task is to develop a machine learning model to determine whether the account tweeting is verified.

Over 100,000 lines of data consisting of tweets from both verified and non-verified users have been organized.

Data

Verified accounts are determined by the presence of a verification badge, a link from a corporate website (verification by the corporation), and other factors that lead the data collector to conclude that the account has a high degree of authoritativeness. Non-verified accounts refer to all other accounts, including anonymous accounts and individual hobby accounts.

Annotation rules

0: Tweets from verified accounts
1: Tweets from non-verified accounts

*The presence or absence of the badges were current at the time of data collection and may have changed.

Rules

Use of outside data, pre-trained models

Training, inference, or prediction with models using data other than the distributed data is forbidden.
The use of APIs such as Google Cloud Vision API is forbidden. However, The use of open-source (source is clear, open access, and non-commercial) pre-trained models or libraries is allowed. When using pre-trained models, please specify the source (link to thesis, etc.).

Disclosure Policy

Participants may freely post to social media or source repositories, or cite in theses, etc.

System Usage

Individual participation
Each person may only use one account, the use of multiple accounts is forbidden.

Competition Rules

Individual clauses are not specified.