Projects / Top Talent Project

Combating Mis/Disinformation in Mali using Machine Learning

Application Deadline: May 13

Omdena Featured image

This is a paid opportunity. In order to be eligible to apply for this project, you need to be part of the Omdena community and have finished at least one AI Innovation Challenge.

You can find our upcoming AI Innovation Challenges at

The problem

The spread of misinformation and disinformation poses a significant challenge, especially given the limited tools available for effectively identifying and mitigating such content. Misinformation (incorrect information shared without harmful intent) and disinformation (deliberately deceptive information) can distort public understanding, influence socio-political dynamics, and escalate conflicts. These types of content can spread rapidly through social media and other digital platforms, making them particularly hard to control without specialized tools tailored to the linguistic and cultural context of Mali.

Impact of the Problem:

  • Distorted Public Perception: Misinformation and disinformation can skew public perception and decision-making, leading to misinformed opinions and potentially harmful societal actions. In a country like Mali, where ethnic and political tensions can be high, the impact can be particularly severe, affecting peace and stability.
  • Undermining Trust in Institutions: Persistent misinformation and disinformation undermine trust in both local and national institutions. This erosion of trust can lead to increased skepticism towards governmental bodies, NGOs, and the media, complicating efforts to implement policies and engage with the community effectively.
  • Interference with Public Health and Safety: Mis/disinformation regarding health, particularly in the context of disease outbreaks or public health measures, can lead to poor health choices, resistance to medical guidance, and increased vulnerability to health crises.
  • Influence on Electoral Processes: During elections, mis/disinformation can manipulate voters’ opinions, disrupt the democratic process, and question the legitimacy of election results. This is particularly problematic in regions with a history of electoral violence or disputes.

This project’s goal is to develop and refine a dataset for training models to detect mis/disinformation in Bambara and to integrate these models into a real-time monitoring system to address these issues directly. By enhancing the capacity to monitor and react to harmful content, the initiative aims to improve public discourse, protect democratic processes, and bolster the overall societal resilience against misinformation and disinformation in Mali.

The project goals

The primary goal of this project is to develop and enhance a system designed to detect mis/disinformation in the Bambara language, thereby strengthening the resilience of communities in Mali against toxic and harmful content. This initiative will unfold over a series of planned phases:

  • Dataset Development: The first phase focuses on creating and refining a comprehensive dataset of Bambara language content, specifically tailored for training machine learning models on mis/disinformation detection. This dataset will serve as the foundation for the models, ensuring they are well-equipped to understand and analyze the nuances of the language and the specific types of misinformation prevalent in Mali.
  • Building/Finetuning The Classification Model: Cutting edge Natural Language Processing models (i.e. LLMs) will be levraged and finetune using this dataset with the goal of detecting toxic and harmful content. This phase is crucial for establishing a robust baseline from which further refinements can be made.
  • Model Validation and Refinement: Following the milestone above, a series of model validation and refinement sessions will be conducted. These sessions are intended to enhance the models’ performance based on real-world feedback and test results, actively addressing any inaccuracies or biases identified during initial testing. 
  • System Integration and Deployment: The final phase involves integrating the validated models into a real-time monitoring system. This system will be capable of providing immediate alerts on mis/disinformation and harmful content, significantly improving the ability of stakeholders in Mali to monitor and respond to such information promptly.

Thus, this project aims to deliver a powerful and effective system that shows significant advancements in the detection of mis/disinformation in the Bambara language. This initiative is expected to have a profound impact on supporting educational campaigns against misinformation, and bolstering the overall information integrity in Mali. Through this strategic enhancement, the project aspires to contribute to a more informed and resilient society in Mali.

**More details will be shared with the designated team.

Why join? The uniqueness of Omdena Top Talent Projects

Top Talent opportunities come as a natural next step after participating in Omdena’s AI Innovation Challenges.

Everyone in the community is eligible to participate once they have shown the relevant skills based on the merit of involvement in past Omdena challenges and the community.

If you are looking for the next challenge after participating in one or more Omdena AI Innovation Challenges, then we believe you have made the right choice! With a healthy, pressured environment, you will be pushed to contribute, learn and grow even more.

Find more information on how an Omdena Top Talent Program works

First Omdena Project?

Join the Omdena community to make a real-world impact and develop your career

Build a global network and get mentoring support

Earn money through paid gigs and access many more opportunities

Eligibility to join an Omdena Top Talent project

Finished at least one AI Innovation Challenge

Received a recommendation from the Omdena Core Team Member/ Project Owner (PO) is a plus

Skill requirements

Good English

Machine Learning Engineer

Experience working with Machine Learning, and/or NLP is a plus.

Application Form
media card
Combating Mis/Disinformation in Mali using Machine Learning
media card
Deploying a Platform for Detecting Dis/Misinformation in El Salvador with AI
media card
Developing a Platform for Detecting Dis/Misinformation in Mongolia with AI

Become an Omdena Collaborator

media card
Visit the Omdena Collaborator Dashboard Learn More