Cross-Language Media Review: Identifying Inaccuracies in GESI Conversations

In today’s digital age, the proliferation of inaccurate or misleading content online poses a significant challenge to societal well-being and informed public discourse. Particularly in the context of Gender Equality and Social Inclusion (GESI), it’s essential to ensure that online narratives are accurate and constructive. This project focuses on developing robust language models for Tamil and Sinhala. These models will be specialized in analyzing online content related to GESI, aiming to identify and flag content that may be misleading or factually inaccurate. In this 8-week challenge, you will join a collaborative team of 50 AI engineers from all around the world.

The problem

The digital landscape, especially in multilingual contexts like Sri Lanka, is often riddled with content that can skew public perception and hinder social progress. Identifying such content manually is a labor-intensive and challenging task, given the volume of data generated every day. There’s a pressing need for automated solutions that can process information in local languages like Tamil and Sinhala effectively, ensuring that the digital discourse surrounding GESI topics is healthy and informative.

The project goals

1. Data Gathering and Annotation: Collect a comprehensive dataset of online content in Tamil and Sinhala, spanning various digital platforms. This dataset will then be meticulously labeled, categorizing content based on its accuracy and relevance to GESI topics.
2. Language Model Development: Develop and fine-tune advanced language models for Tamil and Sinhala. These models will be specifically tailored to understand the nuances of content related to GESI, enabling them to effectively analyze and flag content that does not align with factual accuracy.
3. Promote Informed Discourse: By ensuring that the digital space is conducive to accurate and constructive discussions around GESI, the project aims to contribute to a more informed and inclusive online environment.

Through these goals, the project aspires to foster a digital ecosystem where discussions around GESI are rooted in accuracy and constructive dialogue, thereby supporting social progress and understanding.

Why join? The uniqueness of Omdena AI Innovation Challenges

A collaborative experience you never had in your working life! For the next eight weeks, you will not only build AI solutions to make a real-world impact but also go through an entire data science project lifecycle. This covers problem scoping, data collection, and preparation, as well as modeling for deployment.

And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.

Find more information on how an Omdena project works