AI-Powered Progress Determination on Media Representation for Women, Youth, and Marginalized Groups in Nepali Language Media

Develop an AI-assisted scoring model, that will aid in effectively determining the representation of people belonging from different groups in Nepal using media content. In this 8-week challenge, you will join a collaborative team of 50 AI engineers from all around the world.

The problem

Media plays a vital role in shaping public opinion and perceptions. However, the media can also be biased and inaccurate, which can have a negative impact on marginalized groups. For example, the media often portrays women and youth in a negative light and can be dismissive of the issues that they face. This can lead to discrimination and violence against these groups.

This project aims to address the above problem by conducting a media content analysis of mainstream media, social media, and Nepali radio with a focus on Madhesh Province (Province 2) and Lumbini Province (Province 5). The analysis will be conducted on a yearly basis using a quantitative methodology with the goal of measuring the average rating of the diversity of media content and representation of women, youth, and marginalized groups using the OIND 3.1 indicator.

The project will collect online news, video, and social media data to rate media content based on diversity and reliable representation using natural language processing and machine learning algorithms. 

This project has the following goals:

• Increased awareness of the issue of media bias and inaccuracy.
• Improved representation of women, youth, and marginalized (WYM) groups in the media.
• Reduced discrimination and violence against these groups.

This project aims to be a valuable contribution to the effort to promote equality and justice for all of Nepal’s population.

The project goals

The ultimate project objective is to classify WYM-related media content and rate media content based on diversity and reliable representation using natural language processing and AI algorithms.

The main goals of this Omdena AI Innovation Challenge are:

• Web scraping of online news, video, and social media data.
• Develop Nepali language models that can accurately and comprehensively represent the nuances of the language, including local idioms and expressions. These models will be used to classify WYM-related media content based on multiple factors, such as the presence, context, and sentiment of women, youth, and marginalized groups.
• Develop a scoring model to assign a score to each piece of media content based on its diversity, sentiment, and other relevant factors. The score can be used to measure progress towards improving the availability of credible information and diverse narratives within media that better represent WYM issues and perspectives.

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