Analyzing Land Conflicts and Government Policies through Natural Language Processing

Project completed!

The team built a machine learning driven visualization app that matches land conflict events from news articles with mediating government policies. This enables policy makers to make data-driven decisions and resolve land conflicts faster, save resources, and facilitate environmental sustainability efforts.

The AI project was hosted by the World Resources Institute with a focus on India as a country struggling heavily with land disputes.

A detailed whitepaper from the project can be downloaded here.

Why: AI for environmental sustainability

Land degradation affects 3.2 billion people and costs the global economy about 10 percent of the gross product each year. While dozens of countries have committed to restore 350 million hectares of degraded land, land disputes are a major barrier to effective implementation. Without streamlined access to land use rights, landowners are not able to implement sustainable land-use practices. The problem’s scale requires a scalable solution. In India, where 21 million hectares of land have been committed to the restoration, land conflicts affect more than 3 million people each year. Luckily, AI and machine learning offer tremendous potential to not only identify land-use conflicts events but also match suitable policies.

The solutions: Machine Learning and NLP for identifying land use conflicts

This AI challenge resulted in several solutions such as:

• Applying coreference resolution to news text data using SpaCy and Neuralcoref.
• Using ELMo, BERT, and Logistic Regression algorithms to train on labeled and co-referenced text data to predict positive and negative conflict articles.
• Topic modeling to find relevant topics using CorEx with an accuracy score of 93 percent.
• Matching government policies to the conflict news events to understand policy gaps.
• Visualization of conflict events and their connection to policies.

The data: Land use conflict news articles.

The data for this Omdena challenge was scrapped from various news media reports with 65,000 candidate conflict articles. This process involved downloading GDELT data for a given country for an input period of time using Google Bigquery, scrapping full news text for a media article using news-please, and manually labeling one month of news media data as Negative (no conflict news) and Positive (conflict news) with approximately 1,600 articles.

The impact: AI for environmental sustainability.

Land conflicts in India

According to the Environmental Justice Atlas, India has the most number of environmental conflicts, followed by Colombia and Nigeria. For instance, approximately 66% of all civil cases in the Supreme court of India are related to land disputes for more than 2.5 million hectares of land. This affects an estimated 7.7 million Indians threatening investments worth $ 200 billion, according to the June 2019 report by the Centre for Policy Research.

The solutions will help policymakers to make data-driven decisions in a more accurate and efficient way.

We are thanking all community collaborators for the amazing work done! AI For Environmental Sustainability!