How to decode modern conflicts with cutting-edge technologies
In modern warfare, new technologies are increasingly being used to manipulate information and perceptions on the battlefield. This includes the use of deep fakes, or the malicious use of ICT (Information and Communication Technologies).
Likewise, emerging tech can be instrumental in documenting human rights violations, tracking the movement of troops and weapons, monitoring public sentiments and the effects of conflict on civilians and exposing propaganda and disinformation.
The dual use of new technologies in modern warfare highlights the need for further investigation. Here are two examples how the can be used to advance politial analysis and situaitonal awareness.
Breakthrough for sentiment analysis
The world of Natural Language Processing (NLP) technology took a leap with a recent study on the Russia-Ukraine conflict by Uddagiri Sirisha and Bolem Sai Chandana of the School of Computer Science and Engineering at Vellore Institute of Technology Andhra Pradesh ( VIT-AP) University in Amaravathi Andhra Pradesh, India.
The researchers developed a novel artificial intelligence model to analyze whether a piece of text is positive, negative or neutral in tone. This new model referred to as “ABSA-based ROBERTa-LSTM”, looks at not just the overall sentiment of a piece of text but also the sentiment towards specific aspects or entities mentioned in the text. The study took a pre-processed dataset of 484,221 tweets collected during April — May 2022 related to the Russia-Ukraine conflict and applied the model, resulting in a sentiment analysis accuracy of 94.7%, outperforming current techniques.
With millions of users sharing their thoughts and opinions on social media platforms like Twitter, sentiment analysis provides valuable data for researchers and analysts to understand public opinion, track trends and make predictions about political events, such as elections and protests. To be sure, there are limitations and challenges in depending on data-informed analysis, and sentiment analysis carries concerns surrounding potential biases in training data which could perpetuate existing societal inequalities, or limitations in contextual understanding, struggling in the nuances and subtleties of language, for instance, especially acute when generalizing models across dialects and varieties. However, recent breakthroughs such as ROBERTa-LSTM taking large datasets emerging from the Ukraine crisis could improve the accuracy and accessibility of sentiment analysis, making it possible for organizations to gain deeper insights into public opinion and to respond more effectively to changing sentiment.
Geospatial technologies for real-time monitoring of military activities
This forum has discussed the opportunities provided by open-source geospatial monitoring, and there have been several developments in this domain for early warning efforts. Cases include the increased availability of satellite imagery which allows the collection of datasets almost in real-time. Another is the integration of data from multiple sources, including social media, government reports and news articles which provides a more comprehensive picture of the situation on the ground.
For instance, the UN has monitored military activities through open-source satellite imagery. Using satellites that continuously gather thermal imagery globally, there have been efforts to utilize VIIRS thermal signatures to pinpoint military strikes not yet reported in the media. These signatures were captured several times a day by satellites and updated every 17 minutes. This data was then overlaid on medium-resolution satellite imagery and landcover masks to confirm that the signature was indeed related to ordnance activity in agricultural or irregular areas.
To determine civilian casualties, pilot projects in the UN combined open-source reporting, imagery analysis, and geospatial triangulation of publicly available street view images and mapping. They also conducted Open-Source analysis of news journals, academic and research institutions, think tanks, and published government data to enhance their geospatial analysis further and provide vetted estimates of casualties, equipment loss, and aid assessments throughout the region.
Takeaways
The integration of new technologies, such as Natural Language Processing (NLP) for sentiment analysis and geospatial data for predictive analytics, is transforming the way we understand and respond to modern day conflicts. NLP technologies like ABSA-based ROBERTa-LSTM, which combines machine and deep learning approaches, provide valuable insights into public sentiment through social media data analysis. The UN has been also Geospatial Team of the UN DPPA Innovation Cell, utilizing NASA satellites and various open-source reporting, providing geospatial analysis of conflict zones. These innovative solutions demonstrate the significance of technology in conflict analysis and highlight the potential for even more advanced solutions in the future.
However, it is important to note that NLP and geospatial technologies are far from the only technologies and techniques used in conflict analysis. There are many other technologies and methods, including traditional conflict analysis and reporting, that are essential for a comprehensive understanding and analysis of a conflict. It is crucial to adopt a multi-disciplinary and holistic approach to conflict analysis, utilizing all available resources and technologies to get a complete picture of the situation. This approach helps in making informed decisions and effective responses to conflicts.
About the author: Mykola Blyzniuk is a Public Information Assistant at the United Nations and was previously a Political Affairs Researcher with the UN DPPA Innovation Cell.
“Futuring Peace” is an online magazine published by the Innovation Cell of the United Nations Department of Political and Peacebuilding Affairs (UN DPPA). We explore cross-cutting approaches to conflict prevention, peacemaking and peacebuilding for a more peaceful future worldwide.
