[TMP-023] Building TRUST in social media: assessing the Trustworthiness of public Information on Ukrainian Migration to Europe
The microproject develops an AI-based solution to assess social media trustworthiness, addressing misinformation, legal, and ethical challenges.
Currently, most government, commercial, and non-profit organizations use social media to communicate with citizens and share information. Social media enhances citizen engagement, trust, and transparency while supporting freedom of speech. However, governments must address risks like the spread of misinformation, which is prevalent on social media and undermines trust.
While government and public officials’ accounts aim to provide reliable and timely information, failure to maintain effective two-way communication, update content, or address comments may push citizens to seek information elsewhere. This increases the risk of misinformation, threatening trust, privacy, and data security. Misinformation can also deepen social divisions, exacerbate inequalities, and manipulate opinions.
Our microproject develops an AI-based approach to assess social media information trustworthiness using unsupervised machine learning, text analytics, and event argument extraction. We focus on Polish, Ukrainian, and English content related to migration caused by the Russian invasion of Ukraine. Migration issues are highly debated on social media and prone to disinformation. Associated challenges include ethical concerns, legal barriers, and social security issues for migrants.
This AI-based solution will help governments understand citizens’ information needs, identify causes of misinformation, and establish guidelines to monitor social media while ensuring compliance with ethical, legal, and societal principles.
Using a text analytics approach such as BERTopic topic modeling, we analyzed text messages published on Telegram channels from February 2022 to September 2023, revealing 12 challenges facing Ukrainian migrants. Furthermore, our study delves into these challenges distribution across 6 major European countries with significant migrant populations, providing insights into regional differences. Additionally, temporal changes in 8 narrative themes in discussions of Ukrainian migration, extracted from official government websites, were examined. Together, this research contributes (1) to demonstrating how analytics-driven methodology can potentially be used to extract in-depth knowledge from textual data freely available on social media; and (2) to a deeper understanding of the various issues affecting the adaptation of Ukrainian migrants in European countries. The study also provides recommendations to improve programs and policies to better.
Tangible Outcomes
- Nina Khairova, Nina Rizun, Charalampos Alexopoulos, Magdalena Ciesielska, Arsenii Lukashevskyi, Ivan Redozub/Understanding the Ukrainian Migrants Challenges in the EU: A Topic Modeling Approach/Proceedings of the 25th Annual International Conference on Digital Government Research, 2024, 196-205 p. https://dl.acm.org/doi/abs/10.1145/3657054.3657252
- The SOMTUME dataset contains textual information gathered from social media and news sites, comprising two segments: Trustworthiness Information Content (TIC) and Uncertain Information Content (UIC). The texts pertain to the migration of Ukrainians to the European Union from February 2022, to August 2023. https://github.com/ninakhairova/SOMTUME
- The results “Understanding the Ukrainian Migrants’ Challenges in the EU: A Topic Modeling Approach” of the microproject were presented at the 25th Annual International Conference on Digital Government Research (dg.o 2024), held from June 11–14, 2024, at National Taiwan University in Taipei, Taiwan. https://dgsociety.org/dgo-2024/program/
Partners:
- Umea University, Nina Khairova, nina.khairova@umu.se
- Gdansk University of Technology, Nina Rizun, nina.rizun@pg.edu.pl
- University of the Aegean, Charalampos Alexopoulos, alexop@aegean.g