On GATE, Text and Social Media Analysis, and Detecting Misinformation Online

2026-01-05 · Source: On GATE, Text and Social Media Analysis, and Detecting Misinformation Online · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, medium

Summary

Daniel Kansaon, a PhD student from Brazil specializing in data science and Natural Language Processing, completed a three-month research visit (September–December) at the University of Sheffield through the ATRIUM programme. His doctoral research focuses on analyzing large-scale online communication on WhatsApp and Telegram, specifically investigating coordinated campaigns, harmful attacks, and political polarization, with a recent emphasis on fear-based and othering narratives. During his visit, Kansaon deepened his understanding of "othering" and developed the first dataset specifically for identifying othering language in messaging platforms. This dataset is crucial for analyzing fear-related communication and training computational models. He also integrated into university life, playing football with the university team and attending professional sports events, and experienced Sheffield's Christmas season.

Key takeaway

For NLP Engineers and AI Scientists working on social media analysis, consider applying for transnational access schemes like ATRIUM to gain focused research time and access to specialized infrastructure. Your participation in such programs can accelerate dataset creation and model development for complex tasks like identifying "othering" narratives, directly impacting the quality and scope of your research outputs. Actively engaging with host researchers will also refine your methodological approaches.

Key insights

Focused research visits can significantly advance doctoral work and foster valuable academic collaborations.

Principles

• Daily interaction enhances research outcomes.
• Dataset creation is central to computational linguistics.
• Interdisciplinary feedback refines methodological design.

Method

The researcher deepened understanding of "othering," then created a unique dataset for othering language in messaging platforms, refining annotation strategies and data quality based on group feedback.

In practice

• Seek out research visits for focused work.
• Engage with local academic communities.
• Develop specialized datasets for niche NLP tasks.

Topics

• Natural Language Processing
• Online Communication Analysis
• Political Polarization
• Othering Language Dataset
• Computational Models

Best for: NLP Engineer, AI Scientist, AI Student, AI Researcher, Research Scientist

Related on AIssential

• From Comments to Trends: Studi NLP dan Computational Linguistics dalam Mendeteksi Topik Viral dari… — NLP and computational linguistics are crucial for detecting social media trends from vast, informal, and diverse comment data.
• Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach — Computational methods can reveal hidden patterns in parliamentary discourse beyond voting records.
• Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest — Modern LLMs were systematically evaluated across key social media analytics tasks using a Twitter (X) dataset.
• Exploring NLP Applications in Food Research: my ATRIUM TNA visit to the GATE group — NLP tools significantly enhance social media data analysis for consumer behavior and food research.
• 169  |  Data Conversations with Vidya Setlur — Natural language processing significantly enhances data visualization by enabling intuitive interaction and deeper semantic understanding.
• When his hobbies went on hiatus, this Kaggler made fighting COVID-19 with data his mission | A… — Combining sentence embeddings with a custom BERT QA model and study design classification enhances medical document search and information extraction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by On GATE, Text and Social Media Analysis, and Detecting Misinformation Online.