Exploring NLP Applications in Food Research: my ATRIUM TNA visit to the GATE group

2025-02-03 · Source: On GATE, Text and Social Media Analysis, and Detecting Misinformation Online · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, short

Summary

Tenia Panagiotou, a postdoctoral researcher from the University of the Aegean, visited the GATE group at the University of Sheffield from January 20–31, 2025, through the ATRIUM project's TNA scheme. Her visit focused on exploring Natural Language Processing (NLP) tools for analyzing food consumption-related phenomena and consumer expression on social media. Panagiotou utilized GATE Cloud tools, including a Topic Extractor for social media hashtags to generate hierarchical concept graphs and the TwitIE Named Entity Recognizer to identify individual words within multiword hashtags. She also investigated sentiment analysis, opinion mining, user classification, and the Multilingual Persuasion Technique Classifier. The visit provided guidance on optimizing ChatGPT and Large Language Models for consistent responses and clustering social media hashtags.

Key takeaway

For AI Scientists analyzing social media data in specialized domains like food research, integrating advanced NLP tools is crucial. You should explore Named Entity Recognition (NER) for complex hashtag parsing and consider sentiment analysis and persuasion technique classifiers to extract deeper consumer insights. Optimizing LLMs for consistent responses can further streamline your analytical workflows.

Key insights

NLP tools significantly enhance social media data analysis for consumer behavior and food research.

Principles

• Multiword hashtags require specialized entity recognition.
• LLMs can be optimized for response consistency.

Method

The GATE framework offers tools like Topic Extractor for concept graphs and TwitIE NER for multiword hashtag parsing, alongside sentiment analysis and multilingual persuasion classification.

In practice

• Use Topic Extractor for hierarchical concept graphs.
• Apply TwitIE NER to resolve multiword hashtag challenges.

Topics

• Natural Language Processing
• Social Media Analysis
• Named Entity Recognition
• Food Research
• Large Language Models

Best for: AI Scientist, AI Researcher, Research Scientist, Domain Expert

Related on AIssential

• On GATE, Text and Social Media Analysis, and Detecting Misinformation Online — A multi-layer analytical pipeline effectively extracts and categorizes digital identity aspects of agrifood products from online discourse.
• How to Leverage NER and Advanced NLP Techniques for Life Sciences — NER and advanced NLP are essential for structuring and interpreting the vast unstructured text data in Life Sciences.
• 5 Most Popular Use Cases of AI NLP Technology — Deep learning-powered NLP enables machines to understand and generate human language, driving widespread applications and market growth.
• Data Augmentation for Historical NER: A Systematic Comparison of Lexical and LLM-based Approaches — This paper systematically compares lexical and LLM-based data augmentation for Historical Named Entity Recognition.
• McKenzie Marshall: NLP in Asset Management (Barings) — Effective NLP in asset management augments human analysis by precisely identifying and contextualizing company-specific information from diverse text sources.
• A Beginner’s Guide to NLP Token Classification: NER, POS Tagging, Chunking, and BERT — Token classification, including NER, POS tagging, and chunking, is fundamental for machines to understand human language.

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.