Lexical and Syntactic Characterization of Fake News in Portuguese Produced by Humans and by Machines

2026-04-12 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Natural Language Processing · Depth: Expert, quick

Summary

A study analyzed Portuguese fake news from human and machine sources, utilizing the Fake.br and FakeTrueBR corpora, which were augmented with automatically generated fake news. The research focused on lexically and syntactically characterizing these texts to differentiate between human and machine authorship. Key findings indicate that machine-generated fake news contains significantly longer words, a higher frequency of adjectival modifiers, and reduced syntactic diversity, even while employing more syntactic rules per sentence. Conversely, human-produced fake news demonstrated greater stylistic variability across all examined lexical and syntactic dimensions, highlighting distinct patterns in how each source constructs deceptive content.

Key takeaway

For NLP engineers developing fake news detection systems for Portuguese, your models should prioritize features related to word length, adjectival modifier usage, and syntactic diversity. Incorporating these specific lexical and syntactic characteristics can significantly improve the accuracy of differentiating between human and machine-generated deceptive content, especially given the observed stylistic differences.

Key insights

Machine-generated Portuguese fake news shows distinct lexical and syntactic patterns compared to human-produced content.

Principles

• Machine texts use longer words.
• Human texts show greater stylistic variability.

Method

The study expanded Fake.br and FakeTrueBR corpora with automatically generated fake news, then performed lexical and syntactic characterization to differentiate human from machine authorship.

In practice

• Analyze word length for machine detection.
• Check adjectival modifier frequency.
• Assess syntactic diversity in content.

Topics

• Fake News Detection
• Generative AI
• Lexical Characterization
• Syntactic Characterization
• Portuguese Language

Best for: AI Scientist, NLP Engineer, Research Scientist

Related on AIssential

• Exploring Knowledge Graphs for Automatic Fake News Detection in Portuguese — Knowledge Graphs offer an explainable method for automated fake news detection by modeling news as factual events.
• Gendered Stylistic Variation in Brazilian Portuguese Google Play Reviews: A Large-Scale Study — Gender-associated stylistic differences exist in Brazilian Portuguese Google Play reviews, particularly in paralinguistic expressivity.
• An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect — A hybrid framework combining transformer embeddings with classical classifiers enables effective rumour detection in low-resource Algerian dialect.
• Do we really need to detect LLM-generated text? — Masked word prediction by LLMs can distinguish AI-generated text from human text without explicit training.
• 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.
• 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.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.