Fake Advertisements Detection Using Automated Multimodal Learning: A Case Study for Vietnamese Real Estate Data

2025-01-18

AI Summary

To address the proliferation of fraudulent property advertisements on Vietnamese real estate platforms—posing serious risks to users’ financial security and platform credibility—this paper proposes FADAML, an end-to-end multimodal automated machine learning framework. FADAML innovatively fuses Vietnamese-language textual content, property images, and structured metadata via a lightweight cross-modal alignment network, and integrates AutoML-driven hyperparameter optimization to enable fully automated, localization-aware modeling. Evaluated on a real-world Vietnamese property dataset, FADAML achieves 91.5% accuracy in detecting fraudulent advertisements, significantly outperforming three state-of-the-art fake news detection baselines. This work establishes a reusable technical paradigm and provides empirical validation for multimodal disinformation detection in low-resource language settings.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Multimodal Learning
• Application Domains: Misinformation & Fake News

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Mitigating misinformation and disinformation

Abstract

The popularity of e-commerce has given rise to fake advertisements that can expose users to financial and data risks while damaging the reputation of these e-commerce platforms. For these reasons, detecting and removing such fake advertisements are important for the success of e-commerce websites. In this paper, we propose FADAML, a novel end-to-end machine learning system to detect and filter out fake online advertisements. Our system combines techniques in multimodal machine learning and automated machine learning to achieve a high detection rate. As a case study, we apply FADAML to detect fake advertisements on popular Vietnamese real estate websites. Our experiments show that we can achieve 91.5% detection accuracy, which significantly outperforms three different state-of-the-art fake news detection systems.

Problem

• Fake Advertisement Detection
• Online Shopping Security
• Vietnamese Real Estate

Innovation

• FADAML
• Machine Learning
• Fake Advertisement Detection