Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Health Misinformation Detection in Web Content via Web2Vec: A Structural-, Content-based, and Context-aware Approach based on Web2Vec

Rishabh Upadhyay, Gabriella Pasi, Marco Viviani

TL;DR

The paper tackles health misinformation in Web pages and argues for a domain-aware credibility assessment beyond traditional text features. It adapts Web2Vec to health pages by incorporating domain vocabulary and link-structure signals, using a CNN-BiLSTM with an attention mechanism to fuse DOM, content, and link embeddings for page-level classification. Evaluations on Microsoft Credibility (health subset), Medical Web Reliability Corpus, and CLEF eHealth 2020 Task-2 datasets show that Cred-W2V variants, especially with PubMed initialization and link/domain representations, outperform handcrafted-feature baselines and standard Web2Vec. The work demonstrates that semantic and context-aware representations improve health information credibility detection, with potential to extend domain knowledge integration in future work.

Abstract

In recent years, we have witnessed the proliferation of large amounts of online content generated directly by users with virtually no form of external control, leading to the possible spread of misinformation. The search for effective solutions to this problem is still ongoing, and covers different areas of application, from opinion spam to fake news detection. A more recently investigated scenario, despite the serious risks that incurring disinformation could entail, is that of the online dissemination of health information. Early approaches in this area focused primarily on user-based studies applied to Web page content. More recently, automated approaches have been developed for both Web pages and social media content, particularly with the advent of the COVID-19 pandemic. These approaches are primarily based on handcrafted features extracted from online content in association with Machine Learning. In this scenario, we focus on Web page content, where there is still room for research to study structural-, content- and context-based features to assess the credibility of Web pages. Therefore, this work aims to study the effectiveness of such features in association with a deep learning model, starting from an embedded representation of Web pages that has been recently proposed in the context of phishing Web page detection, i.e., Web2Vec.

Health Misinformation Detection in Web Content via Web2Vec: A Structural-, Content-based, and Context-aware Approach based on Web2Vec

TL;DR

The paper tackles health misinformation in Web pages and argues for a domain-aware credibility assessment beyond traditional text features. It adapts Web2Vec to health pages by incorporating domain vocabulary and link-structure signals, using a CNN-BiLSTM with an attention mechanism to fuse DOM, content, and link embeddings for page-level classification. Evaluations on Microsoft Credibility (health subset), Medical Web Reliability Corpus, and CLEF eHealth 2020 Task-2 datasets show that Cred-W2V variants, especially with PubMed initialization and link/domain representations, outperform handcrafted-feature baselines and standard Web2Vec. The work demonstrates that semantic and context-aware representations improve health information credibility detection, with potential to extend domain knowledge integration in future work.

Abstract

In recent years, we have witnessed the proliferation of large amounts of online content generated directly by users with virtually no form of external control, leading to the possible spread of misinformation. The search for effective solutions to this problem is still ongoing, and covers different areas of application, from opinion spam to fake news detection. A more recently investigated scenario, despite the serious risks that incurring disinformation could entail, is that of the online dissemination of health information. Early approaches in this area focused primarily on user-based studies applied to Web page content. More recently, automated approaches have been developed for both Web pages and social media content, particularly with the advent of the COVID-19 pandemic. These approaches are primarily based on handcrafted features extracted from online content in association with Machine Learning. In this scenario, we focus on Web page content, where there is still room for research to study structural-, content- and context-based features to assess the credibility of Web pages. Therefore, this work aims to study the effectiveness of such features in association with a deep learning model, starting from an embedded representation of Web pages that has been recently proposed in the context of phishing Web page detection, i.e., Web2Vec.
Paper Structure (23 sections, 2 equations, 2 figures, 1 table)

This paper contains 23 sections, 2 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Interactive-based Approaches
  4. Automated Approaches
  5. A Web2Vec-based Solution for Health Misinformation Detection
  6. Data Parsing
  7. DOM Corpus.
  8. Content Corpus.
  9. Link Corpus.
  10. Data Representation
  11. Feature Extraction
  12. CNN.
  13. BiLSTM.
  14. Attention Layer.
  15. Web Page Classification
  16. ...and 8 more sections

Figures (2)

  • Figure 1: Construction of the word-level corpus for links.
  • Figure 2: The word-level embedding phase for the content.