Modeling and Mitigating Online Misinformation: a Suggested Blockchain Approach

Abstract

Misinformation propagation in online social networks has become an increasingly challenging problem. Although many studies exist to solve the problem computationally, a permanent and robust solution is yet to be discovered. In this study, we propose and demonstrate the effectiveness of a blockchain-machine learning hybrid approach for addressing the issue of misinformation in a crowdsourced environment. First, we motivate the use of blockchain for this problem by finding the crucial parts contributing to the dissemination of misinformation and how blockchain can be useful, respectively. Second, we propose a method that combines the wisdom of the crowd with a behavioral classifier to classify the news stories in terms of their truthfulness while reducing the effects of the actions performed by malicious users. We conduct experiments and simulations under different scenarios and attacks to assess the performance of this approach. Finally, we provide a case study involving a comparison with an existing approach using Twitter Birdwatch data. Our results suggest that this solution holds promise and warrants further investigation. CCS Concepts: • Computing methodologies → Neural networks; • Computer systems organization → Dependable and fault-tolerant systems and networks; • Information systems → Crowdsourcing.

Connecting the Dots Between Stance and Fake News Detection with Blockchain, Proof of Reputation, and the Hoeffding Bound

“…Our research aligns with the latter category of approaches. In this sequel, we mainly focus on two recent approaches, [11,13], that effectively combine crowdsourcing and blockchain technology to combat fake news.…”

“…The approach proposed in [13] introduces a decentralized environment where users post and vote on news stories, utilizing the benefits of collective intelligence for information validation. The proposed approach incorporates Lyapunov exponents and Shannon entropy as key metrics to ascertain the equilibrium of votes on a given story and to decide when to end the voting procedure.…”

“…The Story Classifier utilizes Long Short-Term Memory (LSTM) networks to predict the label of a story based on the collective behavior of users who have voted on it. While presenting several interesting ideas, the approach of [13] exhibits two notable shortcomings. Firstly, the reliance on black-box machine learning models might pose challenges for users in understanding how decisions are made.…”

“…In recent years, blockchain technology, with its scalability and authority-free nature [5], is being harnessed to combat the spread of fake news [6]. Existing blockchain-based approaches have primarily focused on tracking the provenance and modification history of news articles and associated images [7][8][9][10] or on assigning veracity labels to them [11][12][13]. Blockchain-based veracity labeling approaches typically incorporate voting mechanisms and/or machine learning models to assess the credibility of news.…”