Analyzing the Spread of Misinformation on Social Networks: A Process and Software Architecture for Detection and Analysis

Abstract

The rapid dissemination of misinformation on social networks, particularly during public health crises like the COVID-19 pandemic, has become a significant concern. This study investigates the spread of misinformation on social network data using social network analysis (SNA) metrics, and more generally by using well known network science metrics. Moreover, we propose a process design that utilizes social network data from Twitter, to analyze the involvement of non-trusted accounts in spreading misinformation supported by a proof-of-concept prototype. The proposed prototype includes modules for data collection, data preprocessing, network creation, centrality calculation, community detection, and misinformation spreading analysis. We conducted an experimental study on a COVID-19-related Twitter dataset using the modules. The results demonstrate the effectiveness of our approach and process steps, and provides valuable insight into the application of network science metrics on social network data for analysing various influence-parameters in misinformation spreading.

A Centrality Metrics Approach to Analyzing Temporal Spread Patterns of Misinformation in Social Networks

“…In this study, we utilize the modules of a software architecture that we have developed and are still working on, for an analysis process and utilize social network data, including replies, mentions, and retweets, in order to analyze misinformation spread [8]. Our process consists of several modules: Data Collection, Data Preprocessing, Data Annotation, Network Creation, Centrality Calculator, Community Detection, and Misinformation Detection.…”

“…Key Features Automated Detection Algorithms [13] Utilizes machine learning for detection Manual Annotation and Verification [3] Relies on human annotators for accuracy Network Analysis and Influence Metrics [23] Identifies influential nodes and patterns Temporal Analysis and Time-Series Models [2] [8] Examines patterns over time Behavioral Analysis of Users [20] Studies user engagement and behavior Geospatial and Demographic Considerations [9] Accounts for regional and demographic variations Cross-Platform Analysis [18] Explores misinformation across platforms Intervention Strategies and Countermeasures [4] Proposes methods to mitigate misinformation Ethical Considerations and Privacy [34] Addresses ethical and privacy concerns Scientific examinations have extensively explored the complex patterns of online disinformation, encompassing not only the dissemination of inaccurate information but also the psychological and sociological dimensions associated with its generation and consumption [39] [36]. The authors of the study examine the complex characteristics of misinformation, delving into the motivations and techniques employed by those who spread false information, as well as the weaknesses and mental preconceptions that render individuals vulnerable to deception [28].…”

“…Through an extensive analysis of a large dataset, we shed light on the significance of various centrality metrics. The initial version of this research was published in [8] as a conference paper with a focus on conducting longitudinal analysis on misinformation dissemination using centrality metrics that primarily evaluate only the network's topology and connectivity. This manuscript extends our previous research by conducting an extensive longitudinal analysis on the spread of misinformation dynamics and influence properties on it, taking into account not only the network's topology and connectivitybased centrality metrics but also the two other categories of centrality metrics: centrality metrics that consider factors such as the importance of connections, information flow, indirect influences, and centrality metrics that measure the importance of a node in a network based on its popularity/prestige.…”