Detection and Resolution of Rumours in Social Media
By Arkaitz Zubiaga, Ahmet Aker, Kalina Bontcheva, Maria Liakata, Rob Procter. 2017
891 citations recorded by the source corpus.
Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i.e., items of information that are unverified at the time of posting. At the same time, the openness of social media platforms provides opportunities to study how users share and discuss rumours, and to explore how to automatically assess their veracity, using natural language processing and data mining techniques. In this article, we introduce and discuss two types of rumours that circulate on social media: long-standing rumours that circulate for long periods of time, and newly emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages. We provide an overview of research into social media rumours with the ultimate goal of developing a rumour classification system that consists of four components: rumour detection, rumour tracking, rumour stance classification, and rumour veracity classification. We delve into the approaches presented in the scientific literature for the development of each of these four components. We summarise the efforts and achievements so far toward the development of rumour classification systems and conclude with suggestions for avenues for future research in social media mining for the detection and resolution of rumours.
Subfields: Communication, Sociology and Political Science, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Communication
In Sociology and Political Science
In Statistical and Nonlinear Physics
Citations in the corpus
- Automated Fact Checking: Task Formulations, Methods and Future Directions (2018, background): “While these are important factors to consider, a sentence can be true or false regardless of whether it is a rumor (Zubiaga et al., 2018).”
- Automated Fact-Checking for Assisting Human Fact-Checkers (2021, neutral): “, 2021], rumors [Zubiaga et al., 2018], factchecking [Thorne and Vlachos, 2018; Kotonya and Toni, 2020], factuality [Li et al.”
- Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks (2020, background): “In some cases, the label y i is one of the four finer-grained classes { N, F, T, U } (i.e., Non-rumor, False Rumor, True Rumor, and Unverified Rumor) (Ma, Gao, and Wong 2017; Zubiaga et al. 2018).”
- An exploratory study of COVID-19 misinformation on Twitter (2020, neutral): “The term fake news is widely used to refer to inaccurate information [100] or more specifically to “fabricated information that mimics news media content in form but not in organisational process or intent” [40].”
- Combating Fake News (2019, methodology): “Zubiaga et al. 2018 note that it is possible to differentiate user responses by their stance, wherein the most commonly used categorization uses the following four types, namely, supporting, denying, querying and commenting (which can be neutral or unrelated).”
- The spread of low-credibility content by social bots (2017, neutral): “Specific systems have been proposed to detect rumors [66].”
- False Information on Web and Social Media: A Survey (2018, background): “news in social media [90, 120], the current survey broadly focuses on three types of false information on the web and social media—fake reviews in e-commerce platforms, hoaxes on collaborative platforms, and fake news in social media.”
- A Survey on Natural Language Processing for Fake News Detection (2018, background): “A recent survey (Zubiaga et al., 2018) de-fines rumor detection as separating personal statements into rumor or non-rumor, where rumor is defined as a statement consisting of unverified pieces of information at the time of posting.”
- Knowledge Conflicts for LLMs: A Survey (2024, background): “Previous research has shown that LMs can be significantly influenced by misinformation or outdated information within a specific context (Zhang and Choi, 2021; Du et al., 2022b).”
- Deep learning for deepfakes creation and detection: A survey (2019, background): “The spread of these fake contents is also quicker thanks to the development of social media platforms [166].”
- SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours (2017, background): “Prior work in the area has found the task difficult, compounded by the variety present in language use between different stories (Lukasik et al., 2015; Zubiaga et al., 2017).”
- Rumor Detection on Twitter with Tree-structured Recursive Neural Networks (2018, background): “Analysis has generally found that Twitter could “self-correct” some inaccurate information as users share opinions, conjectures and evidences (Zubiaga et al., 2017).”
- Cross-modal Ambiguity Learning for Multimodal Fake News Detection (2022, background): “While people enjoy the convenience of online social media, the lack of systematic efforts to verify the credibility of online posts has led to the wide and fast spread of fake news across social platforms [19, 38, 40].”