We introduce SCRum-9, a multilingual dataset for Rumour Stance Classification, containing 7,516 tweet-reply pairs from X. SCRum-9 goes beyond existing stance classification datasets by covering more languages (9), linking examples to more fact-checked claims (2.1k), and including complex annotations from multiple annotators to account for intra- and inter-annotator variability. Annotations were made by at least three native speakers per language, totalling around 405 hours of annotation and 8,150 dollars in compensation. Experiments on SCRum-9 show that it is a challenging benchmark for both state-of-the-art LLMs (e.g. Deepseek) as well as fine-tuned pre-trained models, motivating future work in this area.
Rumours in online social media pose significant risks to modern society, motivating the need for better understanding of how they develop. We focus specifically on the interface between emotion and rumours in threaded discourses, building on the surprisingly sparse literature on the topic which has largely focused on single aspect of emotions within the original rumour posts themselves, and largely overlooked the comparative differences between rumours and non-rumours. In this work, we take one step further to provide a comprehensive analytical emotion framework with multi-aspect emotion detection, contrasting rumour and non-rumour threads and provide both correlation and causal analysis of emotions. We applied our framework on existing widely-used rumour datasets to further understand the emotion dynamics in online social media threads. Our framework reveals that rumours trigger more negative emotions (e.g., anger, fear, pessimism), while non-rumours evoke more positive ones. Emotions are contagious, rumours spread negativity, non-rumours spread positivity. Causal analysis shows surprise bridges rumours and other emotions; pessimism comes from sadness and fear, while optimism arises from joy and love.
The widespread use of social media has accelerated the dissemination of information, but it has also facilitated the spread of harmful rumours, which can disrupt economies, influence political outcomes, and exacerbate public health crises, such as the COVID-19 pandemic. While Graph Neural Network (GNN)-based approaches have shown significant promise in automated rumour detection, they often lack transparency, making their predictions difficult to interpret. Existing graph explainability techniques fall short in addressing the unique challenges posed by the dependencies among feature dimensions in high-dimensional text embeddings used in GNN-based models. In this paper, we introduce Contrastive Token Layerwise Relevance Propagation (CT-LRP), a novel framework designed to enhance the explainability of GNN-based rumour detection. CT-LRP extends current graph explainability methods by providing token-level explanations that offer greater granularity and interpretability. We evaluate the effectiveness of CT-LRP across multiple GNN models trained on three publicly available rumour detection datasets, demonstrating that it consistently produces high-fidelity, meaningful explanations, paving the way for more robust and trustworthy rumour detection systems.
We investigate the challenge of generating adversarial examples to test the robustness of text classification algorithms detecting low-credibility content, including propaganda, false claims, rumours and hyperpartisan news. We focus on simulation of content moderation by setting realistic limits on the number of queries an attacker is allowed to attempt. Within our solution (TREPAT), initial rephrasings are generated by large language models with prompts inspired by meaning-preserving NLP tasks, e.g. text simplification and style transfer. Subsequently, these modifications are decomposed into small changes, applied through beam search procedure until the victim classifier changes its decision. The evaluation confirms the superiority of our approach in the constrained scenario, especially in case of long input text (news articles), where exhaustive search is not feasible.
Conversational prompt-engineering-based large language models (LLMs) have enabled targeted control over the output creation, enhancing versatility, adaptability and adhoc retrieval. From another perspective, digital misinformation has reached alarming levels. The anonymity, availability and reach of social media offer fertile ground for rumours to propagate. This work proposes to leverage the advancement of prompting-dependent LLMs to combat misinformation by extending the research efforts of the RumourEval task on its Twitter dataset. To the end, we employ two prompting-based LLM variants (GPT-3.5-turbo and GPT-4) to extend the two RumourEval subtasks: (1) veracity prediction, and (2) stance classification. For veracity prediction, three classifications schemes are experimented per GPT variant. Each scheme is tested in zero-, one- and few-shot settings. Our best results outperform the precedent ones by a substantial margin. For stance classification, prompting-based-approaches show comparable performance to prior results, with no improvement over finetuning methods. Rumour stance subtask is also extended beyond the original setting to allow multiclass classification. All of the generated predictions for both subtasks are equipped with confidence scores determining their trustworthiness degree according to the LLM, and post-hoc justifications for explainability and interpretability purposes. Our primary aim is AI for social good.
The reasoning capabilities of LLMs are currently hotly debated. We examine the issue from the perspective of claim/rumour verification. We propose the first logical reasoning framework designed to break down any claim or rumour paired with evidence into the atomic reasoning steps necessary for verification. Based on our framework, we curate two annotated collections of such claim/evidence pairs: a synthetic dataset from Wikipedia and a real-world set stemming from rumours circulating on Twitter. We use them to evaluate the reasoning capabilities of GPT-3.5-Turbo and GPT-4 (hereinafter referred to as ChatGPT) within the context of our framework, providing a thorough analysis. Our results show that ChatGPT struggles in abductive reasoning, although this can be somewhat mitigated by using manual Chain of Thought (CoT) as opposed to Zero-Shot (ZS) and ZS CoT approaches. Our study contributes to the growing body of research suggesting that ChatGPT's reasoning processes are unlikely to mirror human-like reasoning, and that LLMs need to be more rigorously evaluated to distinguish between hype and actual capabilities, especially in high-stakes real-world tasks such as claim verification.
We apply causal mediation analysis to explain the decision-making process of neural models for rumour detection on Twitter. Interventions at the input and network level reveal the causal impacts of tweets and words in the model output. We find that our approach CMA-R -- Causal Mediation Analysis for Rumour detection -- identifies salient tweets that explain model predictions and show strong agreement with human judgements for critical tweets determining the truthfulness of stories. CMA-R can further highlight causally impactful words in the salient tweets, providing another layer of interpretability and transparency into these blackbox rumour detection systems. Code is available at: https://github.com/ltian678/cma-r.
The abundance of information on social media has increased the necessity of accurate real-time rumour detection. Manual techniques of identifying and verifying fake news generated by AI tools are impracticable and time-consuming given the enormous volume of information generated every day. This has sparked an increase in interest in creating automated systems to find fake news on the Internet. The studies in this research demonstrate that the BERT and RobertA models with fine-tuning had the best success in detecting AI generated news. With a score of 98%, tweaked RobertA in particular showed excellent precision. In conclusion, this study has shown that neural networks can be used to identify bogus news AI generation news created by ChatGPT. The RobertA and BERT models' excellent performance indicates that these models can play a critical role in the fight against misinformation.
In recent years people have become increasingly reliant on social media to read news and get information, and some social media users post unsubstantiated information to gain attention. Such information is known as rumours. Nowadays, rumour detection is receiving a growing amount of attention because of the pandemic of the New Coronavirus, which has led to a large number of rumours being spread. In this paper, a Natural Language Processing (NLP) system is built to predict rumours. The best model is applied to the COVID-19 tweets to conduct exploratory data analysis. The contribution of this study is twofold: (1) to compare rumours and facts using state-of-the-art natural language processing models in two dimensions: language structure and propagation route. (2) An analysis of how rumours differ from facts in terms of their lexical use and the emotions they imply. This study shows that linguistic structure is a better feature to distinguish rumours from facts compared to the propagation path. In addition, rumour tweets contain more vocabulary related to politics and negative emotions.
Text classification methods have been widely investigated as a way to detect content of low credibility: fake news, social media bots, propaganda, etc. Quite accurate models (likely based on deep neural networks) help in moderating public electronic platforms and often cause content creators to face rejection of their submissions or removal of already published texts. Having the incentive to evade further detection, content creators try to come up with a slightly modified version of the text (known as an attack with an adversarial example) that exploit the weaknesses of classifiers and result in a different output. Here we systematically test the robustness of common text classifiers against available attacking techniques and discover that, indeed, meaning-preserving changes in input text can mislead the models. The approaches we test focus on finding vulnerable spans in text and replacing individual characters or words, taking into account the similarity between the original and replacement content. We also introduce BODEGA: a benchmark for testing both victim models and attack methods on four misinformation detection tasks in an evaluation framework designed to simulate real use-cases of content moderation. The attacked tasks include (1) fact checking and detection of (2) hyperpartisan news, (3) propaganda and (4) rumours. Our experimental results show that modern large language models are often more vulnerable to attacks than previous, smaller solutions, e.g. attacks on GEMMA being up to 27\% more successful than those on BERT. Finally, we manually analyse a subset adversarial examples and check what kinds of modifications are used in successful attacks.
In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection. Our fact-checking module, which is supported by novel natural language inference methods with a self-attention network, outperforms state-of-the-art approaches. It is also able to give automated veracity assessment and ranked supporting evidence with the stance towards the claim to be checked. In addition, PANACEA adapts the bi-directional graph convolutional networks model, which is able to detect rumours based on comment networks of related tweets, instead of relying on the knowledge base. This rumour detection module assists by warning the users in the early stages when a knowledge base may not be available.
Recently, online social media has become a primary source for new information and misinformation or rumours. In the absence of an automatic rumour detection system the propagation of rumours has increased manifold leading to serious societal damages. In this work, we propose a novel method for building automatic rumour detection system by focusing on oversampling to alleviating the fundamental challenges of class imbalance in rumour detection task. Our oversampling method relies on contextualised data augmentation to generate synthetic samples for underrepresented classes in the dataset. The key idea exploits selection of tweets in a thread for augmentation which can be achieved by introducing a non-random selection criteria to focus the augmentation process on relevant tweets. Furthermore, we propose two graph neural networks(GNN) to model non-linear conversations on a thread. To enhance the tweet representations in our method we employed a custom feature selection technique based on state-of-the-art BERTweet model. Experiments of three publicly available datasets confirm that 1) our GNN models outperform the the current state-of-the-art classifiers by more than 20%(F1-score); 2) our oversampling technique increases the model performance by more than 9%;(F1-score) 3) focusing on relevant tweets for data augmentation via non-random selection criteria can further improve the results; and 4) our method has superior capabilities to detect rumours at very early stage.
Social networking sites, blogs, and online articles are instant sources of news for internet users globally. However, in the absence of strict regulations mandating the genuineness of every text on social media, it is probable that some of these texts are fake news or rumours. Their deceptive nature and ability to propagate instantly can have an adverse effect on society. This necessitates the need for more effective detection of fake news and rumours on the web. In this work, we annotate four fake news detection and rumour detection datasets with their emotion class labels using transfer learning. We show the correlation between the legitimacy of a text with its intrinsic emotion for fake news and rumour detection, and prove that even within the same emotion class, fake and real news are often represented differently, which can be used for improved feature extraction. Based on this, we propose a multi-task framework for fake news and rumour detection, predicting both the emotion and legitimacy of the text. We train a variety of deep learning models in single-task and multi-task settings for a more comprehensive comparison. We further analyze the performance of our multi-task approach for fake news detection in cross-domain settings to verify its efficacy for better generalization across datasets, and to verify that emotions act as a domain-independent feature. Experimental results verify that our multi-task models consistently outperform their single-task counterparts in terms of accuracy, precision, recall, and F1 score, both for in-domain and cross-domain settings. We also qualitatively analyze the difference in performance in single-task and multi-task learning models.
Social media has become the fulcrum of all forms of communication. Classifying social texts such as fake news, rumour, sarcasm, etc. has gained significant attention. The surface-level signals expressed by a social-text itself may not be adequate for such tasks; therefore, recent methods attempted to incorporate other intrinsic signals such as user behavior and the underlying graph structure. Oftentimes, the `public wisdom' expressed through the comments/replies to a social-text acts as a surrogate of crowd-sourced view and may provide us with complementary signals. State-of-the-art methods on social-text classification tend to ignore such a rich hierarchical signal. Here, we propose Hyphen, a discourse-aware hyperbolic spectral co-attention network. Hyphen is a fusion of hyperbolic graph representation learning with a novel Fourier co-attention mechanism in an attempt to generalise the social-text classification tasks by incorporating public discourse. We parse public discourse as an Abstract Meaning Representation (AMR) graph and use the powerful hyperbolic geometric representation to model graphs with hierarchical structure. Finally, we equip it with a novel Fourier co-attention mechanism to capture the correlation between the source post and public discourse. Extensive experiments on four different social-text classification tasks, namely detecting fake news, hate speech, rumour, and sarcasm, show that Hyphen generalises well, and achieves state-of-the-art results on ten benchmark datasets. We also employ a sentence-level fact-checked and annotated dataset to evaluate how Hyphen is capable of producing explanations as analogous evidence to the final prediction.
The propagation of rumours on social media poses an important threat to societies, so that various techniques for rumour detection have been proposed recently. Yet, existing work focuses on \emph{what} entities constitute a rumour, but provides little support to understand \emph{why} the entities have been classified as such. This prevents an effective evaluation of the detected rumours as well as the design of countermeasures. In this work, we argue that explanations for detected rumours may be given in terms of examples of related rumours detected in the past. A diverse set of similar rumours helps users to generalize, i.e., to understand the properties that govern the detection of rumours. Since the spread of rumours in social media is commonly modelled using feature-annotated graphs, we propose a query-by-example approach that, given a rumour graph, extracts the $k$ most similar and diverse subgraphs from past rumours. The challenge is that all of the computations require fast assessment of similarities between graphs. To achieve an efficient and adaptive realization of the approach in a streaming setting, we present a novel graph representation learning technique and report on implementation considerations. Our evaluation experiments show that our approach outperforms baseline techniques in delivering meaningful explanations for various rumour propagation behaviours.
Today's social networks continuously generate massive streams of data, which provide a valuable starting point for the detection of rumours as soon as they start to propagate. However, rumour detection faces tight latency bounds, which cannot be met by contemporary algorithms, given the sheer volume of high-velocity streaming data emitted by social networks. Hence, in this paper, we argue for best-effort rumour detection that detects most rumours quickly rather than all rumours with a high delay. To this end, we combine techniques for efficient, graph-based matching of rumour patterns with effective load shedding that discards some of the input data while minimising the loss in accuracy. Experiments with large-scale real-world datasets illustrate the robustness of our approach in terms of runtime performance and detection accuracy under diverse streaming conditions.
It is challenging to control the quality of online information due to the lack of supervision over all the information posted online. Manual checking is almost impossible given the vast number of posts made on online media and how quickly they spread. Therefore, there is a need for automated rumour detection techniques to limit the adverse effects of spreading misinformation. Previous studies mainly focused on finding and extracting the significant features of text data. However, extracting features is time-consuming and not a highly effective process. This study proposes the BERT- based pre-trained language models to encode text data into vectors and utilise neural network models to classify these vectors to detect misinformation. Furthermore, different language models (LM) ' performance with different trainable parameters was compared. The proposed technique is tested on different short and long text datasets. The result of the proposed technique has been compared with the state-of-the-art techniques on the same datasets. The results show that the proposed technique performs better than the state-of-the-art techniques. We also tested the proposed technique by combining the datasets. The results demonstrated that the large data training and testing size considerably improves the technique's performance.
Vital node identification is the problem of finding nodes of highest importance in complex networks. This problem has crucial applications in various contexts such as viral marketing or controlling the propagation of virus or rumours in real-world networks. Existing approaches for vital node identification mainly focus on capturing the importance of a node through a mathematical expression which directly relates structural properties of the node to its vitality. Although these heuristic approaches have achieved good performance in practice, they have weak adaptability, and their performance is limited to specific settings and certain dynamics. Inspired by the power of machine learning models for efficiently capturing different types of patterns and relations, we propose a machine learning-based, data driven approach for vital node identification. The main idea is to train the model with a small portion of the graph, say 0.5% of the nodes, and do the prediction on the rest of the nodes. The ground-truth vitality for the train data is computed by simulating the SIR diffusion method starting from the train nodes. We use collective feature engineering where each node in the network is represented by incorporating elements of its connectivity, degree and extended coreness. Several machine learning models are trained on the node representations, but the best results are achieved by a Support Vector Regression machine with RBF kernel. The empirical results confirms that the proposed model outperforms state-of-the-art models on a selection of datasets, while it also shows more adaptability to changes in the dynamics parameters.
Classification of posts in social media such as Twitter is difficult due to the noisy and short nature of texts. Sequence classification models based on recurrent neural networks (RNN) are popular for classifying posts that are sequential in nature. RNNs assume the hidden representation dynamics to evolve in a discrete manner and do not consider the exact time of the posting. In this work, we propose to use recurrent neural ordinary differential equations (RNODE) for social media post classification which consider the time of posting and allow the computation of hidden representation to evolve in a time-sensitive continuous manner. In addition, we propose a novel model, Bi-directional RNODE (Bi-RNODE), which can consider the information flow in both the forward and backward directions of posting times to predict the post label. Our experiments demonstrate that RNODE and Bi-RNODE are effective for the problem of stance classification of rumours in social media.
Occurrences of catastrophes such as natural or man-made disasters trigger the spread of rumours over social media at a rapid pace. Presenting a trustworthy and summarized account of the unfolding event in near real-time to the consumers of such potentially unreliable information thus becomes an important task. In this work, we propose MTLTS, the first end-to-end solution for the task that jointly determines the credibility and summary-worthiness of tweets. Our credibility verifier is designed to recursively learn the structural properties of a Twitter conversation cascade, along with the stances of replies towards the source tweet. We then take a hierarchical multi-task learning approach, where the verifier is trained at a lower layer, and the summarizer is trained at a deeper layer where it utilizes the verifier predictions to determine the salience of a tweet. Different from existing disaster-specific summarizers, we model tweet summarization as a supervised task. Such an approach can automatically learn summary-worthy features, and can therefore generalize well across domains. When trained on the PHEME dataset [29], not only do we outperform the strongest baselines for the auxiliary task of verification/rumour detection, we also achieve 21 - 35% gains in the verified ratio of summary tweets, and 16 - 20% gains in ROUGE1-F1 scores over the existing state-of-the-art solutions for the primary task of trustworthy summarization.