Xinyi Zhou

Boda Lin, Xinyi Zhou, Binghao Tang et al.

Pre-trained language models have been widely used in dependency parsing task and have achieved significant improvements in parser performance. However, it remains an understudied question whether pre-trained language models can spontaneously exhibit the ability of dependency parsing without introducing additional parser structure in the zero-shot scenario. In this paper, we propose to explore the dependency parsing ability of large language models such as ChatGPT and conduct linguistic analysis. The experimental results demonstrate that ChatGPT is a potential zero-shot dependency parser, and the linguistic analysis also shows some unique preferences in parsing outputs.

Chen Yang, Xinyi Zhou, Reza Zafarani

COVID-19 has impacted all lives. To maintain social distancing and avoiding exposure, works and lives have gradually moved online. Under this trend, social media usage to obtain COVID-19 news has increased. Also, misinformation on COVID-19 is frequently spread on social media. In this work, we develop CHECKED, the first Chinese dataset on COVID-19 misinformation. CHECKED provides a total 2,104 verified microblogs related to COVID-19 from December 2019 to August 2020, identified by using a specific list of keywords. Correspondingly, CHECKED includes 1,868,175 reposts, 1,185,702 comments, and 56,852,736 likes that reveal how these verified microblogs are spread and reacted on Weibo. The dataset contains a rich set of multimedia information for each microblog including ground-truth label, textual, visual, temporal, and network information. Extensive experiments have been conducted to analyze CHECKED data and to provide benchmark results for well-established methods when predicting fake news using CHECKED. We hope that CHECKED can facilitate studies that target misinformation on coronavirus. The dataset is available at https://github.com/cyang03/CHECKED.

Xinyi Zhou, Ashish Sharma, Amy X. Zhang et al. · uw

Real-world misinformation, often multimodal, can be partially or fully factual but misleading using diverse tactics like conflating correlation with causation. Such misinformation is severely understudied, challenging to address, and harms various social domains, particularly on social media, where it can spread rapidly. High-quality and timely correction of misinformation that identifies and explains its (in)accuracies effectively reduces false beliefs. Despite the wide acceptance of manual correction, it is difficult to be timely and scalable. While LLMs have versatile capabilities that could accelerate misinformation correction, they struggle due to a lack of recent information, a tendency to produce false content, and limitations in addressing multimodal information. We propose MUSE, an LLM augmented with access to and credibility evaluation of up-to-date information. By retrieving evidence as refutations or supporting context, MUSE identifies and explains content (in)accuracies with references. It conducts multimodal retrieval and interprets visual content to verify and correct multimodal content. Given the absence of a comprehensive evaluation approach, we propose 13 dimensions of misinformation correction quality. Then, fact-checking experts evaluate responses to social media content that are not presupposed to be misinformation but broadly include (partially) incorrect and correct posts that may (not) be misleading. Results demonstrate MUSE's ability to write high-quality responses to potential misinformation--across modalities, tactics, domains, political leanings, and for information that has not previously been fact-checked online--within minutes of its appearance on social media. Overall, MUSE outperforms GPT-4 by 37% and even high-quality responses from laypeople by 29%. Our work provides a general methodological and evaluative framework to correct misinformation at scale.

Anthony Wise, Xinyi Zhou, Martin Reimann et al.

Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation.

Xinyi Zhou, Kai Shu, Vir V. Phoha et al.

Individuals can be misled by fake news and spread it unintentionally without knowing it is false. This phenomenon has been frequently observed but has not been investigated. Our aim in this work is to assess the intent of fake news spreaders. To distinguish between intentional versus unintentional spreading, we study the psychological explanations of unintentional spreading. With this foundation, we then propose an influence graph, using which we assess the intent of fake news spreaders. Our extensive experiments show that the assessed intent can help significantly differentiate between intentional and unintentional fake news spreaders. Furthermore, the estimated intent can significantly improve the current techniques that detect fake news. To our best knowledge, this is the first work to model individuals' intent in fake news spreading.

Xinyi Zhou, Jindi Wu, Reza Zafarani

Effective detection of fake news has recently attracted significant attention. Current studies have made significant contributions to predicting fake news with less focus on exploiting the relationship (similarity) between the textual and visual information in news articles. Attaching importance to such similarity helps identify fake news stories that, for example, attempt to use irrelevant images to attract readers' attention. In this work, we propose a $\mathsf{S}$imilarity-$\mathsf{A}$ware $\mathsf{F}$ak$\mathsf{E}$ news detection method ($\mathsf{SAFE}$) which investigates multi-modal (textual and visual) information of news articles. First, neural networks are adopted to separately extract textual and visual features for news representation. We further investigate the relationship between the extracted features across modalities. Such representations of news textual and visual information along with their relationship are jointly learned and used to predict fake news. The proposed method facilitates recognizing the falsity of news articles based on their text, images, or their "mismatches." We conduct extensive experiments on large-scale real-world data, which demonstrate the effectiveness of the proposed method.

Kai Shu, Xinyi Zhou, Suhang Wang et al.

Consuming news from social media is becoming increasingly popular. Social media appeals to users due to its fast dissemination of information, low cost, and easy access. However, social media also enables the widespread of fake news. Because of the detrimental societal effects of fake news, detecting fake news has attracted increasing attention. However, the detection performance only using news contents is generally not satisfactory as fake news is written to mimic true news. Thus, there is a need for an in-depth understanding on the relationship between user profiles on social media and fake news. In this paper, we study the challenging problem of understanding and exploiting user profiles on social media for fake news detection. In an attempt to understand connections between user profiles and fake news, first, we measure users' sharing behaviors on social media and group representative users who are more likely to share fake and real news; then, we perform a comparative analysis of explicit and implicit profile features between these user groups, which reveals their potential to help differentiate fake news from real news. To exploit user profile features, we demonstrate the usefulness of these user profile features in a fake news classification task. We further validate the effectiveness of these features through feature importance analysis. The findings of this work lay the foundation for deeper exploration of user profile features of social media and enhance the capabilities for fake news detection.

Xinyi Zhou, Atishay Jain, Vir V. Phoha et al.

Massive dissemination of fake news and its potential to erode democracy has increased the demand for accurate fake news detection. Recent advancements in this area have proposed novel techniques that aim to detect fake news by exploring how it propagates on social networks. Nevertheless, to detect fake news at an early stage, i.e., when it is published on a news outlet but not yet spread on social media, one cannot rely on news propagation information as it does not exist. Hence, there is a strong need to develop approaches that can detect fake news by focusing on news content. In this paper, a theory-driven model is proposed for fake news detection. The method investigates news content at various levels: lexicon-level, syntax-level, semantic-level and discourse-level. We represent news at each level, relying on well-established theories in social and forensic psychology. Fake news detection is then conducted within a supervised machine learning framework. As an interdisciplinary research, our work explores potential fake news patterns, enhances the interpretability in fake news feature engineering, and studies the relationships among fake news, deception/disinformation, and clickbaits. Experiments conducted on two real-world datasets indicate the proposed method can outperform the state-of-the-art and enable fake news early detection when there is limited content information.

Xinyi Zhou, Reza Zafarani

The explosive growth in fake news and its erosion to democracy, justice, and public trust has increased the demand for fake news detection and intervention. This survey reviews and evaluates methods that can detect fake news from four perspectives: (1) the false knowledge it carries, (2) its writing style, (3) its propagation patterns, and (4) the credibility of its source. The survey also highlights some potential research tasks based on the review. In particular, we identify and detail related fundamental theories across various disciplines to encourage interdisciplinary research on fake news. We hope this survey can facilitate collaborative efforts among experts in computer and information sciences, social sciences, political science, and journalism to research fake news, where such efforts can lead to fake news detection that is not only efficient but more importantly, explainable.

Xinyi Zhou, Yong Hu, Yong Deng et al.

Pairwise comparison matrix as a crucial component of AHP, presents the prefer- ence relations among alternatives. However, in many cases, the pairwise comparison matrix is difficult to complete, which obstructs the subsequent operations of the clas- sical AHP. In this paper, based on DEMATEL which has ability to derive the total relation matrix from direct relation matrix, a new completion method for incomplete pairwise comparison matrix is proposed. The proposed method provides a new per- spective to estimate the missing values with explicit physical meaning. Besides, the proposed method has low computational cost. This promising method has a wide application in multi-criteria decision-making.