Fake news and COVID-19: modelling the predictors of fake news sharing among social media users

Fake news dissemination on COVID-19 has increased in recent months, and the factors that lead to the sharing of this misinformation is less well studied. Therefore, this paper describes the result of a Nigerian sample (n = 385) regarding the proliferation of fake news on COVID-19. The fake news phenomenon was studied using the Uses and Gratification framework, which was extended by an “altruism” motivation. The data were analysed with Partial Least Squares (PLS) to determine the effects of six variables on the outcome of fake news sharing. Our results showed that altruism was the most significant factor that predicted fake news sharing of COVID-19. We also found that social media users’ motivations for information sharing, socialisation, information seeking and pass time predicted the sharing of false information about COVID-19. In contrast, no significant association was found for entertainment motivation. We concluded with some theoretical and practical implications.     

基于传播意图特征的虚假新闻检测方法综述

虚假新闻的传播会对个人、社会和国家产生巨大的负面影响,因此虚假新闻的检测始终都是研究的热点问题。虚假新闻检测实质上是一种信息分类问题,旨在验证由文本,图像和视频等多媒体信息构成的新闻的真实性。本文对虚假新闻检测问题和当前的主流方法展开了比较系统的研究,并揭示了虚假新闻的一个本质,即与报道真实事件的真实新闻不同,假新闻通常是有意为之,有特定的传播意图如误导公众等。基于这一特性,本文首先将虚假新闻的传播意图大致分为三类,并根据对应的相关特征对当前的研究方法作了分析,旨在能让读者从一个全新的角度理解虚假新闻检测领域。本文还介绍了虚假新闻检测的问题定义、基本范式、常用数据集和指标,并给出了该领域的未来的一些发展方向。      

一种基于特征点对齐的假脸检测框架

近年来,Deepfake等假脸技术的产生颠覆了人们对人脸信息真实性和安全性的认知,引发广泛的社会担忧,检测假脸成为了学术界、产业界共同关注的热点问题。通过一种基于特征点对齐的假脸检测框架,可以有效对Deepfake技术产生的假脸进行判别。该框架制定了一套包括人脸检测、定点、对齐、特征提取、假脸识别等步骤的假脸检测流程,并通过引入特征点对齐保障假脸检测效果。在Deepfake检测挑战赛(DFDC)数据集上的试验表明,该框架适配4种当前主流骨干网络算法都能获得较好的检测结果;在FaceForensics++数据集上的试验表明,该框架适配ResNet50针对几种不同方式生成的假脸图像都可以取得良好效果。     

News recommendation based on time factor and word embedding

Existing algorithms of news recommendations lack in depth analysis of news texts and timeliness. To address these issues, an algorithm for news recommendations based on time factor and word embedding ( TFWE) was proposed to improve the interpretability and precision of news recommendations. First, TFWE used term frequency- inverse document frequency ( TF-IDF ) to extract news feature words and used the bidirectional encoder representations from transformers ( BERT ) pre-training model to convert the feature words into vector representations. By calculating the distance between the vectors, TFWE analyzed the semantic similarity to construct a user interest model. Second, considering the timeliness of news, a method of calculating news popularity by integrating time factors into the similarity calculation was proposed. Finally, TFWE combined the similarity of news content with the similarity of collaborative filtering ( CF) and recommended some news with higher rankings to users. In addition, results of the experiments on real dataset showed that TFWE significantly improved precision, recall, and F1 score compared to the classic hybrid recommendation algorithm.     

What Creates Interactivity in Online News Discussions? An Exploratory Analysis of Discussion Factors in User Comments on News Items

While the social, political, and journalistic relevance of user comments on online news items has been discussed intensively, no study has tried to examine why some online news discussions are more interactive than others. Based on the rationale of news value theory, this study argues that so‐called discussion factors in user comments indicate general relevance to later users to respond to them. Qualitative interviews with users who comment on news stories online and a quantitative content analysis of 1,580 user comments showed that the discussion factors uncertainty, controversy, comprehensibility, negativity, and personalization can explain interactivity in news discussions. Further, different technological implementations of the comment function seem to have a limited influence on the effects of these discussion factors.     

The role of online news and social media in preventive action in times of infodemic from a social capital perspective: The case of the COVID-19 pandemic in South Korea

Infodemic, the spread of false information during the COVID-19 pandemic, has been raised as one of the major concerns aggravating the confusion in the global society. In this regard, the role of media as an information channel in delivering the reliable information and motivating the active participation of citizens in complying with government’s preventive actions becomes much more important. In this study, the role of online news and social media on people’s preventive actions considering the role of trust in citizens and government from the perspective of social capital is investigated. For the empirical study, a structural equation modeling is employed by using survey material gathered from South Korea in the early days of the COVID-19 outbreak. South Korea was selected as its COVID-19 prevention strategy focused not only on the provision of medical support, but also on the enhancement of social trust through active engagement with people through media channels. Our results reveal that the perceived characteristics of online news and social media influence preventive actions through the trust in citizens or in government. In addition, while online news media enhances trust in both the citizens and the government, social media only influences trust in citizens. Based on our findings, the role of media in preventing the spread of COVID-19 is dicussed.     

What is the impact of service quality on customers’ satisfaction during COVID-19 outbreak? New findings from online reviews analysis

The COVID-19 pandemic has caused major global changes both in the areas of healthcare and economics. This pandemic has led, mainly due to conditions related to confinement, to major changes in consumer habits and behaviors. Although there have been several studies on the analysis of customers’ satisfaction through survey-based and online customers’ reviews, the impact of COVID-19 on customers' satisfaction has not been investigated so far. It is important to investigate dimensions of satisfaction from the online customers’ reviews to reveal their preferences on the hotels' services during the COVID-19 outbreak. This study aims to reveal the travelers’ satisfaction in Malaysian hotels during the COVID-19 outbreak through online customers’ reviews. In addition, this study investigates whether service quality during COVID-19 has an impact on hotel performance criteria and consequently customers' satisfaction. Accordingly, we develop a new method through machine learning approaches. The method is developed using text mining, clustering, and prediction learning techniques. We use Latent Dirichlet Allocation (LDA) for big data analysis to identify the voice-of-the-customer, Expectation-Maximization (EM) for clustering, and ANFIS for satisfaction level prediction. In addition, we use Higher-Order Singular Value Decomposition (HOSVD) for missing value imputation. The data was collected from TripAdvisor regarding the travelers’ concerns in the form of online reviews on the COVID-19 outbreak and numerical ratings on hotel services from different perspectives. The results from the analysis of online customers’ reviews revealed that service quality during COVID-19 has an impact on hotel performance criteria and consequently customers' satisfaction. In addition, the results showed that although the customers are always seeking hotels with better performance, they are also concerned with the quality of related services in the COVID-19 outbreak.     

注意力引导梯形金字塔融合网络识别新冠肺炎X射线影像

新型冠状病毒肺炎(corona virus disease 2019,COVID-19)严重影响人类社会和经济的发展,威胁人类的健康。如何更准确、快速地排查感染病毒的患者,使用卷积神经网络(convolutional neural network, CNN)的方法识别COVID-19胸部X射线影像,完成计算机自动辅助诊断。但是,由于识别精度不高,难以准确判断是否感染了COVID-19。为了提高网络模型对COVID-19胸部X射线影像的识别性能,首先提出注意力引导梯形金字塔融合网络(attention steered trapezoid pyramid fusion network, ASTPNet),该网络可以附加在不同的CNN上,有效地利用模型中深层与浅层网络的特点;其次提出注意力引导块(attention steered block, AS Block),通过通道和空间注意力,强调通道和空间中的有效语义信息,弱化无效的干扰信息,高效地聚合加权信息。最终实验结果表明：将ASTPNet附加在VGG16/19、ResNet34/50和ResNeXt上,识别精度有了显著提升;应用于自建的C...     

BPR-UserRec:a personalized user recommendation method in social tagging systems

Social tagging is one of the most important characteristics of Web 2.0 services, and social tagging systems (STS) are becoming more and more popular for users to annotate, organize and share items on the Web. Moreover, online social network has been incorporated into social tagging systems. As more and more users tend to interact with real friends on the Web, personalized user recommendation service provided in social tagging systems is very appealing. In this paper, we propose a personalized user recommendation method, and our method handles not only the users’ interest networks, but also the social network information. We empirically show that our method outperforms a state-of-the-art method on real dataset from Last.fm dataset and Douban.     

Do social media literacy skills help in combating fake news spread? Modelling the moderating role of social media literacy skills in the relationship between rational choice factors and fake news sharing behaviour

This study modelled the rational factors that predict fake news sharing behaviour. It also tested the moderating role of social media literacy skills. The focus was on social media users in Nigeria. An online survey was conducted to gather the responses from participants across Nigerian geopolitical zones. Structural equation modelling (SEM) Smart PLS 3.6 was used to analyse the data. We found that information sharing, the news finds me perception, trust in social media and status-seeking lead to fake news sharing among social media users in Nigeria. Specifically, trust in social media and status-seeking had a greater effect on fake news sharing behaviour. We also found that social media literacy skills significantly moderate the relationship between information sharing, status-seeking, the news finds me perception, trust in social media and fake news sharing in such a way that the effects/relationships are stronger among those with low social media literacy skills. This outcome contributes to theory and practice which was highlighted in the concluding aspect of this study.     

基于信任度评估的社交网络虚假账户检测

在利益驱动下,社交网络中出现大量虚假账户,其发布的虚假消息可对正常用户产生误导。通过对社交网络中大量数据进行分析,发现虚假账户与正常账户在账户特性、行为特性上有较大差异。基于这些差异,结合Rough Set相关理论提出账户信任度的计算模型。所得信任度可用以区分虚假账户,并为正常用户的判断提供依据。实验显示,根据所得信任度对账户排序得到了较好效果,并能够有效区分虚假账户。     

人脸视频深度伪造与防御技术综述

近年来，得益于深度生成模型的发展，人脸的操控技术取得了巨大突破，以DeepFake为代表的人脸视频深度伪造技术在互联网快速流行，受到了学术界和工业界的广泛重视。这种深度伪造技术通过交换原始人脸和目标人脸的身份信息或编辑目标人脸的属性信息来合成虚假的人脸视频。人脸深度伪造技术激发了很多相关的娱乐应用，如使用面部替换技术将使用者的人脸替换到某段电影片段中，或使用表情重演技术来驱动某个著名人物的静态肖像等。但当前人脸深度伪造技术仍处于快速发展阶段，其生成的真实感和自然度仍有待进一步提升。另一方面，这类人脸深度伪造技术也很容易被不法分子恶意使用，用来制作色情电影、虚假新闻，甚至被用于政要人物来制造政治谣言等，这对国家安全与社会稳定都带来了极大的潜在威胁，因此伪造人脸视频的防御技术至关重要。为了降低深度伪造人脸视频所带来的负面影响，众多学者对伪造人脸视频的检测鉴别技术进行了深入研究，并从不同视角提出了一系列防御方法。然而由于数据集分布形式单一、评价标准不一致、主动性不足等问题，使得防御技术在走向实用的道路上仍有很长一段距离。事实上，人脸深度伪造与防御技术的研究仍旧处在发展期，其技术的内涵与外延正在快速的更新与迭代。本综述将对迄今为止的主要研究工作进行科学系统的总结与归纳，并对现有技术的局限性做简要分析。最后，本文将探讨人脸深度伪造与检测技术的潜在挑战与发展方向，为领域内未来的研究工作提供借鉴。      

Multi-hop Mobility Prediction

With the occurrence of large-scale human trajectories, which imply spatial and temporal patterns, the subject of mobility prediction has been widely studied. A number of approaches are proposed to predict the next location of a user. In this paper, we expect to lengthen the temporal dimension of prediction results beyond one hop. To predict the future locations of a user at every time unit within a specified time, we propose a Markov-based multi-hop mobility prediction (Markov–MHMP) algorithm. It is a hybrid approach that considers multiple factors including personal habit, weekday similarity, and collective behavior. On a GPS dataset, our approach performs prediction better than baseline and state-of-the-art approaches under several evaluation criteria.     

Can COVID-19 pandemic influence experience response in mobile learning?

The mass spreading of COVID-19 has changed the paradigm of the education industry. In China and many other nations, universities have introduced compulsory remote education programs such as mobile learning (m-learning) to prevent public health hazards caused by the pandemic. However, so far, there is still a lack of understanding of student’s learning experience responses in compulsory m-learning programs. As such, there is a necessity to explore the factors and mechanisms which drives students’ experience. This paper evaluates the influence of both pedagogy and technology on learner’s compulsory m-learning experience response (ER) by extending the mobile technology acceptance model (MTAM) during the COVID-19 pandemic. An online self-administered questionnaire was used to collect the data, which was then analysed through SmartPLS 3.2.9. Importance-performance matrix analysis was applied as a post-hoc procedure to gauge the importance and performance of the exogenous constructs. The results revealed that perceptions of m-learning’s learning content quality, user interface, and system’s connectivity affect the perceived mobile usefulness and easiness which in turn affects ER. This paper validates MTAM in the field of education by integrating MTAM with pedagogy and technology attributes under a social emergency setting such as the COVID-19 pandemic. In addition, the current research explains users' ER rather than behaviour intention which is commonly adopted in past studies.     

Arnie gets a green carpet

PV has been much in the news of late — as you can see from any online news source, renewable energy is a hot topic deserving its own newsfeed. Luckily for us in the conventional print media, the majority of such feeds are ‘dumb’. Daily — and indiscriminately — they will retrieve for you several screens worth of items to wade through until you find the few that interest you. All too often these are also short-lived. So we think that the print medium has not had its day just yet.     

Framework for COVID-19 Segmentation and Classification Based on Deep Learning of Computed Tomography Lung Images

Corona Virus Disease 2019 (COVID-19) has affected millions of people worldwide and caused more than 6.3 million deaths (World Health Organization, June 2022). Increased attempts have been made to develop deep learning methods to diagnose COVID-19 based on computed tomography (CT) lung images. It is a challenge to reproduce and obtain the CT lung data, because it is not publicly available. This paper introduces a new generalized framework to segment and classify CT images and determine whether a patient is tested positive or negative for COVID-19 based on lung CT images. In this work, many different strategies are explored for the classification task. ResNet50 and VGG16 models are applied to classify CT lung images into COVID-19 positive or negative. Also, VGG16 and ReNet50 combined with U-Net, which is one of the most used architectures in deep learning for image segmentation, are employed to segment CT lung images before the classifying process to increase system performance. Moreover, the image size dependent normalization technique (ISDNT) and Wiener filter are utilized as the preprocessing techniques to enhance images and noise suppression. Additionally, transfer learning and data augmentation techniques are performed to solve the problem of COVID-19 CT lung images deficiency, therefore the over-fitting of deep models can be avoided. The proposed frameworks, which comprised of end-to-end, VGG16, ResNet50, and U-Net with VGG16 or ResNet50, are applied on the dataset that is sourced from COVID-19 lung CT images in Kaggle. The classification results show that using the preprocessed CT lung images as the input for U-Net hybrid with ResNet50 achieves the best performance. The proposed classification model achieves the 98.98% accuracy (ACC), 98.87% area under the ROC curve (AUC), 98.89% sensitivity (Se), 97.99 % precision (Pr), 97.88% F₁-score, and 1.8974-seconds computational time.     

A Multi-Directional Search technique for image annotation propagation

Image annotation has attracted lots of attention due to its importance in image understanding and search areas. In this paper, we propose a novel Multi-Directional Search framework for semi-automatic annotation propagation. In this system, the user interacts with the system to provide example images and the corresponding annotations during the annotation propagation process. In each iteration, the example images are clustered and the corresponding annotations are propagated separately to each cluster: images in the local neighborhood are annotated. Furthermore, some of those images are returned to the user for further annotation. As the user marks more images, the annotation process goes into multiple directions in the feature space. The query movements can be treated as multiple path navigation. Each path could be further split based on the user’s input. In this manner, the system provides accurate annotation assistance to the user - images with the same semantic meaning but different visual characteristics can be handled effectively. From comprehensive experiments on Corel and U. of Washington image databases, the proposed technique shows accuracy and efficiency on annotating image databases.     

Random Group Recommendation Model Based on Fuzzy Clustering

The group recommendation system is a viral requirement for the Internet service provider to provide recommendation services for all the users in a group. Due to the shared or different interests among users in the group, it is difficult for traditional personal recommendation algorithms to predict items that can meet the requirements of all the users in the group. In this paper, a random group recommendation model is proposed to recommend the top K most appealing items for all the users in a random group. By analyzing item ratings of all the users in the group, the recommendation model can abstract the group as a virtual user. Then a personal recommendation algorithm is applied to suggest the top K most appealing items for the virtual user. And the preference score and fuzzy clustering algorithm based on multiclass are applied to optimize the recommendation result of the group recommendation model. Finally, the MovieLens-100K dataset is applied to verify the efficiency of the recommendation model. The experimental results show that the items recommended by the proposed group recommendation model are more popular for all the users in the group than the items recommended by traditional group recommendation algorithms.     

Objectivity and Information Bias in Campaign News

This article examines whether objective campaign news stories—defined here as those with equitable tone toward 2 competing candidates—are less informative than slanted stories favoring one candidate over the other. Using a large news content dataset composed of campaign news stories from statewide elections in 2004, 2006, and 2008, we measure news story quality 6 different ways. It is modeled as a function of differences in story tone toward opposing candidates and a host of other news outlet and electoral characteristics known to influence the nature and type of information in campaign news. We find that slant is positively related to the likelihood that news articles focus on substance, issues, and include sourced content.     

Defending against phishing attacks: taxonomy of methods,current issues and future directions

Internet technology is so pervasive today, for example, from online social networking to online banking, it has made people’s lives more comfortable. Due the growth of Internet technology, security threats to systems and networks are relentlessly inventive. One such a serious threat is “phishing”, in which, attackers attempt to steal the user’s credentials using fake emails or websites or both. It is true that both industry and academia are working hard to develop solutions to combat against phishing threats. It is therefore very important that organisations to pay attention to end-user awareness in phishing threat prevention. Therefore, aim of our paper is twofold. First, we will discuss the history of phishing attacks and the attackers’ motivation in details. Then, we will provide taxonomy of various types of phishing attacks. Second, we will provide taxonomy of various solutions proposed in literature to protect users from phishing based on the attacks identified in our taxonomy. Moreover, we have also discussed impact of phishing attacks in Internet of Things (IoTs). We conclude our paper discussing various issues and challenges that still exist in the literature, which are important to fight against with phishing threats.