Characterizing multi-domain false news and underlying user effects on Chinese Weibo

False news that spreads on social media has proliferated over the past years and has led to multi-aspect threats in the real world. While there are studies of false news on specific domains (like politics or health care), little work is found comparing false news across domains. In this article, we investigate false news across nine domains on Weibo, the largest Twitter-like social media platform in China, from 2009 to 2019. The newly collected data comprise 44,728 posts in the nine domains, published by 40,215 users, and reposted over 3.4 million times. Based on the distributions and spreads of the multi-domain dataset, we observe that false news in domains that are close to daily life like health and medicine generated more posts but diffused less effectively than those in other domains like politics, and that political false news had the most effective capacity for diffusion. The widely diffused false news posts on Weibo were associated strongly with certain types of users — by gender, age, etc. Further, these posts provoked strong emotions in the reposts and diffused further with the active engagement of false-news starters. Our findings have the potential to help design false news detection systems in suspicious news discovery, veracity prediction, and display and explanation. The comparison of the findings on Weibo with those of existing work demonstrates nuanced patterns, suggesting the need for more research on data from diverse platforms, countries, or languages to tackle the global issue of false news. The code and new anonymized dataset are available at https://github.com/ICTMCG/Characterizing-Weibo-Multi-Domain-False-News.     

A noise-filtering event generator for PIDPlus controllers

In this paper we propose a new event generator, which has strong noise-filtering capabilities, to be used in event-based control systems with a PIDPlus controller. An approximate frequency analysis is performed in order to characterize the event generator system and tuning guidelines are provided for its design parameter. Simulation and experimental results obtained with a laboratory setup demonstrate the effectiveness of the methodology in providing a satisfactory performance related to set-point and load disturbance step responses with a total variation that is significantly reduced with respect to the standard cases.     

Pachinko Prediction: A Bayesian method for event prediction from social media data

The combination of large open data sources with machine learning approaches presents a potentially powerful way to predict events such as protest or social unrest. However, accounting for uncertainty in such models, particularly when using diverse, unstructured datasets such as social media, is essential to guarantee the appropriate use of such methods. Here we develop a Bayesian method for predicting social unrest events in Australia using social media data. This method uses machine learning methods to classify individual postings to social media as being relevant, and an empirical Bayesian approach to calculate posterior event probabilities. We use the method to predict events in Australian cities over a period in 2017/18.     

Diffusion of real versus misinformation during a crisis event: A big data-driven approach

Misinformation has captured the interest of academia in recent years with several studies looking at the topic broadly with inconsistent results. In this research, we attempt to bridge the gap in the literature by examining the impacts of user-, time-, and content-based characteristics that affect the virality of real versus misinformation during a crisis event. Using a big data-driven approach, we collected over 42 million tweets during Hurricane Harvey and obtained 3589 original verified real or false tweets by cross-checking with fact-checking websites and a relevant federal agency. Our results show that virality is higher for misinformation, novel tweets, and tweets with negative sentiment or lower lexical density. In addition, we reveal the opposite impacts of sentiment on the virality of real news versus misinformation. We also find that tweets on the environment are less likely to go viral than the baseline religious news, while real social news tweets are more likely to go viral than misinformation on social news.     

AugPrompt: Knowledgeable augmented-trigger prompt for few-shot event classification

Few-Shot Event Classification (FSEC) aims at assigning event labels to unlabeled sentences when limited annotated samples are available. Existing works mainly focus on using meta-learning to overcome the low-resource problem that still requires abundant held-out classes for model learning and selection. Thus we propose to deal with the low-resource problem by utilizing prompts. Further, existing methods suffer from severe trigger biases that may result in ignorance of the context. That is, the correct classifications are gained by looking at only the triggers, which hurts the model’s generalization ability. Thus, we propose a knowledgeable augmented-trigger prompt FSEC framework (AugPrompt), which can overcome the bias issues and alleviates the classification bottleneck brought by insufficient data. In detail, we first design an External Knowledge Injection (EKI) module to incorporate an external knowledge base (Related Words) for trigger augmentation. Then, we propose an Event Prompt Generation (EPG) module to generate appropriate discrete prompts for initializing the continuous prompts. After that, we propose an Event Prompt Tuning (EPT) module to automatically search prompts in the continuous space for FSEC and finally predict the corresponding event types of the inputs. We conduct extensive experiments on two public English datasets for FSEC, i.e., FewEvent and RAMS. The experimental results show the superiority of our proposal over the competitive baselines, where the maximum accuracy increase compared to the strongest baseline reaches 10.8%.     

A framework for understanding online group behaviors during a catastrophic event

This study investigated the underlying mechanisms of online social media group behaviors in an emergency. The proposed framework was designed to analyze group behaviors/interactions and examine the main topics of interest among numerous tweets generated in an emergency. We collected tweets sent during Hurricane Harvey in 2017 and applied the framework to demonstrate its effectiveness. The proposed framework enables us to understand the unique characteristics of group interactions and develop operational strategies to effectively communicate with the public, as well as other groups, as critical emergency information appears in an online social network.     

A local and global event sentiment based efficient stock exchange forecasting using deep learning

Stock exchange forecasting is an important aspect of business investment plans. The customers prefer to invest in stocks rather than traditional investments due to high profitability. The high profit is often linked with high risk due to the nonlinear nature of data and complex economic rules. The stock markets are often volatile and change abruptly due to the economic conditions, political situation and major events for the country. Therefore, to investigate the effect of some major events more specifically global and local events for different top stock companies (country-wise) remains an open research area. In this study, we consider four countries- US, Hong Kong, Turkey, and Pakistan from developed, emerging and underdeveloped economies’ list. We have explored the effect of different major events occurred during 2012–2016 on stock markets. We use the Twitter dataset to calculate the sentiment analysis for each of these events. The dataset consists of 11.42 million tweets that were used to determine the event sentiment. We have used linear regression, support vector regression and deep learning for stock exchange forecasting. The performance of the system is evaluated using the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results show that performance improves by using the sentiment for these events.     

I-S detectability of partially-observed discrete event systems: a novel matrix-based method

The state estimation problem is always considered to be critical in discrete event systems (DESs). In this paper, two methods are proposed for investigating the initial state estimation problem: one is the matrix-based dimension reduction tracking observation system, and the other is the matrix-based reversal observation system. In our paper, the initial state estimation is treated as the initial-state detectability (I-S detectability). Using the Boolean semi-tensor product method of matrices, the corresponding algebraic forms of the partially-observed DES are separately constructed, where the corresponding computational complexity is reduced to some degree. Based on the newly defined state transition output-event observation matrix, necessary and sufficient criteria are established to determine the I-S detectability of the addressed system. Illustrative examples are also given to show feasibility of the derived results.     

Extracting temporal and causal relations based on event networks

Event relations specify how different event flows expressed within the context of a textual passage relate to each other in terms of temporal and causal sequences. There have already been impactful work in the area of temporal and causal event relation extraction; however, the challenge with these approaches is that (1) they are mostly supervised methods and (2) they rely on syntactic and grammatical structure patterns at the sentence-level. In this paper, we address these challenges by proposing an unsupervised event network representation for temporal and causal relation extraction that operates at the document level. More specifically, we benefit from existing Open IE systems to generate a set of triple relations that are then used to build an event network. The event network is bootstrapped by labeling the temporal disposition of events that are directly linked to each other. We then systematically traverse the event network to identify the temporal and causal relations between indirectly connected events. We perform experiments based on the widely adopted TempEval-3 and Causal-TimeBank corpora and compare our work with several strong baselines. We show that our method improves performance compared to several strong methods.     

Object identification and retrieval from efficient image matching. Snap2Tell with the STOIC dataset

Traditional content based image retrieval attempts to retrieve images using syntactic features for a query image. Annotated image banks and Google allow the use of text to retrieve images. In this paper, we studied the task of using the content of an image to retrieve information in general. We describe the significance of object identification in an information retrieval paradigm that uses image set as intermediate means in indexing and matching. We also describe a unique Singapore Tourist Object Identification Collection with associated queries and relevance judgments for evaluating the new task and the need for efficient image matching using simple image features. We present comprehensive experimental evaluation on the effects of feature dimensions, context, spatial weightings, coverage of image indexes, and query devices on task performance. Lastly we describe the current system developed to support mobile image-based tourist information retrieval.     

Adaptive fault compensation control for nonlinear uncertain fractional-order systems: Static and dynamic event generator approaches

The tracking problem of the fractional-order nonlinear systems is assessed by extending new event-triggered control designs. The considered dynamics are accompanied by the uncertain strict-feedback form, unknown actuator faults and unknown disturbances. By using the neural networks and the fault compensation method, two adaptive fault compensation event-triggered schemes are designed. Unlike the available control designs, two static and dynamic event-triggered strategies are proposed for the nonlinear fractional-order systems, in a sense that the minimum/average time-interval between two successive events can be prolonged in the dynamic event-triggered approach. Besides, it is proven that the Zeno phenomenon is strictly avoided. Finally, the simulation results prove the effectiveness of the presented control methods.     

Oxidative stress is the primary event: Effects of ethanol consumption in brain

Damaging effects of reactive oxygen species on living systems are well documented. They include oxidative attack on vital cell constituents. Chronic ethanol administration is able to induce an oxidative stress in the central nervous system. In the present study, 16–18 week-old male albino rats of Wistar strain were exposed to different concentration of ethanol for 4 weeks. This exposure showed profound effect on body weight. Ascorbic acid level; and activities of alkaline phosphatase and aspartate transaminase in the brain are dependent on the concentration of ethanol exposure. Chronic ethanol ingestion elicits statistically significant increase in thiobarbituric acid reactive substances level and decrease in gluatathione level in the brain. It reduces superoxide dismutase, catalase, glutathione peroxidase, and glutathione reductase activities in a dose dependent manner. However, histological examination could not reveal any pathophysiological changes. Therefore, we conclude that biochemical alterations and oxidative stress related parameters respond early in alcoholism than the histopathological changes in brain.     

多事件触发巨灾债券设计与定价研究:以中国台风债券为例

巨灾损失具有多样化、立体性特征,多国已经开始多事件触发巨灾债券尝试,定价问题成为研究难点与热点。本文设计并阐述了多事件触发巨灾债券产品定价模型及其实现过程,首次基于中国台风巨灾财产损失、受灾面积两事件,进行了产品初步设计和价格估算。具体通过建立委托代理定价模型,对中国1990年以来历次台风直接经济损失和受灾面积的边缘分布分别进行拟合,借助Clayton Copula得到联合概率分布函数确定定价水平,最后进行了价格敏感性和稳定性检验和动态分析。     

Measuring and profiling the topical influence and sentiment contagion of public event stakeholders

When public events occur, users often generate a huge number of microblog entries and their online interactions with one another. Forwarding and commenting on posts contribute to the huge networks of topic and sentiment communication. This study constructs the topic and sentiment propagation maps of microblogging in the context of public events to visually explore the patterns of topic and sentiment propagation among stakeholders across different phases. To quantify the influence of topic and sentiment propagation, four indicators of “topic out-degree,” “topic variation degree,” “sentiment out-degree,” and “sentiment deviation degree” are proposed. We chose the child abuse case in the Beijing Red-Yellow-Blue (RYB) Kindergarten for our study. The positions of various stakeholders in the propagation paths and the relationship among stakeholders were revealed. Results indicate that the government and mainstream media have the greatest influence in terms of topic and sentiment propagation. Moreover, topic propagation was the most influential in the recession phase and the same can be said with sentiment propagation in the spreading phase. The findings can help the emergency management departments gain a better understanding of the propagation patterns of topics and emotions and the role of stakeholders in such phenomena to improve their emergency response ability.     

Heterogeneity in consumer preference toward mega-sport event travel packages: Implications for smart tourism marketing strategy

Consumers’ decision-making processes and behaviors are often considered heterogeneous depending on various factors (i.e., decision strategy, spatial location, and individual characteristics). To better understand consumers’ decision-making process in the context of mega-sport events, the current study explores two potential decision biases inducing consumers’ heterogeneity – 1) a simplified decision rule model and 2) spatial variability. More specifically, this study conducted two sequential analyses that explore spatially varying preferences toward the mega-sport event travel package considering the effect of the simplified decision rule. Results revealed that the simplified decision rule model, including a selective evaluation of product attributes, explained better than the full model, considering all product attributes. This study also observed spatially varying preferences toward mega-sport event packages without any meaningful differences in psychological constructs. The findings contribute to the literature on consumer decision bias and spatial variability in tourists’ behaviors. Theoretical and managerial implications are provided in the conclusion.     

Work from home during the COVID-19 pandemic: An observational study based on a large geo-tagged COVID-19 Twitter dataset (UsaGeoCov19)

As COVID-19 swept over the world, people discussed facts, expressed opinions, and shared sentiments about the pandemic on social media. Since policies such as travel restriction and lockdown in reaction to COVID-19 were made at different levels of the society (e.g., schools and employers) and the government, we build a large geo-tagged Twitter dataset titled UsaGeoCov19 and perform an exploratory analysis by geographic location. Specifically, we collect 650,563 unique geo-tagged tweets across the United States covering the date range from January 25 to May 10, 2020. Tweet locations enable us to conduct region-specific studies such as tweeting volumes and sentiment, sometimes in response to local regulations and reported COVID-19 cases. During this period, many people started working from home. The gap between workdays and weekends in hourly tweet volumes inspire us to propose algorithms to estimate work engagement during the COVID-19 crisis. This paper also summarizes themes and topics of tweets in our dataset using both social media exclusive tools (i.e., #hashtags, @mentions) and the latent Dirichlet allocation model. We welcome requests for data sharing and conversations for more insights.UsaGeoCov19 link: http://yunhefeng.me/geo-tagged_twitter_datasets/.     

Group event recommendation based on graph multi-head attention network combining explicit and implicit information

In event-based social networks (EBSN), group event recommendation has become an important task for groups to quickly find events that they are interested in. Existing methods on group event recommendation either consider just one type of information, explicit or implicit, or separately model the explicit and implicit information. However, these methods often generate a problem of data sparsity or of model vector redundancy. In this paper, we present a Graph Multi-head Attention Network (GMAN) model for group event recommendation that integrates the explicit and implicit information in EBSN. Specifically, we first construct a user-explicit graph based on the user's explicit information, such as gender, age, occupation and the interactions between users and events. Then we build a user-implicit graph based on the user's implicit information, such as friend relationships. The incorporated both explicit and implicit information can effectively describe the user's interests and alleviate the data sparsity problem. Considering that there may be a correlation between the user's explicit and implicit information in EBSN, we take the user's explicit vector representation as the input of the implicit information aggregation when modeling with graph neural networks. This unified user modeling can solve the aforementioned problem of user model vector redundancy and is also suitable for event modeling. Furthermore, we utilize a multi-head attention network to learn richer implicit information vectors of users and events from multiple perspectives. Finally, in order to get a higher level of group vector representation, we use a vanilla attention mechanism to fuse different user vectors in the group. Through experimenting on two real-world Meetup datasets, we demonstrate that GMAN model consistently outperforms state-of-the-art methods on group event recommendation.     

Korean–Japanese story link detection based on distributional and contrastive properties of event terms

In this paper, we propose a novel approach for multilingual story link detection. Our approach utilized the distributional features of terms in timelines and multilingual spaces, together with selected types of named entities in order to get distinctive weights for terms that constitute linguistic representation of events. On timelines term significance is calculated by comparing term distribution of the documents on a day with that of the total document collection. Since two languages can provide more information than one language, term significance is measured on each language space, which is then used as a bridge between two languages on multilingual spaces. Evaluating the method on Korean and Japanese news articles, our method achieved 14.3% improvement for monolingual story pairs, and 16.7% improvement for multilingual story pairs. By measuring the space density, the proposed weighting components are verified with a high density of the intra-event stories and a low density of the inter-events stories. This result indicates that the proposed method is helpful for multilingual story link detection.