Computer Science

We present a study to detect friendship, its strength, and its change from smartphone location data collectedamong members of a fraternity. We extract a rich set of co-location features and build classifiers that detectfriendships and close friendship at 30% above a random baseline. We design cross-validation schema to testour model performance in specific application settings, finding it robust to seeing new dyads and to temporalvariance.

Just like everything in the nature, scientific topics flourish and perish. While existing literature well captures article's life-cycle via citation patterns, little is known about how scientific popularity and impact evolves for a specific topic. It would be most intuitive if we could `feel' topic's activity just as we perceive the weather by temperature. Here, we conceive knowledge temperature to quantify topic overall popularity and impact through citation network dynamics. Knowledge temperature includes 2 parts. One part depicts lasting impact by assessing knowledge accumulation with an analogy between topic evolution and isobaric expansion. The other part gauges temporal changes in knowledge structure, an embodiment of short-term popularity, through the rate of entropy change with internal energy, 2 thermodynamic variables approximated via node degree and edge number. Our analysis of representative topics with size ranging from 1000 to over 30000 articles reveals that the key to flourishing is topics' ability in accumulating useful information for future knowledge generation. Topics particularly experience temperature surges when their knowledge structure is altered by influential articles. The spike is especially obvious when there appears a single non-trivial novel research focus or merging in topic structure. Overall, knowledge temperature manifests topics' distinct evolutionary cycles.

Sudden bursts of information cascades can lead to unexpected consequences such as extreme opinions, changes in fashion trends, and uncontrollable spread of rumors. It has become an important problem on how to effectively predict a cascade' size in the future, especially for large-scale cascades on social media platforms such as Twitter and Weibo. However, existing methods are insufficient in dealing with this challenging prediction problem. Conventional methods heavily rely on either hand crafted features or unrealistic assumptions. End-to-end deep learning models, such as recurrent neural networks, are not suitable to work with graphical inputs directly and cannot handle structural information that is embedded in the cascade graphs. In this paper, we propose a novel deep learning architecture for cascade growth prediction, called CasGCN, which employs the graph convolutional network to extract structural features from a graphical input, followed by the application of the attention mechanism on both the extracted features and the temporal information before conducting cascade size prediction. We conduct experiments on two real-world cascade growth prediction scenarios (i.e., retweet popularity on Sina Weibo and academic paper citations on DBLP), with the experimental results showing that CasGCN enjoys a superior performance over several baseline methods, particularly when the cascades are of large scale.

Graph centrality measures use the structure of a network to quantify central or "important" nodes, with applications in web search, social media analysis, and graphical data mining generally. Traditional centrality measures such as the well known PageRank interpret a directed edge as a vote in favor of the importance of the linked node. We study the case where nodes may belong to diverse communities or interests and investigate centrality measures that can identify nodes that are simultaneously important to many such diverse communities. We propose a family of diverse centrality measures formed as fixed point solutions to a generalized nonlinear eigenvalue problem. Our measure can be efficiently computed on large graphs by iterated best response and we study its normative properties on both random graph models and real-world data. We find that we are consistently and efficiently able to identify the most important diverse nodes of a graph, that is, those that are simultaneously central to multiple communities.

Due to the outbreak of COVID-19, users are increasingly turning to online services. An increase in social media usage has also been observed, leading to the suspicion that this has also raised cyberbullying. In this initial work, we explore the possibility of an increase in cyberbullying incidents due to the pandemic and high social media usage. To evaluate this trend, we collected 454,046 cyberbullying-related public tweets posted between January 1st, 2020 -- June 7th, 2020. We summarize the tweets containing multiple keywords into their daily counts. Our analysis showed the existence of at most one statistically significant changepoint for most of these keywords, which were primarily located around the end of March. Almost all these changepoint time-locations can be attributed to COVID-19, which substantiates our initial hypothesis of an increase in cyberbullying through analysis of discussions over Twitter.

The skepticism towards childhood vaccines and genetically modified (GM) food has grown against scientific evidence of their safety. Distrust in scientific research has important societal consequences, from the spread of diseases to hunger in poorer regions. However, these scientific beliefs are hard to change because they are entrenched within many related moral beliefs and perceived beliefs of one's social network. To understand when belief change is possible, we propose a cognitive network model which integrates both moral and social beliefs and provides testable empirical predictions. Using a probabilistic nationally representative longitudinal study, we find that individuals who changed their beliefs, either towards more positive or negative beliefs about childhood vaccines or GM food, had a reduction in the estimated dissonance of their cognitive belief network. These results are in line with model predictions, shed light on the mechanisms leading to belief change, and have implications for science communication.

In this paper we investigated the possibility to use the magnetic Laplacian to characterize directed graphs (a.k.a. networks). Many interesting results are obtained, including the finding that community structure is related to rotational symmetry in the spectral measurements for a type of stochastic block model. Due the hermiticity property of the magnetic Laplacian we show here how to scale our approach to larger networks containing hundreds of thousands of nodes using the Kernel Polynomial Method (KPM). We also propose to combine the KPM with the Wasserstein metric in order to measure distances between networks even when these networks are directed, large and have different sizes, a hard problem which cannot be tackled by previous methods presented in the literature. In addition, our python package is publicly available at \href{this https URL}{this http URL}. The codes can run in both CPU and GPU and can estimate the spectral density and related trace functions, such as entropy and Estrada index, even in directed or undirected networks with million of nodes.

Despite the valuable social interactions that online media promote, these systems provide space for speech that would be potentially detrimental to different groups of people. The moderation of content imposed by many social media has motivated the emergence of a new social system for free speech named Gab, which lacks moderation of content. This article characterizes and compares moderated textual data from Twitter with a set of unmoderated data from Gab. In particular, we analyze distinguishing characteristics of moderated and unmoderated content in terms of linguistic features, evaluate hate speech and its different forms in both environments. Our work shows that unmoderated content presents different psycholinguistic features, more negative sentiment and higher toxicity. Our findings support that unmoderated environments may have proportionally more online hate speech. We hope our analysis and findings contribute to the debate about hate speech and benefit systems aiming at deploying hate speech detection approaches.

Attitudinal Network Graphs are signed graphs where edges capture an expressed opinion: two vertices connected by an edge can be agreeable (positive) or antagonistic (negative). A signed graph is called balanced if each of its cycles includes an even number of negative edges. Balance is often characterized by frustration index or by finding a single convergent balanced state i.e. network consensus. In this paper, we propose to expand the measures of consensus from a single balanced state associated to the frustration index to the set of nearest balanced states. We introduce the frustration cloud as a set of all nearest balanced states, and use a graph balancing algorithm to find all nearest balanced states in deterministic way. Computational concerns are addressed by measuring consensus probabilistically, and we introduce new vertex and edge metrics to quantify status, agreement, and influence. We introduce new global measure of controversy for a given signed graph, and show that vertex status is a zero-sum game in the signed network. We propose an efficient scalable algorithm for calculating frustration cloud based measures in social network and survey data of up to 80,000 vertices and half-a-million edges, and we demonstrate the power of the proposed approach to provide discriminant features for community discovery when compared to spectral clustering and to automatically identify dominant vertices and anomalous decisions in the network.

From conspiracy theories to fake cures and fake treatments, COVID-19 has become a hot-bed for the spread of misinformation online. It is more important than ever to identify methods to debunk and correct false information online. In this paper, we present a methodology and analyses to characterize the two competing COVID-19 misinformation communities online: (i) misinformed users or users who are actively posting misinformation, and (ii) informed users or users who are actively spreading true information, or calling out misinformation. The goals of this study are two-fold: (i) collecting a diverse set of annotated COVID-19 Twitter dataset that can be used by the research community to conduct meaningful analysis; and (ii) characterizing the two target communities in terms of their network structure, linguistic patterns, and their membership in other communities. Our analyses show that COVID-19 misinformed communities are denser, and more organized than informed communities, with a possibility of a high volume of the misinformation being part of disinformation campaigns. Our analyses also suggest that a large majority of misinformed users may be anti-vaxxers. Finally, our sociolinguistic analyses suggest that COVID-19 informed users tend to use more narratives than misinformed users.