We consider the problem of obtaining unbiased estimates of group properties in social networks when using a classifier for node labels. Inference for this problem is complicated by two factors: the network is not known and must be crawled, and even high-performance classifiers provide biased estimates of group proportions. We propose and evaluate AdjustedWalk for addressing this problem. This is a three step procedure which entails: 1) walking the graph starting from an arbitrary node; 2) learning a classifier on the nodes in the walk; and 3) applying a post-hoc adjustment to classification labels. The walk step provides the information necessary to make inferences over the nodes and edges, while the adjustment step corrects for classifier bias in estimating group proportions. This process provides de-biased estimates at the cost of additional variance. We evaluate AdjustedWalk on four tasks: the proportion of nodes belonging to a minority group, the proportion of the minority group among high degree nodes, the proportion of within-group edges, and Coleman's homophily index. Simulated and empirical graphs show that this procedure performs well compared to optimal baselines in a variety of circumstances, while indicating that variance increases can be large for low-recall classifiers.
Social influence, sometimes referred to as spillover or contagion, have been extensively studied in various empirical social network research. However, there are various estimation challenges in identifying social influence effects, as they are often entangled with other factors, such as homophily in the selection process, the individual's preference for the same social settings, etc. Methods currently available either do not solve these problems or require strong assumptions. Recent works by Xu 2018 and others show that a latent-space adjusted approach based on the latent space model has pote…
In the last years researchers in the field of intelligent transportation systems have made several efforts to extract valuable information from social media streams. However, collecting domain-specific data from any social media is a challenging task demanding appropriate and robust classification methods. In this work we focus on exploring geo-located tweets in order to create a travel-related tweet classifier using a combination of bag-of-words and word embeddings. The resulting classification makes possible the identification of interesting spatio-temporal relations in São Paulo and Rio de …
Accurately analyzing graph properties of social networks is a challenging task because of access limitations to the graph data. To address this challenge, several algorithms to obtain unbiased estimates of properties from few samples via a random walk have been studied. However, existing algorithms do not consider private nodes who hide their neighbors in real social networks, leading to some practical problems. Here we design random walk-based algorithms to accurately estimate properties without any problems caused by private nodes. First, we design a random walk-based sampling algorithm that…
Social media users post content on various topics. A defining feature of social media is that other users can provide feedback -- called community feedback -- to their content in the form of comments, replies, and retweets. We hypothesize that the amount of received feedback influences the choice of topics on which a social media user posts. However, it is challenging to test this hypothesis as user heterogeneity and external confounders complicate measuring the feedback effect. Here, we investigate this hypothesis with a predictive approach based on an interpretable model of an author's decis…
This paper presents a method to validate the true patrons of a brand, group, artist or any other entity on the social networking site Twitter. We analyze the trend of total number of tweets, average retweets and total number of followers for various nodes for different social and political backgrounds. We argue that average retweets to follower ratio reveals the overall value of the individual accounts and helps estimate the true to fake account ratio.
University of Warwick（华威大学）；Alan Turing Institute（艾伦·图灵研究所）；University of Sheffield（谢菲尔德大学）；University of Melbourne（墨尔本大学）；University of Copenhagen（哥本哈根大学）
Rumour stance classification, defined as classifying the stance of specific social media posts into one of supporting, denying, querying or commenting on an earlier post, is becoming of increasing interest to researchers. While most previous work has focused on using individual tweets as classifier inputs, here we report on the performance of sequential classifiers that exploit the discourse features inherent in social media interactions or 'conversational threads'. Testing the effectiveness of four sequential classifiers -- Hawkes Processes, Linear-Chain Conditional Random Fields (Linear CRF)…
In this paper, we propose an approach for the detection of clickbait posts in online social media (OSM). Clickbait posts are short catchy phrases that attract a user's attention to click to an article. The approach is based on a machine learning (ML) classifier capable of distinguishing between clickbait and legitimate posts published in OSM. The suggested classifier is based on a variety of features, including image related features, linguistic analysis, and methods for abuser detection. In order to evaluate our method, we used two datasets provided by Clickbait Challenge 2017. The best perfo…
Mila-Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Columbia University（哥伦比亚大学）
We consider the problem of estimating social influence, the effect that a person's behavior has on the future behavior of their peers. The key challenge is that shared behavior between friends could be equally explained by influence or by two other confounding factors: 1) latent traits that caused people to both become friends and engage in the behavior, and 2) latent preferences for the behavior. This paper addresses the challenges of estimating social influence with three contributions. First, we formalize social influence as a causal effect, one which requires inferences about hypothetical …
Relational learning in networked data has been shown to be effective in a number of studies. Relational learners, composed of relational classifiers and collective inference methods, enable the inference of nodes in a network given the existence and strength of links to other nodes. These methods have been adapted to predict customer churn in telecommunication companies showing that incorporating them may give more accurate predictions. In this research, the performance of a variety of relational learners is compared by applying them to a number of CDR datasets originating from the telecommuni…
We present a computational approach for estimating emotion contagion on social media networks. Built on a foundation of psychology literature, our approach estimates the degree to which the perceivers' emotional states (positive or negative) start to match those of the expressors, based on the latter's content. We use a combination of deep learning and social network analysis to model emotion contagion as a diffusion process in dynamic social network graphs, taking into consideration key aspects like causality, homophily, and interference. We evaluate our approach on user behavior data obtaine…
Online Social Networks (OSNs), such as Facebook and Twitter, have become an integral part of our daily lives. There are hundreds of OSNs, each with its own focus in that each offers particular services and functionalities. Recent studies show that many OSN users create several accounts on multiple OSNs using the same or different personal information. Collecting all the available data of an individual from several OSNs and fusing it into a single profile can be useful for many purposes. In this paper, we introduce novel machine learning based methods for solving Entity Resolution (ER), a probl…
Malicious actors create inauthentic social media accounts controlled in part by algorithms, known as social bots, to disseminate misinformation and agitate online discussion. While researchers have developed sophisticated methods to detect abuse, novel bots with diverse behaviors evade detection. We show that different types of bots are characterized by different behavioral features. As a result, supervised learning techniques suffer severe performance deterioration when attempting to detect behaviors not observed in the training data. Moreover, tuning these models to recognize novel bots requ…
In this paper, a method of modeling the dynamics of electronic discussions is proposed based on the so called FOPDT model (First Order Plus Dead Time) known from the process control. Knowledge of the model points to possibility of estimating dynamic movements in discussions as well as understanding and designing their maintaining and guidance. Real discussions are processed.
This paper considers the problem of estimating exposure to information in a social network. Given a piece of information (e.g., a URL of a news article on Facebook, a hashtag on Twitter), our aim is to find the fraction of people on the network who have been exposed to it. The exact value of exposure to a piece of information is determined by two features: the structure of the underlying social network and the set of people who shared the piece of information. Often, both features are not publicly available (i.e., access to the two features is limited only to the internal administrators of the…
With the increasing popularity of social means to satisfy information needs using Social Media (e.g., Social Media Question Asking, SMQA) or Social Information Retrieval approaches, this paper tries to identify types of information needs which are inherently social and therefore better suited for those techniques. We describe an experiment where prominent websites from various content categories are used to represent their respective content area and allow to correlate attributes of the content areas. The underlying assumption is that successful websites for focused content areas perfectly ali…
University of Cambridge（剑桥大学）；University of Bath（巴斯大学）
Profile images on social networks are users' opportunity to present themselves and to affect how others judge them. We examine what Facebook images say about users' perceived and measured intelligence. 1,122 Facebook users completed a matrices intelligence test and shared their current Facebook profile image. Strangers also rated the images for perceived intelligence. We use automatically extracted image features to predict both measured and perceived intelligence. Intelligence estimation from images is a difficult task even for humans, but experimental results show that human accuracy can be …
Even though the concept of tie strength is central in social network analysis, it is difficult to quantify how strong social ties are. One typical way of estimating tie strength in data-driven studies has been to simply count the total number or duration of contacts between two people. This, however, disregards many features that can be extracted from the rich data sets used for social network reconstruction. Here, we focus on contact data with temporal information. We systematically study how features of the contact time series are related to topological features usually associated with tie s…
Department of Sociology, Cornell University（康奈尔大学社会学系）；Department of Sociology, Dartmouth College（达特茅斯学院社会学系）；Qatar Computing Research Institute（卡塔尔计算研究所）
In online social networks, it is common to use predictions of node categories to estimate measures of homophily and other relational properties. However, online social network data often lacks basic demographic information about the nodes. Researchers must rely on predicted node attributes to estimate measures of homophily, but little is known about the validity of these measures. We show that estimating homophily in a network can be viewed as a dyadic prediction problem, and that homophily estimates are unbiased when dyad-level residuals sum to zero in the network. Node-level prediction model…
University of Sheffield（谢菲尔德大学）；University of Melbourne（墨尔本大学）；University of Warwick（华威大学）
Social media tend to be rife with rumours while new reports are released piecemeal during breaking news. Interestingly, one can mine multiple reactions expressed by social media users in those situations, exploring their stance towards rumours, ultimately enabling the flagging of highly disputed rumours as being potentially false. In this work, we set out to develop an automated, supervised classifier that uses multi-task learning to classify the stance expressed in each individual tweet in a rumourous conversation as either supporting, denying or questioning the rumour. Using a classifier bas…
In the article a virus transmission model is constructed on a simplified social network. The social network consists of more than 2 million nodes, each representing an inhabitant of Slovenia. The nodes are organised and interconnected according to the real household and elderly-care center distribution, while their connections outside these clusters are semi-randomly distributed and fully-linked. The virus spread model is coupled to the disease progression model. The ensemble approach with the perturbed transmission and disease parameters is used to quantify the ensemble spread, a proxy for th…
The Alan Turing Institute（艾伦·图灵研究所）；The Oxford Internet Institute（牛津互联网研究院）；The George Washington University（乔治·华盛顿大学）；The University of Manchester（曼彻斯特大学）；The University of Surrey（萨里大学）；University of Sheffield（谢菲尔德大学）
The outbreak of COVID-19 has transformed societies across the world as governments tackle the health, economic and social costs of the pandemic. It has also raised concerns about the spread of hateful language and prejudice online, especially hostility directed against East Asia. In this paper we report on the creation of a classifier that detects and categorizes social media posts from Twitter into four classes: Hostility against East Asia, Criticism of East Asia, Meta-discussions of East Asian prejudice and a neutral class. The classifier achieves an F1 score of 0.83 across all four classes.…
Online Social Networks (OSNs) facilitate access to a variety of data allowing researchers to analyze users' behavior and develop user behavioral analysis models. These models rely heavily on the observed data which is usually biased due to the participation inequality. This inequality consists of three groups of online users: the lurkers - users that solely consume the content, the engagers - users that contribute little to the content creation, and the contributors - users that are responsible for creating the majority of the online content. Failing to consider the contribution of all the gro…
Breaking news leads to situations of fast-paced reporting in social media, producing all kinds of updates related to news stories, albeit with the caveat that some of those early updates tend to be rumours, i.e., information with an unverified status at the time of posting. Flagging information that is unverified can be helpful to avoid the spread of information that may turn out to be false. Detection of rumours can also feed a rumour tracking system that ultimately determines their veracity. In this paper we introduce a novel approach to rumour detection that learns from the sequential dynam…
LARODEC, University of Tunis（突尼斯大学LARODEC实验室）；IRISA, University of Rennes 1（雷恩第一大学IRISA研究所）
Nowadays, social networks such as Twitter, Facebook and LinkedIn become increasingly popular. In fact, they introduced new habits, new ways of communication and they collect every day several information that have different sources. Most existing research works fo-cus on the analysis of homogeneous social networks, i.e. we have a single type of node and link in the network. However, in the real world, social networks offer several types of nodes and links. Hence, with a view to preserve as much information as possible, it is important to consider so-cial networks as heterogeneous and uncertain…
University of Southern California（南加州大学）；Viterbi School of Engineering（维特比工程学院）
Recent years have witnessed the rise of misinformation campaigns that spread specific narratives on social media to manipulate public opinions on different areas, such as politics and healthcare. Consequently, an effective and efficient automatic methodology to estimate the influence of the misinformation on user beliefs and activities is needed. However, existing works on misinformation impact estimation either rely on small-scale psychological experiments or can only discover the correlation between user behaviour and misinformation. To address these issues, in this paper, we build up a caus…
Universidade Federal Fluminense（弗鲁米嫩塞联邦大学）；Dell Technologies（戴尔科技集团）
The widespread of false information is a rising concern worldwide with critical social impact, inspiring the emergence of fact-checking organizations to mitigate misinformation dissemination. However, human-driven verification leads to a time-consuming task and a bottleneck to have checked trustworthy information at the same pace they emerge. Since misinformation relates not only to the content itself but also to other social features, this paper addresses automatic misinformation checking in social networks from a multimodal perspective. Moreover, as simply naming a piece of news as incorrect…
Influence analysis is a fundamental problem in social network analysis and mining. The important applications of the influence analysis in social network include influence maximization for viral marketing, finding the most influential nodes, online advertising, etc. For many of these applications, it is crucial to evaluate the influenceability of a node. In this paper, we study the problem of evaluating influenceability of nodes in social network based on the widely used influence spread model, namely, the independent cascade model. Since this problem is #P-complete, most existing work is base…
It has been insufficiently explored how to perform density-based clustering by exploiting textual attributes on social media. In this paper, we aim at discovering a social point-of-interest (POI) boundary, formed as a convex polygon. More specifically, we present a new approach and algorithm, built upon our earlier work on social POI boundary estimation (SoBEst). This SoBEst approach takes into account both relevant and irrelevant records within a geographic area, where relevant records contain a POI name or its variations in their text field. Our study is motivated by the following empirical …
KAIST AI（韩国科学技术院人工智能研究院）；KAIST AI & EE（韩国科学技术院人工智能与电子工程学院）；Department of AI, Yonsei University（延世大学人工智能系）
Influence maximization (IM) is one of the most important problems in social network analysis. Its objective is to find a given number of seed nodes that maximize the spread of information through a social network. Since it is an NP-hard problem, many approximate/heuristic methods have been developed, and a number of them repeat Monte Carlo (MC) simulations over and over to reliably estimate the influence (i.e., the number of infected nodes) of a seed set. In this work, we present an inductive machine learning method, called Monte Carlo Simulator (MONSTOR), for estimating the influence of given…
The present study uses the Kohonen self organizing map (SOM) to represent the popularity patterns of Myspace music artists from their attributes on the platform and their position in the social network. The method is applied to cluster the profiles (the nodes of the social network) and the best friendship links (the edges). It shows that the SOM is an efficient tool to interpret the complex links between the audience and the influence of the musicians. It finally provides a robust classifier of the online social network behaviors.
This paper attempt to study the effectiveness of text representation schemes on two tasks namely: User Aggression and Fact Detection from the social media contents. In User Aggression detection, The aim is to identify the level of aggression from the contents generated in the Social media and written in the English, Devanagari Hindi and Romanized Hindi. Aggression levels are categorized into three predefined classes namely: `Non-aggressive`, `Overtly Aggressive`, and `Covertly Aggressive`. During the disaster-related incident, Social media like, Twitter is flooded with millions of posts. In su…
When randomized ensembles such as bagging or random forests are used for binary classification, the prediction error of the ensemble tends to decrease and stabilize as the number of classifiers increases. However, the precise relationship between prediction error and ensemble size is unknown in practice. In the standard case when classifiers are aggregated by majority vote, the present work offers a way to quantify this convergence in terms of "algorithmic variance," i.e. the variance of prediction error due only to the randomized training algorithm. Specifically, we study a theoretical upper …
Emory University（埃默里大学）；USC Information Sciences Institute（南加州大学信息科学研究所）
Cyberbullying is a pervasive problem in online communities. To identify cyberbullying cases in large-scale social networks, content moderators depend on machine learning classifiers for automatic cyberbullying detection. However, existing models remain unfit for real-world applications, largely due to a shortage of publicly available training data and a lack of standard criteria for assigning ground truth labels. In this study, we address the need for reliable data using an original annotation framework. Inspired by social sciences research into bullying behavior, we characterize the nuanced p…
Stanford University（斯坦福大学）；Max Planck Institute SWS（马克斯·普朗克软件系统研究所）
We propose a computational framework for identifying linguistic aspects of politeness. Our starting point is a new corpus of requests annotated for politeness, which we use to evaluate aspects of politeness theory and to uncover new interactions between politeness markers and context. These findings guide our construction of a classifier with domain-independent lexical and syntactic features operationalizing key components of politeness theory, such as indirection, deference, impersonalization and modality. Our classifier achieves close to human performance and is effective across domains. We …
Inria（法国国家信息与自动化研究所）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；Università degli Studi di Milano（米兰大学）；University of Insubria（因苏布里亚大学）；Aalto University（阿尔托大学）
In the problem of edge sign prediction, we are given a directed graph (representing a social network), and our task is to predict the binary labels of the edges (i.e., the positive or negative nature of the social relationships). Many successful heuristics for this problem are based on the troll-trust features, estimating at each node the fraction of outgoing and incoming positive/negative edges. We show that these heuristics can be understood, and rigorously analyzed, as approximators to the Bayes optimal classifier for a simple probabilistic model of the edge labels. We then show that the ma…
The COVID-19 pandemic has caused globally significant impacts since the beginning of 2020. This brought a lot of confusion to society, especially due to the spread of misinformation through social media. Although there were already several studies related to the detection of misinformation in social media data, most studies focused on the English dataset. Research on COVID-19 misinformation detection in Indonesia is still scarce. Therefore, through this research, we collect and annotate datasets for Indonesian and build prediction models for detecting COVID-19 misinformation by considering the…
Social media has recently emerged as a premier method to disseminate information online. Through these online networks, tens of millions of individuals communicate their thoughts, personal experiences, and social ideals. We therefore explore the potential of social media to predict, even prior to onset, Major Depressive Disorder (MDD) in online personas. We employ a crowdsourced method to compile a list of Twitter users who profess to being diagnosed with depression. Using up to a year of prior social media postings, we utilize a Bag of Words approach to quantify each tweet. Lastly, we leverag…
Online social networks are known to be demographically biased. Currently there are questions about what degree of representativity of the physical population they have, and how population biases impact user-generated content. In this paper we focus on centralism, a problem affecting Chile. Assuming that local differences exist in a country, in terms of vocabulary, we built a methodology based on the vector space model to find distinctive content from different locations, and use it to create classifiers to predict whether the content of a micro-post is related to a particular location, having …
Online social networks (OSNs) have become the main medium for connecting people, sharing knowledge and information, and for communication. The social connections between people using these OSNs are formed as virtual links (e.g., friendship and following connections) that connect people. These links are the heart of today's OSNs as they facilitate all of the activities that the members of a social network can do. However, many of these networks suffer from noisy links, i.e., links that do not reflect a real relationship or links that have a low intensity, that change the structure of the networ…
Cliques are defined as complete graphs or subgraphs; they are the strongest form of cohesive subgroup, and are of interest in both social science and engineering contexts. In this paper we show how to efficiently estimate the distribution of clique sizes from a probability sample of nodes obtained from a graph (e.g., by independence or link-trace sampling). We introduce two types of unbiased estimators, one of which exploits labeling of sampled nodes neighbors and one of which does not require this information. We compare the estimators on a variety of real-world graphs and provide suggestions…
The main subject studied in this dissertation is a multi-layered social network (MSN) and its analysis. One of the crucial problems in multi-layered social network analysis is community extraction. To cope with this problem the CLECC measure (Cross Layered Edge Clustering Coefficient) was proposed in the thesis. It is an edge measure which expresses how much the neighbors of two given users are similar each other. Based on this measure the CLECC algorithm for community extraction in the multi-layered social networks was designed. The algorithm was tested on the real single-layered social netwo…
Fraunhofer SIT at CheckThat! 2023: Mixing Single-Modal Classifiers to Estimate the Check-Worthiness of Multi-Modal Tweets
Fraunhofer Institute for Secure Information Technology SIT（弗劳恩霍夫安全信息技术研究所）；ATHENE - National Research Center for Applied Cybersecurity（ATHENE——国家应用网络安全研究中心）
With the rise of Social Media, people obtain and share information almost instantly on a 24/7 basis. Many research areas have tried to gain valuable insights from these large volumes of freely available user generated content. With the goal of extracting knowledge from social media streams that might be useful in the context of intelligent transportation systems and smart cities, we designed and developed a framework that provides functionalities for parallel collection of geo-located tweets from multiple pre-defined bounding boxes (cities or regions), including filtering of non-complying twee…
Many epidemic models approximate social contact behavior by assuming random mixing within mixing groups (e.g., homes, schools and workplaces). The effect of more realistic social network structure on estimates of epidemic parameters is an open area of exploration. We develop a detailed statistical model to estimate the social contact network within a high school using friendship network data and a survey of contact behavior. Our contact network model includes classroom structure, longer durations of contacts to friends than nonfriends and more frequent contacts with friends, based on reports i…
Télécom SudParis（南巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）
Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been addressed more frequently, biases arising from trained classifiers have not yet been a matter of concern. Here, we first introduce a transfer learning approach for hate speech detection based on an existing pre-trained language model called BERT and evaluate the proposed model on two publicly available datasets annotated for racism, sexism, hate or offensive conten…
Université de Tunis（突尼斯大学）；Université de Rennes I（雷恩第一大学）；Centre d’Etude et de Recherche des Télécommunications（电信研究中心）；Université de Carthage（迦太基大学）
Social messages classification is a research domain that has attracted the attention of many researchers in these last years. Indeed, the social message is different from ordinary text because it has some special characteristics like its shortness. Then the development of new approaches for the processing of the social message is now essential to make its classification more efficient. In this paper, we are mainly interested in the classification of social messages based on their spreading on online social networks (OSN). We proposed a new distance metric based on the Dynamic Time Warping dist…
Santa Fe Institute（圣塔菲研究所）；Center for the Study of Complex Systems（复杂系统研究中心）；University of Michigan（密歇根大学）；Vermont Complex Systems Center（佛蒙特复杂系统中心）；University of Vermont（佛蒙特大学）
Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution to this growing global problem is citizen-generated counter speech where citizens actively engage in hate-filled conversations to attempt to restore civil non-polarized discourse. However, its actual effectiveness in curbing the spread of hatred is unknown and hard to quantify. One major obstacle to researching this question is a lack of large labeled data sets for training automated classifiers to identify counter speech. Here we made use of…
