Search

Social media and digital platforms allow us to express our opinions freely and easily to a vast number of people. In this study, we examine whether there are gender-based differences in how communication happens via Twitter in regard to soccer. Soccer is one of the most popular sports, and therefore, on social media, it engages a diverse audience regardless of their technical knowledge. We collected Twitter data for three months (March-June) for English and Portuguese that contains 9.5 million Tweets related to soccer, and only 18.38% tweets were identified as belonging to women, highlighting a possible gender gap already in the number of people who participated actively in this topic. We then conduct a fine-grained text-level and network-level analysis to identify the gender differences that might exist while communicating on Twitter. Our results show that women express their emotions more intensely than men, regardless of the differences in volume. The network generated from Portuguese has lower homophily than English. However, this difference in homophily does not impact how females express their emotions and sentiments, suggesting that these aspects are inherent norms or characteristics of genders. Our study unveils more gaps through qualitative and quantitative analyses, highlighting the importance of examining and reporting gender gaps in online communication to create a more inclusive space where people can openly share their opinions.

In this paper we introduce a new, fast, degree-preserving rewiring algorithm for altering the assortativity of complex networks, which we call \textit{Fast total link (FTL) rewiring} algorithm. Commonly used existing algorithms require a large number of iterations, in particular in the case of large dense networks. This can especially be problematic when we wish to study ensembles of networks. In this work we aim to overcome aforementioned scalability problems by performing a rewiring of all edges at once to achieve a very high assortativity value before rewiring samples of edges at once to reduce this high assortativity value to the target value. The proposed method performs better than existing methods by several orders of magnitude for a range of structurally diverse complex networks, both in terms of the number of iterations taken, and time taken to reach a given assortativity value. Here we test our proposed algorithm on networks with up to $100,000$ nodes and around $750,000$ edges and find that the relative improvements in speed remain, showing that the algorithm is both efficient and scalable., Comment: 13 pages, 14 figures

Graph neural networks (GNNs) have shown promise in addressing graph-related problems, including node classification. However, conventional GNNs assume an even distribution of data across classes, which is often not the case in real-world scenarios, where certain classes are severely underrepresented. This leads to suboptimal performance of standard GNNs on imbalanced graphs. In this paper, we introduce a unique approach that tackles imbalanced classification on graphs by considering graph heterophily. We investigate the intricate relationship between class imbalance and graph heterophily, revealing that minority classes not only exhibit a scarcity of samples but also manifest lower levels of homophily, facilitating the propagation of erroneous information among neighboring nodes. Drawing upon this insight, we propose an efficient method, called Fast Im-GBK, which integrates an imbalance classification strategy with heterophily-aware GNNs to effectively address the class imbalance problem while significantly reducing training time. Our experiments on real-world graphs demonstrate our model's superiority in classification performance and efficiency for node classification tasks compared to existing baselines., Comment: Accepted by Twelfth International Conference on Complex Networks & Their Applications

Community detection in Social Networks is associated with finding and grouping the most similar nodes inherent in the network. These similar nodes are identified by computing tie strength. Stronger ties indicates higher proximity shared by connected node pairs. This work is motivated by Granovetter's argument that suggests that strong ties lies within densely connected nodes and the theory that community cores in real-world networks are densely connected. In this paper, we have introduced a novel method called \emph{Disjoint Community detection using Cascades (DCC)} which demonstrates the effectiveness of a new local density based tie strength measure on detecting communities. Here, tie strength is utilized to decide the paths followed for propagating information. The idea is to crawl through the tuple information of cascades towards the community core guided by increasing tie strength. Considering the cascade generation step, a novel preferential membership method has been developed to assign community labels to unassigned nodes. The efficacy of $DCC$ has been analyzed based on quality and accuracy on several real-world datasets and baseline community detection algorithms., Comment: To be published in CHSN-2022

Active Learning (AL) techniques have proven to be highly effective in reducing data labeling costs across a range of machine learning tasks. Nevertheless, one known challenge of these methods is their potential to introduce unfairness towards sensitive attributes. Although recent approaches have focused on enhancing fairness in AL, they tend to reduce the model's accuracy. To address this issue, we propose a novel strategy, named Fair Active Learning using fair Clustering, Uncertainty, and Representativeness (FAL-CUR), to improve fairness in AL. FAL-CUR tackles the fairness problem in AL by combining fair clustering with an acquisition function that determines which samples to query based on their uncertainty and representativeness scores. We evaluate the performance of FAL-CUR on four real-world datasets, and the results demonstrate that FAL-CUR achieves a 15% - 20% improvement in fairness compared to the best state-of-the-art method in terms of equalized odds while maintaining stable accuracy scores. Furthermore, an ablation study highlights the crucial roles of fair clustering in preserving fairness and the acquisition function in stabilizing the accuracy performance.

In recent years, designing fairness-aware methods has received much attention in various domains, including machine learning, natural language processing, and information retrieval. However, understanding structural bias and inequalities in social networks and designing fairness-aware methods for various research problems in social network analysis (SNA) have not received much attention. In this work, we highlight how the structural bias of social networks impacts the fairness of different SNA methods. We further discuss fairness aspects that should be considered while proposing network structure-based solutions for different SNA problems, such as link prediction, influence maximization, centrality ranking, and community detection. This paper clearly highlights that very few works have considered fairness and bias while proposing solutions; even these works are mainly focused on some research topics, such as link prediction, influence maximization, and PageRank. However, fairness has not yet been addressed for other research topics, such as influence blocking and community detection. We review state-of-the-art for different research topics in SNA, including the considered fairness constraints, their limitations, and our vision. This paper also covers evaluation metrics, available datasets, and synthetic network generating models used in such studies. Finally, we highlight various open research directions that require researchers' attention to bridge the gap between fairness and SNA.

Fairness-aware learning aims at satisfying various fairness constraints in addition to the usual performance criteria via data-driven machine learning techniques. Most of the research in fairness-aware learning employs the setting of fair-supervised learning. However, many dynamic real-world applications can be better modeled using sequential decision-making problems and fair reinforcement learning provides a more suitable alternative for addressing these problems. In this article, we provide an extensive overview of fairness approaches that have been implemented via a reinforcement learning (RL) framework. We discuss various practical applications in which RL methods have been applied to achieve a fair solution with high accuracy. We further include various facets of the theory of fair reinforcement learning, organizing them into single-agent RL, multi-agent RL, long-term fairness via RL, and offline learning. Moreover, we highlight a few major issues to explore in order to advance the field of fair-RL, namely - i) correcting societal biases, ii) feasibility of group fairness or individual fairness, and iii) explainability in RL. Our work is beneficial for both researchers and practitioners as we discuss articles providing mathematical guarantees as well as articles with empirical studies on real-world problems.

Elections are the backbone of any democratic country, where voters elect the candidates as their representatives. The emergence of social networking sites has provided a platform for political parties and their candidates to connect with voters in order to spread their political ideas. Our study aims to use Twitter in assessing the outcome of Delhi Assembly elections held in 2020, using a bi-level approach, i.e., concerning political parties and their candidates. We analyze the correlation of election results with the activities of different candidates and parties on Twitter, and the response of voters on them, especially the mentions and sentiment of voters towards a party. The Twitter profiles of the candidates are compared both at the party level as well as the candidate level to evaluate their association with the outcome of the election. We observe that the number of followers and the replies to the tweets of candidates are good indicators for predicting actual election outcome. However, we observe that the number of tweets mentioning a party and the sentiment of voters towards the party shown in tweets are not aligned with the election result. We also use machine learning models on various features such as linguistic, word embeddings and moral dimensions for predicting the election result (win or lose). The random forest model using tweet features provides promising results for predicting if the tweet belongs to a winning or losing candidate., Comment: 15 pages, 11 figures and 2 tables

The modern educational ecosystem is not one-size fits all. Scholars are accustomed to personalization in their everyday life and expect the same from education systems. Additionally, the COVID-19 pandemic placed us all in an acute teaching and learning laboratory experimentation which now creates expectations of self-paced learning and interactions with focused educational materials. Consequently, we examine how learning objectives can be achieved through a learning platform that offers content choices and multiple modalities of engagement to support self-paced learning, and propose an approach to personalized education based on network science. This framework brings the attention to learning experiences, rather than teaching experiences, by providing the learner engagement and content choices supported by a network of knowledge, based on and driven by individual skills and goals. We conclude with a discussion of a prototype of such a learning platform, called CHUNK Learning.

We construct a network of 1.6 million nodes from banking transactions of users of Rabobank. We assign two weights on each edge, which are the aggregate transferred amount and the total number of transactions between the users from the year 2010 to 2020. We present a detailed analysis of the unweighted and both weighted networks by examining their degree, strength, and weight distributions, as well as the topological assortativity and weighted assortativity, clustering, and weighted clustering, together with correlations between these quantities. We further study the meso-scale properties of the networks and compare them to a randomized reference system. We also analyze the characteristics of nodes and edges using centrality measures to understand their roles in the money transaction system. This will be the first publicly shared dataset of intra-bank transactions, and this work highlights the unique characteristics of banking transaction networks with other scale-free networks.

Rankings of people and items has been highly used in selection-making, match-making, and recommendation algorithms that have been deployed on ranging of platforms from employment websites to searching tools. The ranking position of a candidate affects the amount of opportunities received by the ranked candidate. It has been observed in several works that the ranking of candidates based on their score can be biased for candidates belonging to the minority community. In recent works, the fairness-aware representative ranking was proposed for computing fairness-aware re-ranking of results. The proposed algorithm achieves the desired distribution of top-ranked results with respect to one or more protected attributes. In this work, we highlight the bias in fairness-aware representative ranking for an individual as well as for a group if the group is sub-active on the platform. We define individual unfairness and group unfairness and propose methods to generate ideal individual and group fair representative ranking if the universal representation ratio is known or unknown. The simulation results show the quantified analysis of fairness in the proposed solutions. The paper is concluded with open challenges and further directions.

In real-world complex networks, understanding the dynamics of their evolution has been of great interest to the scientific community. Predicting future links is an essential task of social network analysis as the addition or removal of the links over time leads to the network evolution. In a network, links can be categorized as intra-community links if both end nodes of the link belong to the same community, otherwise inter-community links. The existing link-prediction methods have mainly focused on achieving high accuracy for intra-community link prediction. In this work, we propose a network embedding method, called NodeSim, which captures both similarities between the nodes and the community structure while learning the low-dimensional representation of the network. The embedding is learned using the proposed NodeSim random walk, which efficiently explores the diverse neighborhood while keeping the more similar nodes closer in the context of the node. We verify the efficacy of the proposed embedding method over state-of-the-art methods using diverse link prediction. We propose a machine learning model for link prediction that considers both the nodes' embedding and their community information to predict the link between two given nodes. Extensive experimental results on several real-world networks demonstrate the effectiveness of the proposed framework for both inter and intra-community link prediction.

For decades, complex networks, such as social networks, biological networks, chemical networks, technological networks, have been used to study the evolution and dynamics of different kinds of complex systems. These complex systems can be better described using weighted links as binary connections do not portray the complete information of the system. All these weighted networks evolve in a different environment by following different underlying mechanics. Researchers have worked on unraveling the evolving phenomenon of weighted networks to understand their structure and dynamics. In this chapter, we discuss the evolution of weighted networks and evolving models to generate different types of synthetic weighted networks, including undirected, directed, signed, multilayered, community, and core-periphery structured weighted networks. We further discuss various properties held by generated synthetic networks and their similarity with real-world weighted networks.

In complex networks, each node has some unique characteristics that define the importance of the node based on the given application-specific context. These characteristics can be identified using various centrality metrics defined in the literature. Some of these centrality measures can be computed using local information of the node, such as degree centrality and semi-local centrality measure. Others use global information of the network like closeness centrality, betweenness centrality, eigenvector centrality, Katz centrality, PageRank, and so on. In this survey, we discuss these centrality measures and the state of the art literature that includes the extension of centrality measures to different types of networks, methods to update centrality values in dynamic networks, methods to identify top-k nodes, approximation algorithms, open research problems related to the domain, and so on. The paper is concluded with a discussion on application specific centrality measures that will help to choose a centrality measure based on the network type and application requirements.

Due to the extensive role of social networks in social media, it is easy for people to share the news, and it spreads faster than ever before. These platforms also have been exploited to share the rumor or fake information, which is a threat to society. One method to reduce the impact of fake information is making people aware of the correct information based on hard proof. In this work, first, we propose a propagation model called Competitive Independent Cascade Model with users' Bias (CICMB) that considers the presence of strong user bias towards different opinions, believes, or political parties. We further propose a method, called $k-TruthScore$, to identify an optimal set of truth campaigners from a given set of prospective truth campaigners to minimize the influence of rumor spreaders on the network. We compare $k-TruthScore$ with state of the art methods, and we measure their performances as the percentage of the saved nodes (nodes that would have believed in the fake news in the absence of the truth campaigners). We present these results on a few real-world networks, and the results show that $k-TruthScore$ method outperforms baseline methods., Comment: Accepted in CSoNet 2020

Do studies show that physical and online students' social networks support education? Analyzing interactions between students in schools and universities can provide a wealth of information. Studies on students' social networks can help us understand their behavioral dynamics, the correlation between their friendships and academic performance, community and group formation, information diffusion, and so on. Educational goals and holistic development of students with various academic abilities and backgrounds can be achieved by incorporating the findings attained by the studies in terms of knowledge propagation in classroom and spread of delinquent behaviors. Moreover, we use Social Network Analysis (SNA) to identify isolated students, ascertain the group study culture, analyze the spreading of various habits like smoking, drinking, and so on. In this paper, we present a review of the research showing how analysis of students' social networks can help us identify how improved educational methods can be used to make learning more inclusive at both school and university levels and achieve holistic development of students through expansion of their social networks, as well as control the spread of delinquent behaviors., Comment: Huso 2019

For network scientists, it has always been an interesting problem to identify the influential nodes in a given network. The k-shell decomposition method is a widely used method which assigns a shell-index value to each node based on its influential power. The k-shell method requires the global information of the network to compute the shell-index of a node that is infeasible for large-scale real-world dynamic networks. In this work, we propose a method to estimate the shell-index of a node using its local information. We also propose hill-climbing based approach to hit the top-ranked nodes in a small number of steps. We further discuss a method to estimate the rank of a node based on the proposed estimator., Comment: The preliminary version of this paper is submitted in ASONAM 2018(Ph.D. Forum track) and it is under review

In real world complex networks, the importance of a node depends on two important parameters: 1. characteristics of the node, and 2. the context of the given application. The current literature contains several centrality measures that have been defined to measure the importance of a node based on the given application requirements. These centrality measures assign a centrality value to each node that denotes its importance index. But in real life applications, we are more interested in the relative importance of the node that can be measured using its centrality rank based on the given centrality measure. To compute the centrality rank of a node, we need to compute the centrality value of all the nodes and compare them to get the rank. This process requires the entire network. So, it is not feasible for real-life applications due to the large size and dynamic nature of real world networks. In the present project, we aim to propose fast and efficient methods to estimate the global centrality rank of a node without computing the centrality value of all nodes. These methods can be further extended to estimate the rank without having the entire network. The proposed methods use the structural behavior of centrality measures, sampling techniques, or the machine learning models. In this work, we also discuss how to apply these methods for degree and closeness centrality rank estimation.

Closeness centrality is one way of measuring how central a node is in the given network. The closeness centrality measure assigns a centrality value to each node based on its accessibility to the whole network. In real life applications, we are mainly interested in ranking nodes based on their centrality values. The classical method to compute the rank of a node first computes the closeness centrality of all nodes and then compares them to get its rank. Its time complexity is $O(n \cdot m + n)$, where $n$ represents total number of nodes, and $m$ represents total number of edges in the network. In the present work, we propose a heuristic method to fast estimate the closeness rank of a node in $O(\alpha \cdot m)$ time complexity, where $\alpha = 3$. We also propose an extended improved method using uniform sampling technique. This method better estimates the rank and it has the time complexity $O(\alpha \cdot m)$, where $\alpha \approx 10-100$. This is an excellent improvement over the classical centrality ranking method. The efficiency of the proposed methods is verified on real world scale-free social networks using absolute and weighted error functions.

Most real world dynamic networks are evolved very fast with time. It is not feasible to collect the entire network at any given time to study its characteristics. This creates the need to propose local algorithms to study various properties of the network. In the present work, we estimate degree rank of a node without having the entire network. The proposed methods are based on the power law degree distribution characteristic or sampling techniques. The proposed methods are simulated on synthetic networks, as well as on real world social networks. The efficiency of the proposed methods is evaluated using absolute and weighted error functions. Results show that the degree rank of a node can be estimated with high accuracy using only $1\%$ samples of the network size. The accuracy of the estimation decreases from high ranked to low ranked nodes. We further extend the proposed methods for random networks and validate their efficiency on synthetic random networks, that are generated using Erd\H{o}s-R\'{e}nyi model. Results show that the proposed methods can be efficiently used for random networks as well.