Search

Copyright of Ciencias Administrativas is the property of Universidad Nacional de La Plata and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Brand marketers routinely allocate a significant portion of their budget to sponsorship. Predicting whether those investment decisions will result in a successful, long-term partnership, however, remains a challenge. In an attempt to alleviate this issue, a dataset of more than 5,800 sponsorships has been compiled that investigates the influence of a variety of factors on the probability of sponsor retention. In addition to its contribution to the sponsorship-linked marketing literature, the model can be utilized by managers to predict the probability of a sponsor being retained and time the sponsor will remain with the property, representing a novel managerial contribution. [ABSTRACT FROM AUTHOR]

AbstractStatistical network models are useful for understanding the underlying formation mechanism and characteristics of complex networks. However, statistical models for signed networks have been largely unexplored. In signed networks, there exist both positive (e.g., like, trust) and negative (e.g., dislike, distrust) edges, which are commonly seen in real-world scenarios. The positive and negative edges in signed networks lead to unique structural patterns, which pose challenges for statistical modeling. In this article, we introduce a statistically principled latent space approach for modeling signed networks and accommodating the well-known balance theory, that is, “the enemy of my enemy is my friend” and “the friend of my friend is my friend.” The proposed approach treats both edges and their signs as random variables, and characterizes the balance theory with a novel and natural notion of population-level balance. This approach guides us towards building a class of balanced inner-product models, and toward developing scalable algorithms via projected gradient descent to estimate the latent variables. We also establish non-asymptotic error rates for the estimates, which are further verified through simulation studies. In addition, we apply the proposed approach to an international relation network, which provides an informative and interpretable model-based visualization of countries during World War II. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work. [ABSTRACT FROM AUTHOR]

This work analyses the relationship between Leader and Member Exchange (LMX) and Co-worker Exchanges in a triad. Using a large sample of 1579 observations, our work provides theoretical and empirical support to the idea that the quality of the relationship between two co-workers, rather than being an objective characteristic of the dyad, is in fact an individual variable affected by the perception that each co-worker has of the relationship each member of the same dyad holds with their common leader. Our results, based on 1580 observations, offer some new insights and extend the well-known Balance Theory demonstrating that it is not only the similarity and dissimilarity in their LMX, what determines co-workers' relationships but also the individual perception of own's LMX. Furthermore, we also point at the relevance of the contingent effect played by the average LMX at the team level and the level of differentiation that the leader holds at the team level. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Marketing & Marketing Research / Pazarlama ve Pazarlama Araştırmaları Dergisi is the property of Pazarlama & Pazarlama Arastirmalari Dernegi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Social media has a profound impact on the formation of end-users' social, economic, and political views. Unfortunately, some advertisement agencies and miscreants use fake and misleading reviews to influence people's opinions on their political and business interests. These fake reviews are often posted using fake profiles to conceal the identity of the perpetrator. Such fake reviews are spread on social media platforms through Sockpuppets and Crowdturfing based fake accounts. This paper proposes the Communal Influence Propagation Framework (CIPF), which identifies fake accounts by analysing the essential features set from individual user profile, linguistic, and group profiles (network) feature in userspace. Initially, CIPF scrutinises individual user profile features, group profiles (network) features, and linguistic features to generate the feature vector of the userspace. The CIPF framework then uses the Influence, Homophily and Balance theory of Social Media Mining (SMM) to enrich the malicious user space as an influential index. Additionally, the Jaccard coefficient evaluates the similarity index vector over the influential negative node, identifies Sockpuppet nodes, and generates a negative propagation belonging matrix. The CIPF framework amalgamates influence-based two-tier verification of malicious nodes, the first being the Sockpuppet Detection Phase (IB-SPD) and the second being the Convolutional Neural Network (CNN) based influence-based Crowdturfing Community (IB-CFC). The CIPF framework is evaluated based on the classification performance of Sockpuppet nodes, modularity, and normalised mutual information of the structured crowdturfing community. As a result, the CIPF achieves an approximate 98% accuracy for classifying Sockpuppet nodes and a structured 0.94 modular and 0.91 informative crowdturfing community. [ABSTRACT FROM AUTHOR]

The Chinese government has developed a complicated online censorship regime targeting various media with diversified techniques. Prior literature has argued that the censorship system enjoys general support in China. However, how Chinese people perceive heterogeneous online censorship mechanisms and the corresponding censored objects remains unclear. This study focused on two different online censorship mechanisms in China: the Great Fire Wall and citizen reporting. Using survey data collected in China in 2019, we established two path models to investigate the relationships between perceived media effects, attitudes toward online censorship, desire for censored information, and media being surveilled by each censorship mechanism. Our findings have important implications for understanding the complexity and nuances in censorship-related attitudes in China. [ABSTRACT FROM AUTHOR]

The purpose of this research is to understand the process of attitudinal changes towards a brand in crisis and the brand's communication around the crisis by utilising balance theory and brand personality. Four crisis case studies were selected and data was collected from brands' Twitter platforms on either side of the crisis event horizon. Results demonstrate an opportunity to update the balance theory approach in a crisis by considering the type of crisis (product harm vs. moral harm) relative to brand personality (brand competence vs. brand character). Balance theory helps explain how consumer attitude changes occur through a crisis. Further, the mapping of brand communications in social media over four selected case studies show that brand personality identity can change as a result of a crisis and demonstrate how brand managers can actively frame their online communication to help the brand to recover more effectively from a crisis. [ABSTRACT FROM AUTHOR]

Signed networks and balance theory provide a natural setting for real-world scenarios that show polarization dynamics, positive/negative relationships and political partisanship. For example, they have been proven effective in studying the increasing polarization of the votes in the two chambers of the U.S. Congress from World War II on Andris, Lee, Hamilton, Martino, Gunning & Selden (2015, PLoS ONE , 10, 1–14) and Aref & Neal (2020, Sci. Rep. , 10, 1–10). To provide further insights into this particular case study, we propose the application of a pipeline to analyze and visualize a signed graphs configuration based on the exploitation of the corresponding Laplacian matrix spectral properties. The overall methodology is comparable with others based on the frustration index, but it has at least two main advantages: first, it requires a much lower computational cost and second, it allows for a quantitative and visual assessment of how arbitrarily small subgraphs (even single nodes) contribute to the overall balance (or unbalance) of the network. The proposed pipeline allows the exploration of polarization dynamics shown by the U.S. Congress from 1945 to 2020 at different resolution scales. In fact, we are able to spot and point out the influence of some (groups of) congressmen in the overall balance, as well as to observe and explore polarizations evolution of both chambers across the years. [ABSTRACT FROM AUTHOR]

AbstractBalance theory has advanced with interdisciplinary contributions from social science, physical science, engineering, and mathematics. The common focus of attention is social networks in which every individual has either a positive or negative, cognitive or emotional, appraisal of every other individual. The current frontier of work on balance theory is a hunt for a dynamical model that predicts the temporal evolution of any such appraisal network to a particular structure in the complete set of balanced networks allowed by the theory. Finding such a model has proved to be a difficult problem. In this article, we contribute a parsimonious solution of the problem that explicates the conditions under which a network will evolve either to a set of mutually antagonistic cliques or to an asymmetric structure that allows agreement, cooperation, and compromise among cliques.

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Signed network embedding is an approach to learning low-dimensional representations of nodes in signed networks with both positive and negative links, which facilitates downstream tasks such as link prediction with general data mining frameworks. Due to the distinct properties and significant added value of negative links, existing signed network embedding methods usually design dedicated methods based on social theories such as balance theory and status theory. However, existing signed network embedding methods ignore the characteristics of multiple facets of each node and mix them up in one single representation, which limits the ability to capture the fine-grained attentions between node pairs. In this paper, we propose MUSE , a MU lti-faceted attention-based S igned network E mbedding framework to tackle this problem. Specifically, a joint intra- and inter-facet attention mechanism is introduced to aggregate fine-grained information from neighbor nodes. Moreover, balance theory is also utilized to guide information aggregation from multi-order balanced and unbalanced neighbors. Experimental results on four real-world signed network datasets demonstrate the effectiveness of our proposed framework. [ABSTRACT FROM AUTHOR]

Current machine learning-based methods have achieved inspiring predictions in the scenarios of mono-type and multi-type drug–drug interactions (DDIs), but they all ignore enhancive and depressive pharmacological changes triggered by DDIs. In addition, these pharmacological changes are asymmetric since the roles of two drugs in an interaction are different. More importantly, these pharmacological changes imply significant topological patterns among DDIs. To address the above issues, we first leverage Balance theory and Status theory in social networks to reveal the topological patterns among directed pharmacological DDIs, which are modeled as a signed and directed network. Then, we design a novel graph representation learning model named SGRL-DDI (social theory-enhanced graph representation learning for DDI) to realize the multitask prediction of DDIs. SGRL-DDI model can capture the task-joint information by integrating relation graph convolutional networks with Balance and Status patterns. Moreover, we utilize task-specific deep neural networks to perform two tasks, including the prediction of enhancive/depressive DDIs and the prediction of directed DDIs. Based on DDI entries collected from DrugBank, the superiority of our model is demonstrated by the comparison with other state-of-the-art methods. Furthermore, the ablation study verifies that Balance and Status patterns help characterize directed pharmacological DDIs, and that the joint of two tasks provides better DDI representations than individual tasks. Last, we demonstrate the practical effectiveness of our model by a version-dependent test, where 88.47 and 81.38% DDI out of newly added entries provided by the latest release of DrugBank are validated in two predicting tasks respectively. [ABSTRACT FROM AUTHOR]

Drawing on the marketing aspects of customer satisfaction, this paper provides insights into the relationship between students’ and lecturers’ satisfaction in a higher education institution. The study critically adopts the logic of relationship marketing, arguing that students’ satisfaction affects lecturers’ job satisfaction. The relationship between students’ and lecturers’ satisfaction is explored using Balance Theory and Herzberg’s Motivation Theory. The Critical Incident Technique is used for data collection through interviews with student-lecturer dyads. The findings indicate that lecturers’ job satisfaction increases when students’ holistic feedback is explicitly shared with lecturers. Hence, investing in the communication of students’ satisfaction enhances lecturers’ job satisfaction. The current work adds a critical perspective to the relationship between lecturers’ and students’ satisfaction. It highlights a reversal of the accepted logic of relationship marketing, arguing that students’ satisfaction affects lecturers’ satisfaction. The methodological contribution of this work offers a new approach to using critical incident analysis techniques in dyads of students and lecturers. [ABSTRACT FROM AUTHOR]

Signed network embedding concentrates on learning fixed-length representations for nodes in signed networks with positive and negative links, which contributes to many downstream tasks in social media, such as link prediction. However, most signed network embedding approaches neglect hierarchical graph pooling in the networks, limiting the capacity to learn genuine signed graph topology. To overcome this limitation, this paper presents a unique deep learning-based Signed network embedding model with Hierarchical Graph Pooling (SHGP). To be more explicit, a hierarchical pooling mechanism has been developed to encode the high-level features of the networks. Moreover, a graph convolution layer is introduced to aggregate both positive and negative information from neighbor nodes, and the concatenation of two parts generates the final embedding of the nodes. Extensive experiments on three large real-world signed network datasets demonstrate the effectiveness and excellence of the proposed method. [ABSTRACT FROM AUTHOR]

Drawing from balance theory, this study examines how publics respond to CSA in terms of their identification with the company and attitude toward the company depending on their balanced state and preexisting company attitude valence. Using real companies, two online experiments were employed by replicating different social issues: abortion and gun legislation. The results showed a greater degree of consumer-company identification and company attitude changes, respectively, when people experience an imbalanced state than a balanced state. The study also showed that control mutuality perception weakened such interactions, suggesting the role of equated bilateral relationships in how publics restore the balanced state. Theoretical and practical implications were discussed. [ABSTRACT FROM AUTHOR]

We apply variations and extensions of structural balance theory to analyze the dynamics of geopolitical relations using data from the virtual world Eve Online. The highly detailed data enable us to study the interplay of alliance size, power, and geographic proximity on the prevalence and conditional behavior of triads built from empirical political alliances. Through our analysis, we reveal the degree to which the behaviors of players conform to the predictions of structural balance theory and whether our augmentations of the theory improve these predictions. In addition to studying the time series of the proportions of triad types, we investigate the conditional changes in triad types and the formation of polarized political coalitions. We find that player behavior largely conforms to the predictions of a multipolar version of structural balance theory that separates strong and weak configurations of balanced and frustrated triads. The high degree of explanatory power of structural balance theory in this context provides strong support for both the theory and the use of virtual worlds in social science research. [ABSTRACT FROM AUTHOR]

Friendship and antipathy exist in concert with one another in real social networks. Despite the role they play in social interactions, antagonistic ties are poorly understood and infrequently measured. One important theory of negative ties that has received relatively little empirical evaluation is balance theory, the codification of the adage "the enemy of my enemy is my friend" and similar sayings. Unbalanced triangles are those with an odd number of negative ties, and the theory posits that such triangles are rare. To test for balance, previous works have used a permutation test on the edge signs. The flaw in this method, however, is that it assumes that negative and positive edges are interchangeable. In reality, they could not be more different. Here, we propose a novel test of balance that accounts for this discrepancy and show that our test is more accurate at detecting balance. Along the way, we prove asymptotic normality of the test statistic under our null model, which is of independent interest. Our case study is a novel dataset of signed networks we collected from 32 isolated, rural villages in Honduras. Contrary to previous results, we find that there is only marginal evidence for balance in social tie formation in this setting. [ABSTRACT FROM AUTHOR]

Published 4 decades ago, "Basking in Reflected Glory: Three (Football) Field Studies" (Cialdini et al., 1976) is the most influential study of sport consumer behavior. This article features re-creations of Studies 1 and 2, exactly 40 years after the original publication. The results of Study 1 were reproduced, with participants more than twice as likely to wear school-affiliated apparel after wins and 55% less likely after losses. The study also extends the BIRGing literature in its investigation of the influence of gender and the effect's salience over time. Study 2's results were not reproduced. However, study participants were significantly more likely to use first-person plural pronouns, providing further empirical evidence of BIRGing behaviors. This article makes a novel contribution to the sport consumer behavior literature by advancing the study of one of the field's most foundational theories and serving as an impetus for future investigations of BIRGing motivations. [ABSTRACT FROM AUTHOR]

A complex network is a powerful tool that enables a complex system in the real world to be represented as a network structure. Due to the heterogeneous edges and nodes implying rich semantic information, network representation has received considerable attention in both research and industrial domain. Over the recent years, the graph convolutional network (GCN) has provided a novel approach for learning network embeddings. However, this primarily supports undirected unsigned networks; that is, it cannot be directly applied to directed signed networks because it is challenging to effectively depict the direction and signs of edges in such models. In this paper, we therefore propose a method for semi-supervised gated spectral convolution in directed signed networks. We first extend the concept of the GCN to directed signed networks, which not only preserves the advantages of the traditional GCN but also properly describes the significance of the directions and signs of the edges. We then innovatively define sign (label) propagation rules in directed signed networks, rendering the networks semi-supervised. Furthermore, we enhance the balance theory to constrain the process of sign propagation to obtain network embedding with better interpretability. To satisfy the needs of large-scale complex networks, we propose a gating mechanism to adaptively forget sign information, which significantly reduces the time-space complexity of the sign propagation process. Finally, we compare the proposed method with state-of-the-art baselines using four real-world data sets for the classical link sign prediction task. Experimental results demonstrate that the proposed method is competitive.

Cancer is commonly known as a disease of the genes. Almost all the studies about cancers are based on finding the effective genes for each cancer and most of the efforts for diagnosing or curing cancer have faced several challenges. From the point of view of complexity, collective behaviors that have emerged from the interactions of many-body systems are not solely describable by knowing about the system’s building blocks (genes) and we cannot understand what happens at a higher level of organization by just knowing how each element works at a lower scale! We know, each gene’s expression affects other genes expression levels and this correlation causes a collective behavior which that alters the expression levels of the genes. In this study, instead of following the common reductionist view, we use the techniques of inverse statistical physics and infer the interaction matrix of the genes. Then, by applying the balance theory, we show the differences between the social behavior of cancer genes and normal genes as a whole. Our results show that the energy distribution of triads formed in the interaction networks behaves in a power-law manner and the energy of the normal network is higher than the cancer network.

Signed network embedding concentrates on learning fixed-length representations for nodes in signed networks with positive and negative links, which contributes to many downstream tasks in social media, such as link prediction. However, most signed network embedding approaches neglect hierarchical graph pooling in the networks, limiting the capacity to learn genuine signed graph topology. To overcome this limitation, this paper presents a unique deep learning-based Signed network embedding model with Hierarchical Graph Pooling (SHGP). To be more explicit, a hierarchical pooling mechanism has been developed to encode the high-level features of the networks. Moreover, a graph convolution layer is introduced to aggregate both positive and negative information from neighbor nodes, and the concatenation of two parts generates the final embedding of the nodes. Extensive experiments on three large real-world signed network datasets demonstrate the effectiveness and excellence of the proposed method.

Genes communicate with each other through different regulatory effects, which lead to the emergence of complex network structures in cells, and such structures are expected to be different for normal and cancerous cells. To study these differences, we have investigated the Gene Regulatory Network (GRN) of cells as inferred from RNA-sequencing data. The GRN is a signed weighted network corresponding to the inductive or inhibitory interactions. Here we focus on a particular of motifs in the GRN, the triangles, which are imbalanced if the number of negative interactions is odd. By studying the stability of imbalanced triangles in the GRN, we show that the network of cancerous cells has fewer imbalanced triangles compared to normal cells. Moreover, in the normal cells, imbalanced triangles are isolated from the main part of the network, while such motifs are part of the network's giant component in cancerous cells. Our result demonstrates that due to genes' collective behavior the structure of the complex networks is different in cancerous cells from those in normal ones.

The progressive development of accounting in both theoretical and practical terms has an extremely complex historical and evolutionary character. At the same time, domestic periods have always been characterized by periods of both the strengthening of original national principles and their weakening. Therefore, it is very important to achieve harmonization of these separate aspects of comprehension of accounting science, allowing simultaneously to take into account not only national economic interests, but also to use the best world experience. The presented article is just considering these features on the example of the scientifc and teaching creativity of one of the outstanding representatives of the Moscow accounting school, G.A. Bakhchisaraytsev. Here it is necessary to take into account a different understanding of the accounting methodology that existed at that time in Russia. The generalizations and conclusions presented in the article make it possible to ensure a holistic perception of the preparation of accounting personnel, to prove the correctness of the consistent study of thematic materials that allow accounting to be considered as an informational reflection of a single reproduction cycle with the access to the system of the most important fnancial and result and exchange indicators. This approach is widely used in modern methods of teaching accounting. In addition, it is necessary to note the severity of the problem of training highly professional accountants, and in this respect, referring to the experience of G.A. Bakhchisaraytsev, we should remember the need for a high degree of responsibility for training accounting personnel. It emphasizes the exceptional importance of the continuity of training in accounting, including through self-education, which allows you to expand the range of professional knowledge, and thus increase the credibility and importance of the accounting profession.

The emergence of collective behavior has been extensively studied in the field of artificial life. We propose a self-driven particle system with the dynamics of both social preferences and social relationships in the socio-psychological space to computationally understand the dynamics of human social relationships. Social preferences, represented as a matrix with the values of how much a person prefers another, is updated according to Heider's balance theory. In addition, social relationships, represented as the distribution of particle agents in the two-dimensional space, is updated based on Kano's model. Our experimental results show that if we assume the loop dynamics caused by the social preferences and social relationships, the community tends to converge to a state with two major subgroups accompanied by a few minor subgroups as a locally optimal solution. [ABSTRACT FROM AUTHOR]

A disparate literature hypothesizes what can broadly be described as the common‐enemy effect: the fact that the interaction with a common enemy (formed by Nature, an individual, or a group) increases cooperation. This review identifies the multidisciplinary antecedents of this effect, and then distinguishes between several strands of literature applying noncooperative game theory to account for it. A first strand argues that the threat posed by a common enemy makes each player's cooperative effort more critical. In a second strand a behavioral common‐enemy effect caused by group interaction is studied experimentally. A third strand models the common‐enemy effect as the formation of a coalition of players against another player in a contest. A fourth strand formalizes the principle that the 'enemy of my enemy is my friend', either in a model of social relations, interdependent altruistic preferences, or indirect reciprocity in repeated games. The connections between these strands of literature are investigated, and questions for future research are proposed. [ABSTRACT FROM AUTHOR]

Genes communicate with each other through different regulatory effects, which lead to the emergence of complex network structures in cells, and such structures are expected to be different for normal and cancerous cells. To study these differences, we have investigated the Gene Regulatory Network (GRN) of cells as inferred from RNA-sequencing data. The GRN is a signed weighted network corresponding to the inductive or inhibitory interactions. Here we focus on a particular of motifs in the GRN, the triangles, which are imbalanced if the number of negative interactions is odd. By studying the stability of imbalanced triangles in the GRN, we show that the network of cancerous cells has fewer imbalanced triangles compared to normal cells. Moreover, in the normal cells, imbalanced triangles are isolated from the main part of the network, while such motifs are part of the network's giant component in cancerous cells. Our result demonstrates that due to genes' collective behavior the structure of the complex networks is different in cancerous cells from those in normal ones. [ABSTRACT FROM AUTHOR]

Signed two-mode networks have so far predominantly been analyzed using blockmodeling techniques. In this work, we put forward the idea of projecting such networks onto its modes. Two projection methods are introduced which allow the application of known dichotomization tool for weighted networks to obtain a simple signed network. It turns out, however, that resulting networks may contain ambivalent ties, defined as conjunctions of positive and negative ties. We show that this requires the reformulation of matrices related to the network and introduce the complex adjacency and Laplacian matrix. These matrices are used to prove some properties related to balance theory including ambivalence. [ABSTRACT FROM AUTHOR]

• Presents a new theory of when negative and positive ties both occur in large numbers. • People send disliking ties to those who constrain their social agency. • This happens between socially close individuals (friends of friends) in 'intense foci'. • Intense foci are settings that concentrate social ties, and in which people are difficult to avoid. • Concentrations of positive and negative ties can therefore occur together in schools and similar 'intense' social settings. Current network scholarship does not explain why negative and positive ties both frequently occur in large numbers in some settings, such as schools. In the present paper, I argue that this can happen when people disproportionately send negative ties to socially close individuals ('friends of friends'). I propose a new theory—'intensity theory'—which argues that disliking ties disproportionately occur between friends of friends in 'intense foci'. Intense foci are settings that concentrate social relations, and in which other people are difficult to avoid. I draw on a mixed-methods case study of a boarding school and several strands of literature to substantiate the theory. In so doing, I offer a new mechanism for the initial appearance of disliking ties, propose a contextual approach to balance theory and networks in general, and suggest a more complex view of the link between positive and negative ties. [ABSTRACT FROM AUTHOR]

Online social networking services have become the most important information-sharing medium of modern society due to several merits, such as creating opportunities to broaden social relations, easy and instant communication, and fast data propagation. These advantages, however, are being abused by malicious users to disseminate unsolicited spam messages, causing great harm to both users and service providers. To address this problem, numerous spam detection methods utilizing various spam characteristics have been proposed, but most of them suffer from several limitations. Using individual behaviors and the content of messages for spam classification has been revealed to have bounded performance, since attackers can easily fake them. Instead, exploitation of social-network-related features has been highlighted as an alternative solution, but recent spam attacks can adroitly avoid these methods by controlling their ranking through various forms of attack. In this paper, we delineate a signed-network-analysis-based spam classification method. Our key hypothesis is that the edge signs are highly likely to be determined by considering users' social relationships, so there will be a substantial difference between the edge sign patterns of spammers and that of non-spammers. To identify our hypothesis, we employ two social psychological theories for signed networks—structural balance theory and social status theory—and the concept of surprise is adopted to quantitatively analyze the given network according to these theories. These surprise measurements are then used as the main features for spam classification. In addition, we develop a graph-converting method for applying our scheme to unsigned networks. Extensive experimental results with Twitter and Epinions datasets show that the proposed scheme obtains significant classification performance improvement compared to conventional schemes. [ABSTRACT FROM AUTHOR]