Bilateral Filtering Graph Convolutional Network for Multi-relational Social Recommendation in the Power-law Networks

In recent years, advances in Graph Convolutional Networks (GCNs) have given new insights into the development of social recommendation. However, many existing GCN-based social recommendation methods often directly apply GCN to capture user-item and user-user interactions, which probably have two main limitations: (a) Due to the power-law property of the degree distribution, the vanilla GCN with static normalized adjacency matrix has limitations in learning node representations, especially for the long-tail nodes; (b) multi-typed social relationships between users that are ubiquitous in the real world are rarely considered. In this article, we propose a novel Bilateral Filtering Heterogeneous Attention Network (BFHAN), which improves long-tail node representations and leverages multi-typed social relationships between user nodes. First, we propose a novel graph convolutional filter for the user-item bipartite network and extend it to the user-user homogeneous network. Further, we theoretically analyze the correlation between the convergence values of different graph convolutional filters and node degrees after stacking multiple layers. Second, we model multi-relational social interactions between users as the multiplex network and further propose a multiplex attention network to capture distinctive inter-layer influences for user representations. Last but not least, the experimental results demonstrate that our proposed method outperforms several state-of-the-art GCN-based methods for social recommendation tasks.

Examining the Association between Racialized Economic Threat and White Suicide in the United States, 2000–2016

Suicide is steadily rising. Many blamed worsening economic conditions for this trend. Sociological theory established clear pathways between joblessness and suicide focused on status threat, shame, and consequent disruption of social relationships. However, recent empirical research provides little support for a link between unemployment and suicide. I attempt to reconcile this contradiction by focusing on white suicide and white employment-to-population ratio. Whiteness is not just a default category but a pervasive ideology that amplifies the effects of status loss. The white employment-to-population ratio represents a form of racialized economic threat and accounts for discouraged workers who have exited the labor force. I use longitudinal hybrid models with U.S. state-level data, 2000 to 2016, and find that decreasing employment is associated with increasing suicide among the white population and white men. I discuss this study’s contributions to the literature on suicide and joblessness and the emerging scholarship on whiteness and health.

Promoting engagement with social fact-checks online

Social corrections, wherein social media users correct one another, are an important mechanism for debunking online misinformation. But users who post misinformation only rarely engage with social corrections, instead typically choosing to ignore them. Here, we investigate how the social relationship between the corrector and corrected user affect the willingness to engage with corrective, debunking messages. We explore two key dimensions: (i) partisan agreement with, and (ii) social relationships between the user and the corrector. We conducted a randomized field experiment with Twitter users and a conceptual replication survey experiment with Amazon Mechanical Turk workers in which posts containing false news were corrected. We varied whether the corrector identified as a Democrat or Republican; and whether the corrector followed the user and liked three of their tweets the day before issuing the correction (creating a minimal social relationship). Surprisingly, we did not find evidence that shared partisanship increased a user’s probability of engaging with the correction. Conversely, forming a minimal social connection significantly increased engagement rate. A second survey experiment found that minimal social relationships foster a general norm of responding, such that people feel more obligated to respond – and think others expect them to respond more – to people who follow them, even outside the context of misinformation correction. These results emphasize social media’s ability to foster engagement with corrections via minimal social relationships, and have implications for effective, engaging fact-check delivery online.

THE TASTE OF HOME: THE CONSTRUCTION OF SOCIAL RELATIONSHIPS THROUGH COMMENSALITY AMONGST FEMALE MALAY STUDENTS IN THE UNITED KINGDOM

Background and Purpose: Commensality is an act of eating together among migrant communities as a means of passing down the culture and ethnic identity. There is very limited discussion on commensality that pays attention to food sharing and eating that extends beyond the traditional forms of social relationships, identity, and space among the Malay community abroad. Thus, this article aims to explore the connections of social relationships through food, space and identity amongst female Malay students in the United Kingdom. Methodology: This research is based on one-year ethnographic fieldwork amongst female Malaysian Muslim students in Manchester and Cardiff. Thirty in-depth interviews were conducted with both undergraduate and postgraduate students from sciences and social sciences courses. Besides, in-depth interviews, participant observation, conversation and fieldnotes methods were deployed as supplementary for data collection. Findings: This paper argues that cooking and eating together in a private space is a way for them to maintain social relationships and overcome stress in their studies, and fulfil their desire to create harmony and trust at home. Besides, places such as the kitchen, play an essential space in building the Malay identity and social relationships between female Malay students’ communities in the host country. Contributions: This study has contributed to an understanding of the meaning of friendship, identity, space, and the discussion on the anthropology of food from international students’ perspectives and migration studies. Keywords: Food and identity, commensality, Malay students, friendship, international students. Cite as: Ibnu, I. N. (2022). The taste of home: The construction of social relationships through commensality amongst female Malay students in the United Kingdom. Journal of Nusantara Studies, 7(1), 316-334. http://dx.doi.org/10.24200/jonus.vol7iss1pp316-334

Disentangling help-seeking and giving up: differential human-directed gazing by dogs in a modified unsolvable task paradigm

Dogs are renowned for ‘looking back’ at humans when confronted with a problem, but it has been questioned whether this implies help-seeking or giving up. We tested 56 pet dogs from two breed groups (herding dogs and terriers) in a modified unsolvable task paradigm. One reward type (food or toy) was enclosed in a box, while the respective other reward was accessible. With both reward types, human-directed gazing in relation to the box was significantly positively correlated with interaction with the box, as long as an alternative was available. This suggests that both behaviours served to attain the unavailable reward and reflected individual motivation for the inaccessible vs the accessible reward. Furthermore, we varied whether the owner or the experimenter was responsible for handling the rewards. In the owner-responsible group, dogs rarely gazed at the experimenter. In the experimenter-responsible group, dogs preferentially directed box-related gazing (prior to or after looking at or interacting with the box) at the owner. Still, they gazed at the experimenter significantly longer than the owner-responsible group. Conversely, toy-related gazing was directed significantly more at the experimenter. Thus, dogs adjust their gazing behaviour according to the people’s responsibility and their current goal (help-seeking vs play). Gaze duration did not differ between herding dogs and terriers. We conclude that dogs use gazing at humans’ faces as a social problem-solving strategy, but not all gazing can be classified as such. Dogs’ human-directed gazing is influenced by the social relationships with the persons, situational associations, and context (unsolvable problem vs play).

Transitivity scores to account for triadic edge weight similarity in undirected weighted graphs

The graph transitivity measures the probability that adjacent vertices in a network are interconnected, thus revealing the existence of tightly connected neighborhoods playing a role in information and pathogen circulation. The graph transitivity is usually computed for dichotomized networks, therefore focusing on whether triangular relationships are closed or open. But when the connections vary in strength, focusing on whether the closing ties exist or not can be reductive. I score the weighted transitivity according to the similarity between the weights of the three possible links in each triad. In a simulation, that new technique correctly diagnosed excesses of balanced or imbalanced triangles, for example, strong triplets closed by weak links. I illustrate the biological relevance of that information with two reanalyses of animal contact networks. In the rhesus macaque Macaca mulatta, a species in which kin relationships strongly predict social relationships, the new metrics revealed striking similarities in the configuration of grooming networks in captive and free-ranging groups, but only as long as the matrilines were preserved. In the barnacle goose Branta leucopsis, in an experiment designed to test the long-term effect of the goslings' social environment, the new metrics uncovered an excess of weak triplets closed by strong links, particularly pronounced in males, and consistent with the triadic process underlying goose dominance relationships.

The Six Components of Social Interactions: Actor, Partner, Relation, Activities, Context, and Evaluation

Social interactions are essential aspects of social relationships. Despite their centrality, there is a lack of a standardized approach to systematize social interactions. The present research developed (Study 1) and tested (Study 2) a taxonomy of social interactions. In Study 1 (5,676 descriptions of social interactions from N = 708 participants, age range 18–83 years), we combined a bottom-up approach based on the grounded theory with a top-down approach integrating existing empirical and theoretical literature to develop the taxonomy. The resulting taxonomy (APRACE) comprises the components Actor, Partner, Relation, Activities, Context, and Evaluation, each specified by features on three levels of abstraction. A social situation can be described by a combination of the components and their features on the respective abstraction level. Study 2 tested the APRACE using another dataset (N = 303, age range 18–88 years) with 1,899 descriptions of social interactions. The index scores of the six components, the frequencies of the features on the most abstract level, and their correlations were largely consistent across both studies, which supports the generalizability of the APRACE. The APRACE offers a generalizable tool for the comprehensive, parsimonious, and systematic description of social interactions and, thus, enables networked research on social interactions and application in a number of practical fields.

Rethinking Social Relationships in Adulthood: The Differential Investment of Resources Model

Empirical evidence about the development of social relationships across adulthood into late life continues to accumulate, but theoretical development has lagged behind. The Differential Investment of Resources (DIRe) model integrates these empirical advances. The model defines the investment of time and energy into social ties varying in terms of emotional closeness and kinship as the core mechanism explaining the formation and maintenance of social networks. Individual characteristics, acting as capacities, motivations, and skills, determine the amount, direction, and efficacy of the investment. The context (e.g., the living situation) affects the social opportunity structure, the amount of time and energy available, and individual characteristics. Finally, the model describes two feedback loops: (a) social capital affecting the individual’s living situation and (b) different types of ties impacting individual characteristics via social exchanges, social influences, and social evaluations. The proposed model will provide a theoretical basis for future research and hypothesis testing.