SPEX: A Generic Framework for Enhancing Neural Social Recommendation

Social Recommender Systems (SRS) have attracted considerable attention since its accompanying service, social networks, helps increase user satisfaction and provides auxiliary information to improve recommendations. However, most existing SRS focus on social influence and ignore another essential social phenomenon, i.e., social homophily. Social homophily, which is the premise of social influence, indicates that people tend to build social relations with similar people and form influence propagation paths. In this article, we propose a generic framework Social PathExplorer (SPEX) to enhance neural SRS. SPEX treats the neural recommendation model as a black box and improves the quality of recommendations by modeling the social recommendation task, the formation of social homophily, and their mutual effect in the manner of multi-task learning. We design a Graph Neural Network based component for influence propagation path prediction to help SPEX capture the rich information conveyed by the formation of social homophily. We further propose an uncertainty based task balancing method to set appropriate task weights for the recommendation task and the path prediction task during the joint optimization. Extensive experiments have validated that SPEX can be easily plugged into various state-of-the-art neural recommendation models and help improve their performance. The source code of our work is available at: https://github.com/XMUDM/SPEX.

Audience size, moderator activity, gender, and content diversity: Exploring user participation and financial commitment on Twitch.tv

User participation has long been recognized as a cornerstone of thriving online communities. Social live-streaming service (SLSS) communities are built on a subscription-based model and rely on viewers’ participation and financial support. Using the collective effort model and heuristics of social influence, this study examines the influence of streamer and viewer behaviors on viewers’ participation and financial commitment on the SLSS, Twitch.tv. Findings from behavioral data collected over 7 weeks show larger audiences diminish individual participation and financial commitment while moderation may encourage more. Female streamers benefit from increased moderation, earning two to three times more in financial commitment compared to men, who streamed more frequently and for longer durations but attracted much smaller audiences. Viewers’ participation and financial commitment did not differ across streams with more content diversity. Our results demonstrate how group factors influence individual participation and financial commitment in newer subscription-based media.

Social Influence on Fad Diet Use: A Systematic Literature Review

Background: A fad diet is a broad term used to describe dieting methods that recommend altering the intake of macronutrients to specific proportions or instruct people to intake or avoid particular foods, often with the goal of rapid weight loss. Previous literature reviews report social influence impacts general diet behaviour, but have yet to examine fad diets, specifically. Therefore, the purpose of this systematic review was to synthesize literature related to social influence on an individual's fad diet use and understand the sociocultural factors related to diet use. Methods: Using PRISMA guidelines, Medline, PsycInfo, Embase, CINAHL, and CENTRAL databases were searched to identify articles investigating the impact of social on fad diet use. Covidence was used to manage the review process and Garrard's Matrix Method was used to extract data from reviewed articles (n = 13). Results: A majority of reviewed studies examined interpersonal influence (62%) and reported social influence impacting a variety of fad diet behaviours (92%). Interpersonal and media influence were highlighted as motivating factors for adopting unhealthy dieting methods (54%), and studies showed interpersonal support impacted adoption and maintenance of fad diet use (23%). Also, social norms were reported to influence unhealthy weight control behaviours (15%). Discussion: This review revealed social influence is associated with the adoption, adherence, and termination of fad diets. The prevalence of fad diets in society and the lack of research on this topic warrants further examination of factors related to fad diets use and the spread among interpersonal networks.

Does social influence affect COVID-19 vaccination intention among the unvaccinated?

Conformist social influence is a double-edged sword when it comes to vaccine promotion. On the one hand, social influence may increase vaccine uptake by reassuring the hesitant about the safety and effectiveness of the vaccine; on the other, people may forgo the cost of vaccination when the majority is already vaccinated – giving rise to a public goods dilemma. Here, we examine whether available information on the percentage of double-vaccinated people affects COVID-19 vaccination intention among unvaccinated people in Turkey. In an online experiment, we divided participants (n = 1013) into low, intermediate, and high social influence conditions, reflecting the government’s vaccine promotion messages. We found that social influence did not predict COVID-19 vaccination intention, but psychological reactance and collectivism did. People with higher reactance (intolerance of others telling one what to do and being sceptical of consensus views) had lower vaccination intention, whilst people with higher collectivism (how much a person considers group benefits over individual success) had higher vaccination intention. Our findings suggest that advertising the percentage of double-vaccinated people is not sufficient to trigger a cascade of others getting themselves vaccinated. Diverse promotion strategies reflecting the heterogeneity of individual attitudes could be more effective.

Spatial clustering in vaccination hesitancy: the role of social influence and social selection

The phenomenon of vaccine hesitancy behavior has gained ground over the last three decades, jeopardizing the maintenance of herd immunity. This behavior tends to cluster spatially, creating pockets of unprotected sub-populations that can be hotspots for outbreak emergence. What remains less understood are the social mechanisms that can give rise to spatial clustering in vaccination behavior, particularly at the landscape scale. We focus on the presence of spatial clustering, and aim to mechanistically understand how different social processes can give rise to this phenomenon. In particular, we propose two hypotheses to explain the presence of spatial clustering: (i) social selection, in which vaccine-hesitant individuals share socio-demographic traits, and clustering of these traits generates spatial clustering in vaccine hesitancy; and (ii) social influence, in which hesitant behavior is contagious and spreads through neighboring societies, leading to hesitant clusters. Adopting a theoretical spatial network approach, we explore the role of these two processes in generating patterns of spatial clustering in vaccination behaviors under a range of spatial structures. We find that both processes are independently capable of generating spatial clustering, and the more spatially structured the social dynamics in a society are, the higher spatial clustering in vaccine-hesitant behavior it realizes. Together, we demonstrate that these processes result in unique spatial configurations of hesitant clusters, and we validate our models on both processes with fine-grain empirical data on vaccine hesitancy, social determinants, and social connectivity in the US. Finally, we propose, and evaluate the effectiveness of, two novel intervention strategies to diminish hesitant behavior. Our generative modeling approach informed by unique empirical data provides insights on the role of complex social processes in driving spatial heterogeneity in vaccine hesitancy.

HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

With the continuous enrichment of social network applications, such as TikTok, Weibo, Twitter, and others, social media have become an indispensable part of our lives. Web users can participate in their favorite events or pay attention to people they like. The “heterogeneous” influence between events and users can be effectively modeled, and users’ potential future behaviors can be predicted, so as to facilitate applications such as recommendations and online advertising. For example, a user’s favorite live streaming host (user) recommends certain products (event), can we predict whether the user will buy these products in the future? The majority of studies are based on a homogeneous graph neural network to model the influence between users. However, these studies ignore the impact of events on users in reality. For instance, when users purchase commodities through live streaming channels, in addition to the factors of the host, the commodity is also a key factor that influences the behavior of users. This study designs an influence prediction model based on a heterogeneous neural network HetInf. Specifically, we first constructed the heterogeneous social influence network according to the relationship between event nodes and user nodes, then sampled the user heterogeneous subgraph for each user, extracted the relevant node features, and finally predicted the probability of user behavior through the heterogeneous neural network model. We conducted comprehensive experiments on two large social network datasets. Furthermore, the experimental results show that HetInf is significantly superior to the previous homogeneous neural network methods.