Homophily Effect Research Articles

HyGate-GCN: Hybrid-Gate-Based Graph Convolutional Networks with dynamical ratings estimation for personalized POI recommendation

The presence of user-generated ratings has dramatically facilitated the development of recommendation systems to aid users in discovering relevant and personalized points of interest (POI). It is worth mentioning that users’ choices and preferences are not static but rather dynamic, reflecting the ever-changing nature of human experiences and influences. Furthermore, the utilization of social influence and geographical proximity of users is still insufficient to capture the homophily effect within networks. In this paper, an interesting Hybrid Gate-based Graph Convolutional Network (HyGate-GCN) combining with feature vectors embedding and interaction, where a modified gated-GCN is proposed for personalized recommendations by adequately employing the behavior of users’ check-ins, temporal properties of users’ decisions, social properties of users, as well as the user/POI profile information data. Specifically, a novel POI graph reflecting the geographical proximity is first established to describe the behavior of users’ check-ins and, at the same time, an improved overlap ratio about POIs is employed to effectively describe temporal properties of users’ decisions. Then, an attention mechanism is developed to encode feature vectors of both the users and POIs, with the objective of assigning higher importance to features that are deemed relevant. Furthermore, a temporal Kalman filter dynamically estimating ratings is developed to exploit the information about the evolving preferences of users over time. Finally, a modified gated-GCN model with merging and refining gates is constructed to effectively acquire the homophily phenomenon in both trust network graphs and spatial adjacency matrix graphs of users and POIs respectively. Experimental results provide evidence of the effectiveness of our approach in improving accuracy and personalization.

The Effect of Homophily on Co-Offending Outcomes

The Effect of Homophily on Co-Offending Outcomes

Foreign Director Exit in the Midst of Deteriorating Bilateral Political Relations

Amid global geopolitical realism pushing for a race of hegemonic rivalry nowadays, an outflow of global human talents is a pressing organizational concern. Our study draws attention to the underexamined phenomenon of the exit of foreign directors from their host countries during geopolitical tensions. Theorizing from a sensemaking logic, we posit that the deterioration of bilateral political relations serves as an unexpected event that activates foreign directors’ schemas for dual identity conflict, propelling them to react behaviorally to such identity threats by exiting the board in the host country. In addition, we further posit that the sensemaking process is contingent on how the foreign director draws cues from the embedded social context, including organizational identification, socialization and homophily effect, and socioemotional climate. Our empirical analyses from a sample of 1,014 foreign directors in China from 1999 to 2018 provide strong and robust support for the hypotheses. This study instills important theoretical insights into the transcending impacts of international relations and geopolitics, international governance and foreign directors, and the situated cognitive process of sensemaking regarding the intertwining effects of cognitive schema and social contexts.

Effect of homophily on coupled behavior-disease dynamics near a tipping point

Understanding the interplay between social activities and disease dynamics is crucial for effective public health interventions. Recent studies using coupled behavior-disease models assumed homogeneous populations. However, heterogeneity in population, such as different social groups, cannot be ignored. In this study, we divided the population into social media users and non-users, and investigated the impact of homophily (the tendency for individuals to associate with others similar to themselves) and online events on disease dynamics. Our results reveal that homophily hinders the adoption of vaccinating strategies, hastening the approach to a tipping point after which the population converges to an endemic equilibrium with no vaccine uptake. Furthermore, we find that online events can significantly influence disease dynamics, with early discussions on social media platforms serving as an early warning signal of potential disease outbreaks. Our model provides insights into the mechanisms underlying these phenomena and underscores the importance of considering homophily in disease modeling and public health strategies.

Examining physical and virtual sexual and drug risk venue co-attendance among PrEP-eligible Latinx sexual minority men

Disparities in Latinx sexual minority men (LSMM) pre-exposure prophylaxis (PrEP) initiation and adherence demonstrate the need for innovative strategies to improve outcomes along the PrEP Care Continuum. The purpose of this study was to examine physical and virtual risk venue co-attendance among LSMM of varying stages of PrEP use living in South Florida, an Ending the HIV Epidemic (EHE) priority jurisdiction. Venue co-attendance may be leveraged to support equitable dissemination and implementation (D&I) of HIV and drug use preventive interventions to LSMM. Ninety-four LSMM completed surveys on PrEP use and identified physical and virtual sexual and drug risk venues (where men seek sex partners and/or have sex or access or use drugs). Bivariate analyses examined differences in demographics and venue endorsement by PrEP status. Exponential random graph models examined endorsement of venues by PrEP status. One-mode projection visualizations portray the structure of venue co-attendance networks by PrEP status. Participants identified 49 physical and virtual sexual and drug risk venues. A homophily effect of PrEP status on venue endorsement was identified for both sexual and drug risk venues. Network size and density differed by PrEP status and whether the venue was identified as a sexual or drug risk location. Online dating apps, bars, and saunas had the highest centrality in each network type suggesting their potential role in implementing preventive programming. This study identified specific sexual and drug risk venues that may be leveraged to both disseminate targeted PrEP and harm reduction information and to implement interventions to improve PrEP uptake and adherence among LSMM living in EHE priority jurisdictions.

A Survey of Graph Neural Networks for Social Recommender Systems

Social recommender systems (SocialRS) simultaneously leverage the user-to-item interactions as well as the user-to-user social relations for the task of generating item recommendations to users. Additionally exploiting social relations is clearly effective in understanding users’ tastes due to the effects of homophily and social influence. For this reason, SocialRS has increasingly attracted attention. In particular, with the advance of graph neural networks (GNN), many GNN-based SocialRS methods have been developed recently. Therefore, we conduct a comprehensive and systematic review of the literature on GNN-based SocialRS. In this survey, we first identify 84 papers on GNN-based SocialRS after annotating 2,151 papers by following the PRISMA framework (preferred reporting items for systematic reviews and meta-analyses). Then, we comprehensively review them in terms of their inputs and architectures to propose a novel taxonomy: (1) input taxonomy includes five groups of input type notations and seven groups of input representation notations; (2) architecture taxonomy includes eight groups of GNN encoder notations, two groups of decoder notations, and 12 groups of loss function notations. We classify the GNN-based SocialRS methods into several categories as per the taxonomy and describe their details. Furthermore, we summarize benchmark datasets and metrics widely used to evaluate the GNN-based SocialRS methods. Finally, we conclude this survey by presenting some future research directions. GitHub repository with the curated list of papers are available at https://github.com/claws-lab/awesome-GNN-social-recsys

Using Respondent-Driven Sampling (RDS) to Identify the Healthcare Needs among Women of Reproductive Age Who Migrated from Venezuela to Brazil, 2018-2021.

In 2021, an RDS survey was conducted among Venezuelan migrant women of reproductive age who migrated to two Brazilian cities (Manaus and Boa Vista) from 2018 to 2021. To start the RDS recruitment, we chose seeds non-randomly in both cities. The study variables were age, educational level, self-rated health, pregnancy, migratory status and use of health services. We estimated the prevalence, confidence intervals and homophily effects by variable category. We used a multivariate logistic regression model to identify the main factors associated with healthcare use. A total of 761 women were recruited in Manaus and 1268 in Boa Vista. Manaus showed more irregular migrants than Boa Vista. The main reasons for using health services were as follows: illness, disease prevention and prenatal care. The logistic regression model showed the use of health services was associated with educational level and healthcare needs but not with migratory status. The social inclusion of Venezuelan migrants is extremely relevant, although many challenges must be overcome. The strategy of the Brazilian Federal Government for providing humanitarian assistance to Venezuelan migrants should be expanded to include and facilitate their integration into labor markets, access to healthcare and education, benefiting both migrants and the Brazilian people by reducing social inequality.

‘University matching’ in state-regulated Sino-Australian transnational higher education: a Bourdieusian social network analysis

ABSTRACT The past three decades have seen proliferating research on Transnational Higher Education (TNHE), mostly understood through a market-oriented lens as a means of institutional and individual investment in economic and status gains. Less understood is the interplay between the state and the market logic in TNHE. Large-scale research on the market-state-status coordinated effect on TNHE is absent. This study makes a contribution in this regard through a Bourdieusian social network analysis of 130 state-regulated TNHE partnerships between 64 Chinese and 28 Australian universities. Descriptive analysis shows the evolvement of state-regulated Sino-Australian TNHE ‘networks’ over time from 2003 to 2019. Inferential statistics shows a significant homophily effect in the TNHE partnerships between Chinese and Australian universities with high rankings and research income. These results allude to a strong influence from the Chinese state on Sino-Australian TNHE partnerships.

The role of anthropomorphism and racial homophily of virtual influencers in encouraging low‐ versus high‐cost pro‐environmental behaviors

AbstractVirtual influencers have great potential to shape the audience's perception and motivate behavioral change. Drawing upon anthropomorphism theory and social identity theory, this paper examined the interaction effect of anthropomorphism and racial homophily of virtual influencers in shaping audiences' trust and subsequently pro‐environmental behaviors in low‐ and high‐cost contexts. Two online studies employing experimental materials generated by artificial intelligence were conducted. Study 1 revealed that high anthropomorphism (human‐like virtual influencers) and high racial homophily (local‐like virtual influencers) are more effective for eliciting trust in the context of low‐cost pro‐environmental behaviors. The findings also showed that low racial homophily (foreign‐like virtual influencers) would further weaken the trust level of a virtual influencer in low anthropomorphism (animate‐like virtual influencers). Study 2 aimed to replicate the findings from Study 1 in the context of high‐cost pro‐environmental behaviors. The findings showed that low racial homophily (foreign‐like virtual influencers) enhanced the trust in a high anthropomorphism (human‐like virtual influencers) virtual influencer. The moderated mediation analyses confirmed the hypothesized relationships in the proposed research model. This research advanced our understanding on the moderating role of racial homophily that serves as a cognitive shortcut for low‐cost and quick decisions. However, a low racial homophily (foreign‐like) virtual influencer would be more effective for high‐cost and symbolic pro‐environmental behaviors. These insights provide valuable guidance to businesses, marketers, and environmental advocates aiming to leverage virtual influencers for encouraging sustainability practices.

Organised crime movement across local communities: A network approach

This paper explores the structure of organised crime movement across local communities and the drivers underpinning such movement. Firstly, it builds on network analysis to offer a novel methodological approach to empirically and quantitatively study the movement of organised crime offenders across geographical areas. The paper then applies this approach to evidence from Cambridgeshire in the United Kingdom. It reconstructs the movement of organised crime members across local areas based on a large-scale police dataset that includes 41 months of recorded crime events. It identifies organised crime “turf” and “target” areas and then explores the drivers of movement from the former to the latter using Exponential Random Graph Models. Findings confirm that geographical distance matters; however, socio-demographic, urban, economic and crime-related characteristics of communities play a key role. Organised crime group members target urban communities with higher than average illegal market opportunities (proxied by drug-related activity). The work also finds the effect of socio-demographic homophily between turf and target communities, suggesting that organised crime group members might target territories that are similar to their own. While a high level of deprivation makes a community more likely to send organised crime members, its impact on a community’s probability of being a receiver is less clear. Finally, the paper offers a way to identify communities (local areas) at risk of being targeted by criminal organisations, thus providing practitioners with a tool for early interventions.

Hybrid organisations and governance systems: the case of the European Space Agency

ABSTRACT The constitutive organisations of governance systems tend to multiply and diversify over time. In parallel, a tendency toward homophily favours the creation of clusters of homogeneous organisations. Yet, few systems drift to the point of disconnection or dislocation. Several remain sufficiently cohesive to allow adaptation and other complex properties to emerge. To maintain equilibrium between order and chaos, some organisations must create bridges between otherwise homogeneous groups. This paper argues that hybrid organisations are ideally suited for this role. By their nature, hybrids share characteristics with different types of organisations in global governance, allowing them to overcome strict homophily and create bridges across clusters. Hybrids benefit from acting as brokers and in doing so, they facilitate the exchange of material and ideational resources across the governance system. Even if it is not their intention, they contribute to holding governance systems together and counterbalance the effect of homophily. We illustrate this argument by examining the space governance system and the hybrid nature, bridging activities, and brokerage role of the European Space Agency.

Does board diversity mitigate risk? The effect of homophily and social ties on risk-taking in financial institutions

Research Question/IssueThis study investigates whether greater board diversity and looser social network ties have an impact on board independence and risk-taking in US financial institutions from 2010 to 2022.The econometric strategy involved structural equation models, where risk as a dependent variable was measured by two latent variables and a total of five measures of risk. Several aspects of board diversity were utilized including gender, social, experience and educational backgrounds. Research Findings/InsightsThe findings suggested that diversity in nationality had a significant positive effect, while age and gender diversity had a minor effect on mitigating risk. Two measures of educational diversity had mixed results while suggesting that financial education is associated with greater risk. Also, social networks had a significant effect on risk-taking, especially on market risk. Theoretical/Academic ImplicationsThe study highlights the importance of maintaining a sensible level of board diversity across all aspects to avoid issues of cohesion and poor communication. This implication arises from the conclusion that too diverse a board might suffer from the lack of cohesion and communication, while a board with very low diversity will not be able to benefit from diverse backgrounds and expertise. Practitioner/Policy ImplicationsResults from this study recommend incorporating social networking requirements in defining the independence of directors.

Social Network Community Detection to Deal with Gray-Sheep and Cold-Start Problems in Music Recommender Systems

Information from social networks is currently being widely used in many application domains, although in the music recommendation area, its use is less common because of the limited availability of social data. However, most streaming platforms allow for establishing relationships between users that can be leveraged to address some drawbacks of recommender systems. In this work, we take advantage of the social network structure to improve recommendations for users with unusual preferences and new users, thus dealing with the gray-sheep and cold-start problems, respectively. Since collaborative filtering methods base the recommendations for a given user on the preferences of his/her most similar users, the scarcity of users with similar tastes to the gray-sheep users and the unawareness of the preferences of the new users usually lead to bad recommendations. These general problems of recommender systems are worsened in the music domain, where the popularity bias drawback is also present. In order to address these problems, we propose a user similarity metric based on the network structure as well as on user ratings. This metric significantly improves the recommendation reliability in those scenarios by capturing both homophily effects in implicit communities of users in the network and user similarity in terms of preferences.

“I think exactly the same”—trust in SMIs and online purchase intention: a moderation mediation analysis using PLS-SEM

PurposeThe purpose of this paper is to investigate the moderating effect of homophily between trust in social media influencers (SMIs) and credibility of the post in influencer marketing by incorporating the similarity attraction theory (SAT) and analysing the effect of trust in SMIs on online purchase intention and credibility of the post. This study also explored the mediating role of influencers’ credibility of the post between trust in SMIs and online purchase intention.Design/methodology/approachThe data were collected from 417 respondents in Jaipur, India, using an online questionnaire via Google Forms. A convenience sampling technique was employed to collect the data. Partial least squares structural equation modelling (PLS-SEM) was used to test the proposed hypotheses with the help of SmartPLS version 4.FindingsThe results exhibit a positive and significant influence of trust in SMIs on credibility of the post and online purchase intention. Also, this study found a positive and significant relationship between credibility of the post and online purchase intention. Additionally, credibility of the post had a positive and significant mediation role in the relationship between trust in SMIs and online purchase intention. In addition, homophily positively moderated the relationship between trust in SMIs and credibility of the post.Practical implicationsThe findings of this study can be used by marketing professionals working in the e-commerce industry to ensure their continued in success using the right influencers for their specific target audiences and help them create and implement more effective promotional strategies, increasing brand awareness, announcing sales, using them for creative content and so on.Originality/valueUntil now, there has been no study in the Indian context that has tested the moderation effect of homophily between the trust in SMIs and credibility of the post by incorporating the SAT, according to the researchers’ knowledge. Furthermore, this novel piece of research explored the relationship between trust in SMIs and online purchase intention with credibility of the post as a mediator.

Homophily and its effects on collaborations and repeated collaborations: a study across scientific fields

This study examines the influence of homophily on research collaborations across all scientific fields, noting the role of ascribed, acquired, geographical, current career, and educational and career history attributes. Our analysis builds on previous studies by adopting a comparative approach across scientific fields and examining the effect of homophily on repeated collaborations. Our findings reveal physical proximity as a universal driver of collaboration across all scientific fields, both for overall collaborations and as a maintainer of collaborative endeavors. We also note that most attributes that are responsible for overall collaborations are similar to the attributes that play a role in maintaining them, with a few exceptions, notably when it comes to institutional characteristics. Our results also show the complex role of career history attributes, such as job variety and international mobility, in influencing the likelihood of collaboration. This study sheds light on the intricate interplay of different attributes in shaping scientific collaborations, underscoring the need for a multidisciplinary approach in future homophily studies and nuanced strategies for fostering collaborations across different scientific fields.

The role of online identity orientation and socializing for information search: a case of ethnic minority guests’ hospitality experiences

PurposeThis paper aims to investigate the impact of online identity orientation and online friendship homophily on online socializing, online information search and ethnic guests’ hospitality experiences.Design/methodology/approachThe study uses structural equation modeling to test a conceptual model developed after reviewing hospitality literature. Data is collected from a sample of 514 Turkish-Dutch ethnic guests living in the Netherlands using a self-administered questionnaire.FindingsThe results show that online identity orientations aligned with minority and majority cultures impact online friendship homophily and online socializing, which subsequently impact online information search and hospitality experiences of ethnic guests.Practical implicationsOn the whole, ethnic communities have considerable spending power. The findings point to heritage and mainstream cultural socialization accounting for travel and hospitality experiences within an ethnic minority group. The findings supply relevant information for hospitality sectors on services to endorse or promote to guests from ethnic communities.Originality/valueThe study examines the simultaneous effects of online identity orientations and online friendship homophily on online socialization and hospitality experiences of ethnic guests. It highlights the role of culture in explaining the use of social networking sites and its potential impact on hospitality-related behaviors and experiences of ethnic guest consumers.

Designing profitable seeding Programs: The effects of social network properties and consumer homophily

This study explores the main and interaction effects of consumer social network properties and homophily on the profit impact of seeding programs. Social network properties capture the topology of the connections between consumers, while homophily captures the degree to which consumers share similar attributes with their social connections.We conduct extensive agent-based simulation experiments on eight empirical social networks mapped from Facebook, Twitter, and Emails, among others. The results reveal that seeding programs generate higher profits in clustered social networks, and are less profitable when the network diameter and average distance between consumers increase. The effects of social network diameter and average distance are only observed when homophily is high and are negligible when homophily is low. For random seeding and targeting social hubs, the effect of social network clustering on profits is stronger when homophily is high. For early adopters and experts, the effect depends on the attribute on which homophily exists in the market.We explain the findings by distinguishing between the effects of seeding programs on local diffusions—effects on direct acquaintances—and global diffusion processes—the impact across the social network. The findings offer critical implications for marketers aiming to maximize the return-on-investment in seeding programs.

Geographic proximity and homophily effects drive social interactions within VGI communities: an example of iNaturalist

ABSTRACT Social interactions among online community members contributing to volunteered geographic information (VGI) are a key element and often crucial to VGI project success. Existing studies on VGI lack investigations into the patterns of social interactions within VGI communities and the drivers that may have shaped these patterns. This study bridges this gap by analyzing social interaction patterns in the iNaturalist citizen science project and exploring potential driving factors through social network analysis. The relationships between potential drivers of social interactions in iNaturalist (i.e. geographic distance, species taxon composition similarity, and land cover composition similarity) and the establishment, intensity, and clustering of interactions were examined. The results revealed that geographic proximity, common interests in species taxon categories, and shared preferences in observation environments are major drivers of inter-contributor species identification interactions in iNaturalist. These findings are supported by theories that explain the social forces behind social link formation. Geographic distance represents physical proximity, whereas species taxon composition similarity and land cover similarity reflect homophily effects. iNaturalist and many other VGI communities are spatially embedded social networks. The discovered interaction drivers in iNaturalist generally align with those in spatial social networks and are expected to be generalizable to VGI communities beyond iNaturalist.

From Organizational Gossip to a Corporate Crisis: A Network Analysis of Anonymous Online Communication on the Blind Application

This study examined an anonymous online community, Blind, while focusing on the role of social networks in information flow, to explain how internal organizational gossip is diffused to employees of other companies and even to the public through its distinctive network structures. We analyzed three cases of gossip networks that differed in terms of the organizations involved and issue severity. The findings suggest that online gossip networks with a large size, low connectedness, and high centralization can easily diffuse information to community members and the outside public. Logistic regression Quadratic Assignment Procedures (QAPs) were used to examine the endogenous and exogenous effects in each network. The results showed that the receiver effect of company size negatively predicted tie formation in NAVER and Samsung’s gossip networks, indicating that gossip diffusion was more likely facilitated by members of smaller companies actively commenting on gossip. The homophily effect of working for the same company predicted tie formation in Samsung’s gossip network, indicating the difficulty of gossip diffusion to external members. Finally, the results of the structural hole analysis suggest that journalists play an important role in issue delivery and gossip diffusion in NAVER’s case. The findings reveal that internal workplace gossip can spill over an organizational boundary online and develop into a corporate crisis.

Educator–Learner Homophily Effect on Participants’ Adoption of Agribusiness Recordkeeping Practices

Homophily is the tendency of individuals to be attracted to and associate with people who share similar sociodemographic, behavioral, and intrapersonal characteristics. Homophily plays a significant role when introducing innovations to create behavioral change. Understanding the educator–learner homophily effect is important to introduce and diffuse innovations efficiently and effectively. A quasi-experimental design was used to test the effect of educator–learner homophily on technology adoption in agriculture. Researchers showed one of four instructional videos about agribusiness recordkeeping practices to 238 Guatemalan female farmers. After the video instruction, the participants were given agribusiness logbooks to track farm sales and expenses. Initially, literate participants were more than four times as likely to adopt agribusiness recordkeeping practices than illiterate participants. Logistic regression determined the effects of the trainer’s gender and nationality on the participants’ likelihoods of adopting agribusiness recordkeeping practices at 6- and 21-weeks post-training. The 21-week logistic regression model was statistically significant; participants who received training from a female instructor were 0.441 times less likely to adopt and maintain agribusiness recordkeeping practices over the long-term. Nationality was not associated with the likelihood of adopting recordkeeping as an agribusiness practice. Program administrators should consider trainers’ perceived credibility and participants’ cultural norms when planning agribusiness management training programs with topics having limited immediate benefit.