Using Partially-Observed Facebook Networks to Develop a Peer-Based HIV Prevention Intervention: Case Study

Abstract

Background: This is a case study from an HIV prevention project among young black men who have sex with men. Individual-level prevention interventions have had limited success among young black men who have sex with men, a population that is disproportionately affected by HIV; peer network-based interventions are a promising alternative. Facebook is an attractive digital platform because it enables broad characterization of social networks. There are, however, several challenges in using Facebook data for peer interventions, including the large size of Facebook networks, difficulty in assessing appropriate methods to identify candidate peer change agents, boundary specification issues, and partial observation of social network data.

Objective: This study aimed to explore methodological challenges in using social Facebook networks to design peer network-based interventions for HIV prevention and present techniques to overcome these challenges.

Methods: Our sample included 298 uConnect study respondents who answered a bio-behavioral survey in person and whose Facebook friend lists were downloaded (2013-2014). The study participants had over 180,000 total Facebook friends who were not involved in the study (nonrespondents). We did not observe friendships between these nonrespondents. Given the large number of nonrespondents whose networks were partially observed, a relational boundary was specified to select nonrespondents who were well connected to the study respondents and who may be more likely to influence the health behaviors of young black men who have sex with men. A stochastic model-based imputation technique, derived from the exponential random graph models, was applied to simulate 100 networks where unobserved friendships between nonrespondents were imputed. To identify peer change agents, the eigenvector centrality and keyplayer positive algorithms were used; both algorithms are suitable for identifying individuals in key network positions for information diffusion. For both algorithms, we assessed the sensitivity of identified peer change agents to the imputation model, the stability of identified peer change agents across the imputed networks, and the effect of the boundary specification on the identification of peer change agents.

Results: All respondents and 78.9% (183/232) of nonrespondents selected as peer change agents by eigenvector on the imputed networks were also selected as peer change agents on the observed networks. For keyplayer, the agreement was much lower; 42.7% (47/110) and 35.3% (110/312) of respondent and nonrespondent peer change agents, respectively, selected on the imputed networks were also selected on the observed network. Eigenvector also produced a stable set of peer change agents across the 100 imputed networks and was much less sensitive to the specified relational boundary.

Conclusions: Although we do not have a gold standard indicating which algorithm produces the most optimal set of peer change agents, the lower sensitivity of eigenvector centrality to key assumptions leads us to conclude that it may be preferable. The methods we employed to address the challenges in using Facebook networks may prove timely, given the rapidly increasing interest in using online social networks to improve population health.

Keywords: African Americans; HIV infections; computer simulation; data mining; peer group; pre-exposure prophylaxis; sexual and gender minorities; social media; social networking.

Figure 1

Illustration of the problem of unobserved tie imputation. Facebook friendships between individuals are classified into categories: observed respondent-respondent (bottom left quadrant), observed respondent-nonrespondent (diagonal quadrants), and unobserved nonrespondent-nonrespondent (top right quadrant). The approximate number of dyads in each quadrant is stated.

Figure 2

Illustration of the Facebook network data structure. Facebook friendships between respondents and between respondents and nonrespondents are observed. The friendships between nonrespondents are unobserved. Our data contain more nonrespondents than respondents.

Figure 3

Frequency plots for imputed networks: the top figure displays data for all 885 nodes, and the bottom figure displays a subset comprising the first 50 respondents and first 50 nonrespondents (bottom), uConnect 2013-2014. The bottom left and the diagonals cells in both matrices consist entirely of observed dyads that required no imputation. The top right cell contains unobserved dyads, and edges in these dyads were stochastically imputed, and hence, appear in grey. The bottom panel is shown to produce a clearer display of the cell shading.

Figure 4

Degree distributions of respondents (top) and nonrespondents (bottom) in the observed and imputed networks. The respondent degree distributions in the top graph are identical because the imputation does not impact respondent ties. The degrees are binned together in sets of size 10.

Figure 5

Distribution of the number of nodes selected as peer change agents on the imputed networks, conditional on their being selected at least once. This figure also illustrates the cutoff point for each algorithm, which is used to determine the sufficiency condition of peer change agent selection for each algorithm across the hundred imputations. KP: keyplayer; EV: eigenvector.

Figure 6

Proportion of nodes selected as sPCAs (peer change agents who met the sufficiency condition for each of the two peer change agent identification algorithms) on the imputed networks who were also selected as peer change agents on the observed network.