Tailoring Facebook Advertisements to Reach Gay and Bisexual Men: Short Report (Preprint)
Bibliographic record
Abstract
BACKGROUND Facebook advertisements are an important way for public health agencies and researchers to reach gay and bisexual men (gbMSM). However, few published studies have examined how to maximize engagement by tailoring and targeting Facebook advertisements to this population. OBJECTIVE To determine whether different types of ad messaging and imagery were associated with greater user engagement among male Facebook users, aged 18+, in Vancouver, Toronto, and Montreal. METHODS We compared the success of 24 Facebook ad campaigns – varied by image type (Neutral vs. Sexy), message (Financial Incentive, Altruism, Personal Health), target location (Vancouver, Toronto, and Montreal), language (English, French), and target demographics (age: 18-24, 25-34, 35-44, 45-54, 55-64, 65+). Bivariate and multivariable Poisson regression models tested the effect of each variable on the ad’s click rate (i.e., number of clicks on ad / number of users shown ad) controlling for average number of impressions per person. Interaction terms between age and image type and between age and message type were also considered in our final multivariable models to explore the role of age in shaping engagement behavior. RESULTS A total of 351,624 impressions among 257,136 users were made, resulting in 4,267 clicks. At the bivariate level, a sexy image (vs. a neutral image) and a financial incentive message (vs. an altruistic message) were predictive of higher click rates. However, in multivariable modeling, the success of the sexualized image appeared to be driven primarily by its popularity among older men – as suggested by the positive association for older men in the interaction effect (P < 0.001). Similarly, for messaging, the success of the financial incentive message appeared to be negatively associated with age in the interaction effect (P < 0.001) – suggestive of its popularity among younger users. Nevertheless, the main effect for the financial incentive image remained strong and positive even when controlling for the interaction term (P < 0.001). CONCLUSIONS These results demonstrate that both user targets and post-related characteristics impact user engagement. Furthermore, it was found that post and user characteristics have the potential to interact – highlighting the importance of considering not only the content of advertisements, but to whom they are tailored. Future studies are needed to understand what motivates specific sub-groups of gbMSM to engage with tailored content on Facebook.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.023 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".