Deep Learning and Statistical Models to Analyse Online Misinformation and Hate Speech Impact on African Youth
Bibliographic record
Abstract
This study examines the perceptions, behaviour, and digital experiences of African youth in relation to online misinformation and hate speech. Using a large-scale, cross-national survey with 10,005 valid responses, the research relies on both statistical clustering and deep learning-based autoencoder models to group youth together based on their trust in information, concern about misinformation, verification behaviours and platform usage. The dual-method analysis highlights three distinct behavioural and attitudinal clusters of youth, denoting different levels of digital skeptical engagement, exposure, and civic engagement. The findings highlight the heterogeneity within the youth population and emphasize that a one-size-fits-all approach to combating misinformation is insufficient. Notably, youth with high concern also demonstrated strong verification habits, while less engaged clusters exhibited low concern and limited digital resilience. These insights offer a foundation for designing cluster-specific interventions and media literacy strategies that are regionally and behaviourally responsive. This combination advances research through unsupervised deep learning on large social survey data, as well as demonstrating the utility of deep learning in revealing latent behaviours. The implications of this study's findings are timely for educators, policy makers and digital platforms more broadly, that want to foster informed and safe digital participation for African youth. As scalable, data-driven framework is a contribution towards an inclusive digital policy package for varied youth realities that exist in an African context.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".