Social-DeepWriter: An iterative retrieval-augmented framework for strategic social media content generation
Bibliographic record
Abstract
Social media has become a critical domain for strategic communication, influencing public perception and supporting both civil and military operations. In high-tempo information environments, traditional manual content creation is often too slow and resource-intensive to meet the demands of real-time engagement. While large language models (LLMs) such as GPT-4 offer the capability to generate human-like text at scale, their reliance on static training data limits their contextual relevance, factual accuracy, and responsiveness to evolving mission needs. To overcome these limitations, this paper introduces Social-DeepWriter, an AI-enabled framework for the automatic generation of mission-aligned social media content. Built upon the Deep Research paradigm, Social-DeepWriter enhances traditional Retrieval-Augmented Generation (RAG) by incorporating iterative query refinement, multi-hop retrieval, and content evaluation, mirroring the layered reasoning of human analysts. We evaluate how factors such as retrieval quality, prompt design, and generation constraints influence the informativeness, coherence, and strategic fit of generated posts. Our findings highlight the potential of Social-DeepWriter to support dual-use communication scenarios, including military public affairs, psychological operations, and rapid-response campaigns, where accuracy, adaptability, and scalability are essential.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".