Bibliographic record
Abstract
Core Ideas Social media data provide quantitative and qualitative data on agricultural practices. Twitter data accurately captures timing of crop planting across the United States. Maximum positive sentiment in planting tweets aligned with optimal planting period. Opportunities for mapping emerging agricultural issues and targeted intervention. Challenges include data availability and representativeness of social media users. The use of social media in scientific research is rapidly increasing, typically focusing on discrete events of interest to many people and/or spatially mapping a variable of interest. Relatively little research has been done on the utility of social media for monitoring the spatiotemporal patterns of day‐to‐day life, and none within the agricultural sciences. Here, I discuss the potential applications and limitations of social media data for agricultural research. As an example, I demonstrate the ability of Twitter to map state‐level corn and soy planting progress in the conterminous United States. Results compare favorably to traditional survey‐based crop progress monitoring, with mean absolute differences of <10% for most state‐crop combinations. I also highlight the additional contextual information available from social media data including factors contributing to replanting decision‐making and the evolution of farmer sentiment through time. Using analogs from other disciplines, I then discuss key opportunities and challenges for agricultural research using social media. Social media is particularly well‐suited for identifying emerging agricultural issues (e.g., weather, crop pests) and guiding extension and outreach directly to affected areas. However, limited data and unknown representativeness of social media users relative to the overall agricultural population are challenges which must be addressed for social media‐based agricultural research in the future.
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 | 0.020 | 0.100 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.013 | 0.015 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.013 | 0.014 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.018 | 0.007 |
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".