Assessing Sustainable Development Goal Alignment in Local Food Systems: Insights from an Automated Text Analysis of the Organizational Literature
Bibliographic record
Abstract
There is growing interest in assessing local food systems to guide efforts toward sustainability and aligning these assessments with the United Nations’ 17 Sustainable Development Goals (SDGs). However, the complexity of portraying local food systems poses numerous challenges for local communities, and automated text analysis and artificial intelligence (AI) offer promising solutions. This study tested the use of an automated textual analysis to assess the alignment of the Mauricie region’s food system in Quebec, Canada, with the SDGs. The analysis examined 35 organizational documents from the region using an automated text analysis based on a list of keywords for each SDG. Initially, the analysis revealed that several initiatives in the Mauricie region covered specific SDGs quite well, such as eliminating hunger (SDG 2). Areas such as health and well-being (SDG 3) received moderate attention, while SDGs such as life below water and on land (SDGs 14 and 15) were less emphasized. When these results were presented to regional stakeholders, these stakeholders reported that the findings did not closely reflect their perceptions of the food system. This study confirms the potential of automated textual analysis and AI in assessing local food systems and underscores the parameters and challenges of accurately portraying sustainability in local food systems.
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 | 0.005 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.012 | 0.009 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".