FoodSwitch: A Mobile Phone App to Enable Consumers to Make Healthier Food Choices and Crowdsourcing of National Food Composition Data
Bibliographic record
Abstract
BACKGROUND: Front-of-pack nutrition labeling (FoPL) schemes can help consumers understand the nutritional content of foods and may aid healthier food choices. However, most packaged foods in Australia carry no easily interpretable FoPL, and no standard FoPL system has yet been mandated. About two thirds of Australians now own a smartphone. OBJECTIVE: We sought to develop a mobile phone app that would provide consumers with easy-to-understand nutrition information and support the selection of healthier choices when shopping for food. METHODS: An existing branded food database including 17,000 Australian packaged foods underpinned the project. An iterative process of development, review, and testing was undertaken to define a user interface that could deliver nutritional information. A parallel process identified the best approach to rank foods based on nutritional content, so that healthier alternative products could be recommended. RESULTS: Barcode scanning technology was identified as the optimal mechanism for interaction of the mobile phone with the food database. Traffic light labels were chosen as the preferred format for presenting nutritional information, and the Food Standards Australia New Zealand nutrient profiling method as the best strategy for identifying healthier products. The resulting FoodSwitch mobile phone app was launched in Australia in January 2012 and was downloaded by about 400,000 users in the first 18 months. FoodSwitch has maintained a 4-plus star rating, and more than 2000 users have provided feedback about the functionality. Nutritional information for more than 30,000 additional products has been obtained from users through a crowdsourcing function integrated within the app. CONCLUSIONS: FoodSwitch has empowered Australian consumers seeking to make better food choices. In parallel, the huge volume of crowdsourced data has provided a novel means for low-cost, real-time tracking of the nutritional composition of Australian foods. There appears to be significant opportunity for this approach in many other countries.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.020 | 0.006 |
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".