Crowdsourced Exploration of Mobile App Features: A Case Study of the Fort McMurray Wildfire
Bibliographic record
Abstract
The ubiquity of mobile devices has led to unprecedented growth in not only the usage of apps, but also their capacity to meet people's needs. Smart phones take on a heightened role in emergency situations, as they may suddenly be among their owner's only possessions and resources. The 2016 wildfire in Fort McMurray, Canada, intrigued us to study the functionality of the existing apps by analyzing social media information. We investigated a method to suggest features that are useful for emergency apps. Our proposed method called MAPFEAT, combines various machine learning techniques to analyze tweets in conjunction with crowdsourcing and guides an extended search in app stores to find currently missing features in emergency apps based on the needs stated in social media. MAPFEAT is evaluated by a real-world case study of the Fort McMurray wildfire, where we analyzed 69,680 unique tweets recorded over a period from May 2nd to May 7th, 2016. We found that (i) existing wildfire apps covered a range of 28 features with not all of them being considered helpful or essential, (ii) a large range of needs articulated in tweets can be mapped to features existing in non-emergency related apps, and (iii) MAPFEAT's suggested feature set is better aligned with the needs expressed by general public. Only six of the features existing in wildfire apps is among top 40 crowdsourced features explored by MAPFEAT, with the most important one just ranked 13th. By using MAPFEAT, we proactively understand victims' needs and suggest mobile software support to the people impacted. MAPFEAT looks beyond the current functionality of apps in the same domain and extracts features using variety of crowdsourced data.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".