Towards Addressing Ethical Concerns of Mobile Applications from User Feedback
Bibliographic record
Abstract
The proliferation of mobile applications (mobile apps) has significantly altered user interactions with various services such as transportation, finance, and healthcare. However, this widespread adoption has also led to a surge in ethical concerns, such as privacy, security, and accessibility, which are commonly subsumed under non-functional requirements. Ride-hailing apps like Uber and Lyft exemplify this, with passengers and drivers reporting issues such as opaque wage algorithms, surge pricing, and safety incidents. Users often raise these concerns through app reviews, which have proved to be a useful datasource for many areas of software engineering (e.g., requirement engineering, testing, etc.). However, effectively mining this information poses two key challenges: (1) ethical concern-related app reviews generally use domain-specific language and represent only a small fraction of the massive volume of app reviews; and (2) user feedback is unstructured, noisy, and linguistically diverse, making it difficult to extract actionable software requirements from app reviews using traditional methods to address users’ ethical concerns. To address these challenges, we drive our research through three research objectives. First, we perform a large-scale analysis of ride-hailing apps using driver and passenger reviews, revealing significant concerns re-lated to transparency, fairness, accountability, and safety. Next, we propose a novel domain-specific context-aware approach to automatically identify ethical concern-related app reviews. We evaluate our proposed approach on two datasets from two different domains, finance and mental health (MH), and extract 748 privacy reviews from the MH domain and 2,178 privacy/security reviews from the finance domain. Finally, we propose two approaches to efficiently extract requirements from ethical concern-related app reviews. The preliminary evaluation of both approaches on benchmark datasets shows their potential for app developers to translate users’ concerns into actionable requirements. In conclusion, our findings could assist developers and system architects in recognizing and prioritizing non-functional requirements at the initial stages of the development lifecycle, whereas researchers can expand upon this synthesis to create tools for the automated detection of ethical concerns.
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 | 0.013 | 0.091 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.011 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".