Learning Sentiment Analysis for Accessibility User Reviews
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Nowadays, people use different ways to express emotions and sentiments such as facial expressions, gestures, speech, and text. With the exponentially growing popularity of mobile applications (apps), accessibility apps have gained importance in recent years as it allows users with specific needs to use an app without many limitations. User reviews provide insightful information that helps for app evolution. Previously, work has been done on analyzing the accessibility in mobile applications using machine learning approaches. However, to the best of our knowledge, there is no work done using sentiment analysis approaches to understand better how users feel about accessibility in mobile apps. To address this gap, we propose a new approach on an accessibility reviews dataset, where we use two sentiment analyzers, i.e., TextBlob and VADER along with Term Frequency—Inverse Document Frequency (TF-IDF) and Bag-of-words (BoW) features for detecting the sentiment polarity of accessibility app reviews. We also applied six classifiers including, Logistic Regression, Support Vector, Extra Tree, Gaussian Naive Bayes, Gradient Boosting, and Ada Boost on both sentiments analyzers. Four statistical measures namely accuracy, precision, recall, and F1-score were used for evaluation. Our experimental evaluation shows that the TextBlob approach using BoW features achieves better results with accuracy of 0.86 than the VADER approach with accuracy of 0.82.
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.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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 it