Towards Extracting Software Requirements from App Reviews using Seq2seq Framework
Bibliographic record
Abstract
Mobile app reviews are a large-scale data source for software improvements. A key task in this context is effectively extracting requirements from app reviews to analyze the users’ needs and support the software’s evolution. Recent studies show that existing methods fail at this task since app reviews usually contain informal language, grammatical and spelling errors, and a large amount of irrelevant information that might not have direct practical value for developers. To address this, we propose a novel reformulation of requirements extraction as a Named Entity Recognition (NER) task based on the sequence-to-sequence (Seq2seq) generation approach. With this aim, we propose a Seq2seq framework, incorporating a BiLSTM encoder and an LSTM decoder, enhanced with a self-attention mechanism, GloVe embeddings, and a CRF model. We evaluated our framework on two datasets: a manually annotated set of 1,000 reviews (Dataset 1) and a crowdsourced set of 23,816 reviews (Dataset 2). The quantitative evaluation of our framework showed that it outperformed existing state-of-the-art methods with an F1 score of 0.96 on Dataset 2, and achieved comparable performance on Dataset 1 with an F1 score of 0.47.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.004 |
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".