Predicting and Reducing the Impact of \nErrors in Character-Based Text Entry
Bibliographic record
Abstract
This dissertation focuses on the effect of errors in character-based text entry techniques. The effect of errors is targeted from theoretical, behavioral, and practical standpoints. This document starts with a review of the existing literature. It then presents results of a user study that investigated the effect of different error correction conditions on popular text entry performance metrics. Results showed that the way errors are handled has a significant effect on all frequently used error metrics. The outcomes also provided an understanding of how users notice and correct errors. Building on this, the dissertation then presents a new high-level and method-agnostic model for predicting the cost of error correction with a given text entry technique. Unlike the existing models, it accounts for both human and system factors and is general enough to be used with most character-based techniques. A user study verified the model through measuring the effects of a faulty keyboard on text entry performance. Subsequently, the work then explores the potential user adaptation to a gesture recognizer’s misrecognitions in two user studies. Results revealed that users gradually adapt to misrecognition errors by replacing the erroneous gestures with alternative ones, if available. Also, users adapt to a frequently misrecognized gesture faster if it occurs more frequently than the other error-prone gestures. Finally, this work presents a new hybrid approach to simulate pressure detection on standard touchscreens. The new approach combines the existing touch-point- and time-based methods. Results of two user studies showed that it can simulate pressure detection more reliably for at least two pressure levels: regular (~1 N) and extra (~3 N). Then, a new pressure-based text entry technique is presented that does not require tapping outside the virtual keyboard to reject an incorrect or unwanted prediction. Instead, the technique requires users to apply extra pressure for the tap on the next target key. The performance of the new technique was compared with the conventional technique in a user study. Results showed that for inputting short English phrases with 10% non-dictionary words, the new technique increases entry speed by 9% and decreases error rates by 25%. Also, most users (83%) favor the new technique over the conventional one. Together, the research presented in this dissertation gives more insight into on how errors affect text entry and also presents improved text entry methods.
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 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".