Design and Development of a Chatbot as an Alternative Web-browser for those with Severe Motor Impairments
Bibliographic record
Abstract
Ensuring equitable digital access for individuals with severe motor impairments remains a pressingchallenge. Conventional web navigation relies heavily on manual interactions—pointing, clicking, and typing—that are often inaccessible to users with limited motor function or atypical speech patterns. This research addresses the digital divide by proposing and evaluating two complementary solutions: (1) an eye gaze-controlled chatbot for hands-free, conversational access to online information, and (2) a synthetic data generation approach to improve voice-based chatbot systems’ ability to interpret atypical speech. First, an empirical study involving 20 participants established optimal parameters for eye-gaze target interaction in an Augmented Reality (AR) environment: a 2.25-meter eye-to-target distance and a 0.072-meter Area of Interest (Area of Interest (AOI)) diameter. These parameters achieved target selection rates exceeding 90%. Guided by these findings, the “EyeChat” system integrates an innovative circular text-entry interface that centralizes frequently used keys, reducing unnecessary eye movement. In a subsequent study with 12 participants, EyeChat demonstrated a 4.1-fold increase in text-entry speed (from 2.41 to 9.88 words per minute), a reduction in error rate (from 4.53% to 1.01%), and high user satisfaction, with over 83% of responses meeting or exceeding expectations. Second, to address the needs of individuals who rely on speech-based inputs yet exhibit atypical linguistic patterns, a novel synthetic data generation technique was developed. This method enhanced intent classification accuracy by 4.39% (from 75.86% to 80.25%) without compromising user privacy or requiring large-scale data collection from vulnerable populations. Using an optimized AR-based eye-gaze chatbot, this dissertation lays the foundation for novel eye-gaze-driven chatbot experiences. In addition, the synthetic data generation strategy for atypical linguistic patterns can help develop high-performance speech recognition, which is necessary for voice-based chatbot systems. These two types of chatbot systems can help close the digital divide for people with severe motor impairments. Future integration of synthetic data generation techniques into voice-based chatbots, in combination with the eye-gaze-based system, has the potential ii to further enhance accessibility and foster a more inclusive digital environment. This multimodal approach could afford the user choice between eye gaze and speech input, and thus better accommodate diverse motor and speech abilities.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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".