{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dyslexml-screening-tool-for-dyslexia-using","title":"DysLexML: Screening Tool for Dyslexia Using Machine Learning","arxiv_id":"1903.06274","date":"2019-03-14","proceeding":null,"authors":["Thomais Asvestopoulou","Victoria Manousaki","Antonis Psistakis","Ioannis Smyrnakis","Vassilios Andreadakis","Ioannis M. Aslanides","Maria Papadopouli"],"abstract":"Eye movements during text reading can provide insights about reading\ndisorders. Via eye-trackers, we can measure when, where and how eyes move with\nrelation to the words they read. Machine Learning (ML) algorithms can decode\nthis information and provide differential analysis. This work developed\nDysLexML, a screening tool for developmental dyslexia that applies various ML\nalgorithms to analyze fixation points recorded via eye-tracking during silent\nreading of children. It comparatively evaluated its performance using\nmeasurements collected in a systematic field study with 69 native Greek\nspeakers, children, 32 of which were diagnosed as dyslexic by the official\ngovernmental agency for diagnosing learning and reading difficulties in Greece.\nWe examined a large set of features based on statistical properties of\nfixations and saccadic movements and identified the ones with prominent\npredictive power, performing dimensionality reduction. Specifically, DysLexML\nachieves its best performance using linear SVM, with an a accuracy of 97 %,\nwith a small feature set, namely saccade length, number of short forward\nmovements, and number of multiply fixated words. Furthermore, we analyzed the\nimpact of noise on the fixation positions and showed that DysLexML is accurate\nand robust in the presence of noise. These encouraging results set the basis\nfor developing screening tools in less controlled, larger-scale environments,\nwith inexpensive eye-trackers, potentially reaching a larger population for\nearly intervention.","url_abs":"http://arxiv.org/abs/1903.06274v1","url_pdf":"http://arxiv.org/pdf/1903.06274v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dyslexml-screening-tool-for-dyslexia-using","repo_url":"https://github.com/AryaKoureshi/Magnocellular-Parvocellular-Coactivation-Task-in-MATLAB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.06274","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}