2026-09-19T17:24:09Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1327342026-06-06T00:55:41Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Tomas Palacios and Daniel Belcher.
Clayberg, Lauren
(Lauren W.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2021-10-06T17:43:49Z
2021-10-06T17:43:49Z
2020
2020
https://hdl.handle.net/1721.1/132734
1265297009
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 89-90).
Machine learning has enhanced many existing tech industries, including end-to-end test automation for web applications. One of the many goals that mabl and other companies have in this new tech initiative is to automatically gain insight into how web applications work. The task of web element role prediction is vital for the advancement of this newly emerging product category. I applied supervised visual machine learning techniques to the task. In addition, I created a novel dataset and present detailed attribute distribution and bias information. The dataset is used to provide updated baselines for performance using current day web applications, and a novel metric is provided to better quantify the performance of these models. The top performing model achieves an F1-score of 0.45 on ten web element classes. Additional findings include color distributions for different web element roles, and how some color spaces are more intuitive to humans than others.
by Lauren Clayberg.
M.Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
90 pages
eng
Massachusetts Institute of Technology
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Web element role prediction from visual information using a novel dataset
Thesis
application/pdf
2021-10-06T17:43:49Z
Publication
Master
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="c1471439-145c-49b5-96b8-86d7e9cb3230">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Web element role prediction from visual information using a novel dataset</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2020</PublicationDate>
<Authors>
<Author>
<DisplayName>Clayberg, Lauren
(Lauren W.)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Machine learning has enhanced many existing tech industries, including end-to-end test automation for web applications. One of the many goals that mabl and other companies have in this new tech initiative is to automatically gain insight into how web applications work. The task of web element role prediction is vital for the advancement of this newly emerging product category. I applied supervised visual machine learning techniques to the task. In addition, I created a novel dataset and present detailed attribute distribution and bias information. The dataset is used to provide updated baselines for performance using current day web applications, and a novel metric is provided to better quantify the performance of these models. The top performing model achieves an F1-score of 0.45 on ten web element classes. Additional findings include color distributions for different web element roles, and how some color spaces are more intuitive to humans than others.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>