Khawatmi, Ahmad: Predicting Knowledge Gain during Web Search based on Eye-movement Patterns. Hannover : Gottfried Wilhelm Leibniz Universität, Institut für Verteilte Systeme, Bachelor Thesis, 2022, XVI, 52 S. DOI: https://doi.org/10.15488/13172
Abstract: | |
The content on the internet is expanding exponentially, and the virtual space has become a messy place. Therefore, acquiring information to fulfill the learning need is a difficult task. Search as Learning (SAL) is a new domain that investigates the importance of the learning process and supports individuals in acquiring information. Therefore, a solution to make obtaining information easier for knowledge seekers from a web search. Prior work in this field focused extensively on resource data (e.g., text and multimedia resources) and behavioral data (e.g., search interactions) to make a knowledge gain (KG) prediction during a web search. However, eye movement and reading pattern data are yet to be explored. Thereby, in this work, we introduce a set of features related to eye movements that would help us predict knowledge gain based on the reading pattern of the participants. For this purpose, we relied on data from a prior work-study, in which 114 participants had to acquire information about the foundation of lightning and thunder from a web search. We used a cutting-edge approach for the evaluation. Moreover, we extended with a word-level mapping to eye fixations of web pages, unlike prior work that attempted to rely on the eye’s central vision to map the eye fixations. Experimental results demonstrate the ability to predict knowledge gain based on the reading pattern and eye movements. | |
License of this version: | Es gilt deutsches Urheberrecht. Das Dokument darf zum eigenen Gebrauch kostenfrei genutzt, aber nicht im Internet bereitgestellt oder an Außenstehende weitergegeben werden. |
Document Type: | BachelorThesis |
Publishing status: | publishedVersion |
Issue Date: | 2022 |
Appears in Collections: | Fakultät für Elektrotechnik und Informatik |
pos. | country | downloads | ||
---|---|---|---|---|
total | perc. | |||
1 | Russian Federation | 177 | 40.14% | |
2 | Germany | 142 | 32.20% | |
3 | United States | 39 | 8.84% | |
4 | Peru | 11 | 2.49% | |
5 | Netherlands | 9 | 2.04% | |
6 | No geo information available | 7 | 1.59% | |
7 | China | 6 | 1.36% | |
8 | Italy | 5 | 1.13% | |
9 | France | 4 | 0.91% | |
10 | Egypt | 4 | 0.91% | |
other countries | 37 | 8.39% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.