Publication Date


Date of Final Oral Examination (Defense)


Type of Culminating Activity


Degree Title

Master of Science in Computer Science


Computer Science

Major Advisor

Maria Soledad Pera, Ph.D.


Casey Kennington, Ph.D.


Jerry Alan Fails, Ph.D.


Michael Ekstrand, Ph.D.


Children regularly turn to search engines (SEs) to locate school-related materials. Unfortunately, research has shown that when utilizing SEs, children do not always access resources that specifically target them. To support children, popular and child-oriented SEs make available a safe search filter, which is meant to eliminate inappropriate resources. Safe search is, however, not always the perfect deterrent as pornographic and hate-based resources may slip through the filter, while resources relevant to an educational search context may be misconstrued and filtered out. Moreover, filtering inappropriate resources in response to children searches is just one perspective to consider in offering them the right resources, as aspects that are key for this audience are overlooked, including reading level, resource subjectivity, or the context of the search (i.e., educational setting). To verify impediments of existing SEs in response to children searches conducted at school, we conduct an empirical study on well known SEs: Google, Bing, their safe search counterparts, Kidrex and Kidzsearch. Based on our findings, we present KiSuRF, a novel filtering and ranking strategy that not only eliminates inappropriate resources while retaining education-relevant ones, but also simultaneously examines multiple qualitative aspects of online resources in order to offer suitable ones. Empirical studies conducted using diverse datasets, including one comprised of children search sessions in the school setting, showcase (i) the usefulness of simultaneously integrating evidences from multiple perspectives in order to inform resource suitability detection, and (ii) the correctness and effectiveness of KiSuRF in prioritizing child-suitable resources.