CRII: III: Children and Information Retrieval Tasks: Search Intent, Query Suggestions, and Adequate Online Resources

Children are introduced to the Web at increasingly young ages. While early exposure can help them build foundational skills vital in a knowledge-rich society, search tools were not designed with children in mind nor do retrieved results explicitly target children. Most engines do not support children's inquiry approaches (or do not support them well) and typically do not return content suitable to children's interests or reading levels. This need is important to address given that early experiences can affect attitudes in using the Web, skill development in making adequate use of resources for personal and educational interests, and the ability to leverage information and use it to make contributions into adulthood. The PI and her team will design and develop software modules as search engine add-ons to meet the needs of children searching the Web. The modules, which will upgrade current computation infrastructure, will be domain-independent, tailored to children, and usable on Google, to locate child-friendly educational- and leisure-related information. Research outputs will facilitate children's engagement with technology by improving their interactions on the Web. The proposed work can potentially further computer science research across a wide range of possible applications to impact the development of increasingly essential research and analysis skills among the general population of K-9 school-aged children and the underserved. Partnerships with Idaho K-9 classrooms will allow the research team to gather feedback from children and teachers and verify the usefulness of the proposed modules in their intended, formal setting. An underrepresented minority in computer science, the female, Hispanic PI will recruit and mentor female and/or Hispanic graduate student researchers. The team will disseminate research results at interdisciplinary conferences, and make educational material produced as part of the research effort available to teachers. The proposed work will advance computer science research and technology and benefit childhood instruction across a wide variety of ages and domains. It will also address three significant problems in web information retrieval for children: search intent, query suggestion, and information filtering. Common Core state standards of education and online sources will help define target content areas. Together, the proposed modules offer children a way to post (natural language) queries that overcome common search challenges. The proposed modules will: (1) identify search intent on-the-fly given a child's natural language or keyword query; (2) suggest queries based on keywords and phrases in child vocabulary lists, literature, content written by children, and subject areas appealing to youngsters; and (3) filter results to meet readability and suitability levels as well as domain categories that children prefer. Researchers will conduct studies to verify module usefulness and measure the degree to which search environments enhanced with these modules can benefit educational tasks. The team will also integrate research and education by facilitating student research, advancing current technology, and contributing to the specific needs of children. For further information see the project web page: http://cs.boisestate.edu/~sole/web/index.html#projects