New query suggestion framework and algorithms: A case study for an educational search engine |
| |
Institution: | 1. Institute of Computing, Federal University of Amazonas, AM, Brazil;2. Department of Computer Science, Federal University of Minas Gerais, MG, Brazil;3. Institute of Computing, University of Campinas, SP, Brazil;1. Universitat Politècnica de València, 46022 Valencia, Spain;2. Sciling, 46022 Valencia, Spain;3. Brown University, Providence, RI 02912, United States;4. École Polytechnique de Montréal, QC 06079, Canada |
| |
Abstract: | Query suggestion is generally an integrated part of web search engines. In this study, we first redefine and reduce the query suggestion problem as “comparison of queries”. We then propose a general modular framework for query suggestion algorithm development. We also develop new query suggestion algorithms which are used in our proposed framework, exploiting query, session and user features. As a case study, we use query logs of a real educational search engine that targets K-12 students in Turkey. We also exploit educational features (course, grade) in our query suggestion algorithms. We test our framework and algorithms over a set of queries by an experiment and demonstrate a 66–90% statistically significant increase in relevance of query suggestions compared to a baseline method. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|