Improving educational web search for question-like queries through subject classification

2019-01-01
Yilmaz, Tolga
Ozcan, Rifat
Altıngövde, İsmail Sengör
ULUSOY, ÖZGÜR
Students use general web search engines as their primary source of research while trying to find answers to school-related questions. Although search engines are highly relevant for the general population, they may return results that are out of educational context. Another rising trend; social community question answering websites are the second choice for students who try to get answers from other peers online. We attempt discovering possible improvements in educational search by leveraging both of these information sources. For this purpose, we first implement a classifier for educational questions. This classifier is built by an ensemble method that employs several regular learning algorithms and retrieval based approaches that utilize external resources. We also build a query expander to facilitate classification. We further improve the classification using search engine results and obtain 83.5% accuracy. Although our work is entirely based on the Turkish language, the features could easily be mapped to other languages as well. In order to find out whether search engine ranking can be improved in the education domain using the classification model, we collect and label a set of query results retrieved from a general web search engine. We propose five ad-hoc methods to improve search ranking based on the idea that the query-document category relation is an indicator of relevance. We evaluate these methods for overall performance, varying query length and based on factoid and non-factoid queries. We show that some of the methods significantly improve the rankings in the education domain.
INFORMATION PROCESSING & MANAGEMENT

Suggestions

Identifying the effectiveness of a web search engine with Turkish domain dependent impacts and global scale information retrieval improvements
Fidan, Güven; Demirörs, Onur; Yöndem, Meltem Turhan; Department of Information Systems (2012)
This study investigates the effectiveness of a Web search engine with newly added or improved features in Web search engine architecture. These features can be categorized into three groups: The impact of link quality and usage information on page importance calculation; the use of Turkish stemmer for indexing and query substitution; and, the use of thumbnails for Web search engine result visualization. As Web search engines have become the primary means for finding and accessing information on the Internet...
Limitations and improvement opportunities for implicit result diversification in search engines
Ulu, Yaşar Barış; Altıngövde, İsmail Sengör; Department of Computer Engineering (2019)
Search engine users essentially expect to find the relevant results for their query. Additionally, the results of the query should contain different possible query intents, which leads to the well-known problem of search result diversification. Our work first investigates the limitations of implicit search result diversification, and in particular, reveals that typical optimization tricks (such as clustering) may not necessarily improve the diversification effectiveness. Then, as our second contribution, we...
Ask a Scientist Website: Trends in Chemistry Questions in Turkey
Elmas, Ridvan; Akın Çelebi, Fatma; Geban, Ömer (2013-11-01)
The purpose of this study was to investigate questions submitted by users of a website that is popular with Turkish students learning about chemistry and thereby to inform teachers about trends in student interest. The website contains articles and information about chemistry and encourages visitors to "Ask a Scientist" questions about the subject. Over 1,500 enquiries, submitted over a 5-year period between 2006 and 2011, were classified according to field of interest in chemistry, type of information requ...
Development of Metacognitive Skills Inventory for Internet Search (MSIIS): Exploratory and Confirmatory Factor Analyses
Şendurur, Emine; Yıldırım, Zahide (Ilkogretim Online, 2018-01-01)
This study reports the development of metacognition inventory for Internet search for middle school students. In this study, analysis and results of both exploratory and confirmatory factors are reported. Firstly, 37-items were generated considering literature review and metacognitive challenges faced during the search process, and pilot exploratory factor analysis was conducted. Secondly, the final version of the scale was distributed to 273 seventh grade students, and the existing constructs were extracte...
A framework for information quality and coverageassessment for type 2 diabetes websites
Ölçer, Didem; Taşkaya Temizel, Tuğba; Department of Information Systems (2020-10-22)
Health information seekers often use search engines to access high-quality and up-to-date information. However, finding online high-quality health information is increasingly getting difficult due to the high volume of information generated by non-experts in the area. There are manual tools which help end-users in assessing the quality of websites. However, they are labour-intensive. This thesis aims to propose a framework that automatically evaluates the content coverage and quality of health websites acco...
Citation Formats
T. Yilmaz, R. Ozcan, İ. S. Altıngövde, and Ö. ULUSOY, “Improving educational web search for question-like queries through subject classification,” INFORMATION PROCESSING & MANAGEMENT, pp. 228–246, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/37220.