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

Yilmaz, Tolga; Ozcan, Rifat; Altıngövde, İsmail Sengör; Ulusoy, Özgür

doi:10.1016/j.ipm.2018.10.013

Cited by 26 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Collins‐Thompson et al (2011) proposed to personalize Web search results by re‐ranking them with respect to the reading difficulty. More recently, Yilmaz, Ozcan, Altingovde, and Ulusoy (2019) proposed an approach in which they trained classifiers using various educational resources to predict the course category of question‐like queries, and then employed these predictions as a signal for re‐ranking the initial query results. Both works customized the final result list w.r.t.…”

Section: Related Workmentioning

confidence: 99%

Explicit diversification of search results across multiple dimensions for educational search

Yigit-Sert

Altıngövde

Macdonald

et al. 2020

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Making use of search systems to foster learning is an emerging research trend known as search as learning. Earlier works identified result diversification as a useful technique to support learning‐oriented search, since diversification ensures a comprehensive coverage of various aspects of the queried topic in the result list. Inspired by this finding, first we define a new research problem, multidimensional result diversification, in the context of educational search. We argue that in a search engine for the education domain, it is necessary to diversify results across multiple dimensions, that is, not only for the topical aspects covered by the retrieved documents, but also for other dimensions, such as the type of the document (e.g., text, video, etc.) or its intellectual level (say, for beginners/experts). Second, we propose a framework that extends the probabilistic and supervised diversification methods to take into account the coverage of such multiple dimensions. We demonstrate its effectiveness upon a newly developed test collection based on a real‐life educational search engine. Thorough experiments based on gathered relevance annotations reveal that the proposed framework outperforms the baseline by up to 2.4%. An alternative evaluation utilizing user clicks also yields improvements of up to 2% w.r.t. various metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Explicit diversification of search results across multiple dimensions for educational search

Yigit-Sert

Altıngövde

Macdonald

et al. 2020

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…User Dimension PK (Lu and Hsiao, 2017), (Taibi et al, 2017), (Syed and Collins-Thompson, 2018), (Syed and Collins-Thompson, 2016), (Jansen et al, 2009), (Yu et al, 2018), (Al-Tawil et al, 2019), (Rieh et al, 2012), (Sendurur et al, 2019) (Tibau et al, 2018), (Azpiazu et al, 2017), (Karanam and van Oostendorp, 2016), (Wilson et al, 2016), (Crescenzi, 2016), (Mao et al, 2016), (Bhattacharya and Gwizdka, 2019), (Ibieta et al, 2019), (Biletskiy et al, 2009), (Pereira et al, 2019) DI (Taibi et al, 2017), (Azpiazu et al, 2017), (Ibieta et al, 2019), (Yilmaz et al, 2019), (Biletskiy et al, 2009), (Lu and Hsiao, 2017), (Moraes et al, 2018) Interaction Dimension ESA (Tibau et al, 2018), (Lu and Hsiao, 2017), (Moraes et al, 2018), (Ghosh et al, 2018), (Bhattacharya and Gwizdka, 2019), (Yu et al, 2018), (Ibieta et al, 2019), (Vakkari et al, 2019), (Biletskiy et al, 2009) AV (Bhattacharya and Gwizdka, 2019), (Yu et al, 2018), (Rieh et al, 2012), (Karanam and van Oostendorp, 2016), (Ibieta et al, 2019),…”

Section: Dimension Variables Papersmentioning

confidence: 99%

Raising the Dimensions and Variables for Searching as a Learning Process: A Systematic Mapping of the Literature

Machado¹,

Gimenez²,

Siqueira³

2020

Anais Do XXXI Simpósio Brasileiro De Informática Na Educação (SBIE 2020)

View full text Add to dashboard Cite

Search engines are great allies in our daily educational tasks. However, usually, these tools are prepared only for factual learning and are less effective when dealing with more complex learning tasks. Thus, in recent years, Searching as Learning (SAL) research area has been developing from proposals that target the main challenges involving learning during the search process. The effectiveness of educational technologies in providing appropriate instructions depends directly on the input information. Gathering information on what should be taken into account in a search as a learning process can support the development of specialized search engines to support learning. Therefore, we performed a systematic mapping of the literature in order to gather this information, raising the dimensions and their associated variables.

show abstract

“…Conforme apresentado por Yilmaz et al (2019), para que seja possível prover uma ordenação de conteúdo específico para a educação, são necessários dois passos: a classificação da busca pelo tipo de consulta (intenção de aprendizado) e a arrumação do conteúdo recuperado (feita a partir dos critérios de relevância, foco deste trabalho). Objetos educacionais podem ser ordenados através de estratégias enquadradas em três categorias (Ochoa e Duval, 2008): por similaridade textual, por perfil de usuário e por revisão humana.…”

Section: Trabalhos Relacionadosunclassified

Google, se reordene e me ajude a aprender: Critérios de relevância para reordenar resultados de busca como um processo de aprendizagem

Pinelli¹,

Tibau²,

Siqueira³

2019

Anais Do XXX Simpósio Brasileiro De Informática Na Educação (SBIE 2019)

View full text Add to dashboard Cite

Search engines can assist people to conduct tasks during an informal learning experience, however their ranking criteria are focused to provide factual rather than procedural information. In this context, this paper presents relevance criteria in accordance with learning theories to support search results reorder based on content suitability to learning purposes. In order to evaluate the proposed criteria applicability, it was applied a survey to search engine users comparing Google's and modified search engine result pages. The survey indicated that the modified result was better accepted, especially by searching experts. It might be an indication that reorganized search results based on learning theories may support informal learning.

show abstract

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

Cited by 26 publications

References 44 publications

Explicit diversification of search results across multiple dimensions for educational search

Explicit diversification of search results across multiple dimensions for educational search

Raising the Dimensions and Variables for Searching as a Learning Process: A Systematic Mapping of the Literature

Google, se reordene e me ajude a aprender: Critérios de relevância para reordenar resultados de busca como um processo de aprendizagem

Contact Info

Product

Resources

About