Exploring multiple diversification strategies for academic citation contexts recommendation

Chen, Haihua; Yang, Yunhan; Lu, Wei; Chen, Jiangping

doi:10.1108/el-02-2020-0046

Cited by 5 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The construction and evaluation of our testing dataset resembles the approach used by Chen et al (2020), yet it's tailored to our research context. We utilized a subset of the dataset provided by Pantula and Kuppasamy (2020), specifically focusing on films produced in spoken English with English subtitles.…”

Section: Datamentioning

confidence: 99%

Enriching Library Holdings for English Language Learners: Applying Traditional Readability Formulas and Modern Cohesion Methods to Film

Durward,

Organisciak

2023

Proceedings of the Association for Information Science and Tech

View full text Add to dashboard Cite

This study evaluates the effectiveness of various readability measures when assessing the difficulty of film materials for English Language Learners (ELLs). Library materials catering to ELLs are frequently limited to formal instruction texts and fiction materials. This study explores the feasibility of less laborious, computational text assessment methods to better understand library holdings from the perspective of ELL appropriateness. The investigation applies traditional formulaic readability measures and modern cohesion methods to film subtitle data. While text difficulty assessment with readability measures has been widely studied, there is a need to investigate which measures are most suitable for film application. In addition to evaluating existing readability measures, a more robust composite score is also presented, combining aspects of traditional readability formulas and modern cohesion methods. The experiments were conducted on real‐world datasets and tested on film data marked for difficulty by ELLs.

show abstract

Section: Datamentioning

confidence: 99%

Enriching Library Holdings for English Language Learners: Applying Traditional Readability Formulas and Modern Cohesion Methods to Film

Durward,

Organisciak

2023

Proceedings of the Association for Information Science and Tech

View full text Add to dashboard Cite

show abstract

“…Following that idea, Caragea et al relied on singular value decomposition as a more efficient and extendable approach for citation recommendation [3]. Other approaches make use of deep learning techniques for citation recommendation but focus on context-sensitive scenarios [4,47,48,49,50,51,52]. Thus, we recognize the need for new methods that are not only based on item co-occurrence but also take additional metadata into account for these partial set completion problems.…”

Section: Research Paper and Citation Recommendationmentioning

confidence: 99%

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

Vagliano¹,

Galke²,

Scherp³

2021

Preprint

View full text Add to dashboard Cite

We address the problem of recommending relevant items to a user in order to "complete" a partial set of items already known. We consider the two scenarios of citation and subject label recommendation, which resemble different semantics of item co-occurrence: relatedness for co-citations and diversity for subject labels. We assess the influence of the completeness of an already known partial item set on the recommender performance. We also investigate data sparsity through a pruning parameter, and the influence of using additional metadata. As recommender models, we focus on different autoencoders, which are particularly suited for reconstructing missing items in a set. We extend autoencoders to exploit a multi-modal input of text and structured data. Our experiments on six real-world datasets show that supplying the partial item set as input is helpful when item co-occurrence resembles relatedness, while metadata are effective when co-occurrence implies diversity. This outcome means that the semantics of item co-occurrence is an important factor. The simple item co-occurrence model is a strong baseline for citation recommendation. However, autoencoders have the advantage to enable exploiting additional metadata besides the partial item set as input, and achieve comparable performance. For the subject label recommendation task, the title is the most important attribute. Adding more input modalities sometimes even harms the result. In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate recommendation model and carefully decide which metadata to exploit.

show abstract

Recommendations for item set completion: on the semantics of item co-occurrence with data sparsity, input size, and input modalities

2022

View full text Add to dashboard Cite

We address the problem of recommending relevant items to a user in order to “complete” a partial set of already-known items. We consider the two scenarios of citation and subject label recommendation, which resemble different semantics of item co-occurrence: relatedness for co-citations and diversity for subject labels. We assess the influence of the completeness of an already known partial item set on the recommender’s performance. We also investigate data sparsity by imposing a pruning threshold on minimum item occurrence and the influence of using additional metadata. As models, we focus on different autoencoders, which are particularly suited for reconstructing missing items in a set. We extend autoencoders to exploit a multi-modal input of text and structured data. Our experiments on six real-world datasets show that supplying the partial item set as input is usually helpful when item co-occurrence resembles relatedness, while metadata are effective when co-occurrence implies diversity. The simple item co-occurrence model is a strong baseline for citation recommendation but can provide good results also for subject labels. Autoencoders have the capability to exploit additional metadata besides the partial item set as input, and achieve comparable or better performance. For the subject label recommendation task, the title is the most important attribute. Adding more input modalities sometimes even harms the results. In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate model and carefully decide which metadata to exploit.

show abstract

Exploring multiple diversification strategies for academic citation contexts recommendation

Cited by 5 publications

References 38 publications

Enriching Library Holdings for English Language Learners: Applying Traditional Readability Formulas and Modern Cohesion Methods to Film

Enriching Library Holdings for English Language Learners: Applying Traditional Readability Formulas and Modern Cohesion Methods to Film

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

Recommendations for item set completion: on the semantics of item co-occurrence with data sparsity, input size, and input modalities

Contact Info

Product

Resources

About