Hidden features identification for designing an efficient research article recommendation system

Chaudhuri, Arpita; Sinhababu, Nilanjan; Sarma, Monalisa; Samanta, Debasis

doi:10.1007/s00799-021-00301-2

Cited by 13 publications

(19 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Novel rarely used Evaluation Measures. In our considered approaches we only encountered three novel evaluation measures: Recommendation quality as defined by Chaudhuri et al [ 26 ] is the acceptance of recommendations by users rated on a Likert scale from 1 to 10.…”

Section: Discussionmentioning

confidence: 99%

“…For venue-based popularity measures, we found an unspecific reputation notion [ 116 ] as well as incorporation of the impact factor [ 26 , 117 ].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Users can be modelled as a combination of features of papers they interacted with [19,21], e.g. their clicked [26] or authored publications [22]. Papers can for example be represented by their textual content [88].…”

Section: Problem Statementmentioning

confidence: 99%

“…We differentiate between profiles derived from user interactions and ones derived from papers. Most user profiles are constructed from users' actual interactions: unspecified historical interaction [30,37,56,57,64,118], the mean of the representation of interacted with papers [19], time decayed interaction behaviour [62], liked papers [69,123], bookmarked papers [84,119], read papers [111,113], rated papers [3,4,110], clicked on papers [24,26,49], categories of clicked papers [1], features of clicked papers [104], tweets [74][75][76], social interactions [65] and explicitly defined topics of interest tags [119].…”

Section: User Profilementioning

confidence: 99%

See 3 more Smart Citations

Scientific paper recommendation systems: a literature review of recent publications

Kreutz

Schenkel

2022

Int J Digit Libr

View full text Add to dashboard Cite

Scientific writing builds upon already published papers. Manual identification of publications to read, cite or consider as related papers relies on a researcher’s ability to identify fitting keywords or initial papers from which a literature search can be started. The rapidly increasing amount of papers has called for automatic measures to find the desired relevant publications, so-called paper recommendation systems. As the number of publications increases so does the amount of paper recommendation systems. Former literature reviews focused on discussing the general landscape of approaches throughout the years and highlight the main directions. We refrain from this perspective, instead we only consider a comparatively small time frame but analyse it fully. In this literature review we discuss used methods, datasets, evaluations and open challenges encountered in all works first released between January 2019 and October 2021. The goal of this survey is to provide a comprehensive and complete overview of current paper recommendation systems.

show abstract

Section: Discussionmentioning

confidence: 99%

“…For venue-based popularity measures, we found an unspecific reputation notion [ 116 ] as well as incorporation of the impact factor [ 26 , 117 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

Section: User Profilementioning

confidence: 99%

See 2 more Smart Citations

Scientific paper recommendation systems: a literature review of recent publications

Kreutz

Schenkel

2022

Int J Digit Libr

View full text Add to dashboard Cite

show abstract

“…e information gain algorithm takes the value brought by the feature to the whole as the evaluation standard and represents the amount of information brought by the feature to the system according to the difference between the amount of information when the system includes feature a and does not include feature a [20]. When calculating the information gain of a single text feature, calculate the difference between the direct line of the classification system when the text feature a is included and the direct line of the classification system when the text feature a is not included, which represents the information gain brought by the text feature a to the classification system and the contribution value of the text feature a. ere are two cases without feature a: the first case is that feature a does not exist in the classification system, and the second case is that feature a exists but a has been fixed in the classification system.…”

Section: Information Gain (Ig)mentioning

confidence: 99%

English Text Analysis System Based on Genetic Algorithm

Yao

2022

Mobile Information Systems

View full text Add to dashboard Cite

In order to accurately extract the useful information in English, this paper studies English text analysis combined with a genetic algorithm and establishes a text analysis system. In this method, a text tendency analysis algorithm based on a genetic algorithm language model is proposed, and a Doc2vec text feature representation algorithm integrating the LDA model is designed; the parallelization technology of text analysis algorithm is studied, and the parallelization model of the algorithm by using spark big data platform is designed; the process of English text tendency analysis is studied, and a Chinese text analysis system is designed and implemented based on big data platform, including corpus intake, corpus annotation, corpus storage, model training, model verification, and other modules. In order to verify the feasibility of this subject, the accuracy of the Doc2vec text feature representation algorithm of the fused LDA model designed in the prototype system is tested. The experimental results show that the fused text representation model has high recognition degree, and the AUC value of the ROC curve reaches 0.95. At the same time, this paper tests the text analysis-related algorithms involved in the system. The test results show that the parallel algorithm can greatly improve the efficiency of the system.

show abstract

Modeling Topic Evolution to Steer Interactive Information Search

Adhav,

Singh

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Hidden features identification for designing an efficient research article recommendation system

Cited by 13 publications

References 52 publications

Scientific paper recommendation systems: a literature review of recent publications

Scientific paper recommendation systems: a literature review of recent publications

English Text Analysis System Based on Genetic Algorithm

Modeling Topic Evolution to Steer Interactive Information Search

Contact Info

Product

Resources

About