COCOON CORE: CO-author REcommendations Based on Betweenness Centrality and Interest Similarity

Sie, Rory; Engelen, Bart Jan van; Bitter-Rijpkema, Marlies; Sloep, Peter

doi:10.1007/978-1-4939-0530-0_13

Cited by 9 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interestingly, in user studies, it seems the evaluation focus is nearly as often on the recommender algorithm (49%) as it is on the recommender system (51%). In some publications, for example in [64], [92], [107], [140], [141], [155] and [212], it was explicitly mentioned that the recommender algorithm was evaluated separately in addition to the overall evaluation of the recommender system usually as two distinct phases of the evaluation.…”

Section: Subject Of Evaluationmentioning

confidence: 99%

“…User studies and real life testing cover nearly all effects measured. For example, a user study in [64] is performed to measure the accuracy of the recommender algorithm as well as the usability of the whole recommender system. In contrast, offline experiments are mainly used to measure accuracy and prediction speed, but, surprisingly also learning performance.…”

Section: Effects Measured By Evaluationmentioning

confidence: 99%

“…• Accuracy: Metrics used to measure accuracy were for example, precision, recall and f-measure in [82] and [83]; Mean Average Error (MAE) in [83] and [27]; and Root-mean-square-error (RMSE) in [136] and [151]. In user studies, for example in [64] and [65], the perceived relevance or the learner's acceptance of the recommendations were measured by asking the users to rate the recommendations received. As measuring the accuracy of a recommender algorithm is not easily decoupled from the impact of the usability of the system as a whole, a usability test was performed as well in [64].…”

Section: Effects Measured By Evaluationmentioning

confidence: 99%

“…In user studies, for example in [64] and [65], the perceived relevance or the learner's acceptance of the recommendations were measured by asking the users to rate the recommendations received. As measuring the accuracy of a recommender algorithm is not easily decoupled from the impact of the usability of the system as a whole, a usability test was performed as well in [64]. • Prediction Speed: the prediction speed of the recommender algorithm was measured in [27], [141] and [191].…”

Section: Effects Measured By Evaluationmentioning

confidence: 99%

“…The benefits of the system with respect to learning and enjoyment were also measured in [177], and the ease of use for both students and teachers in [88]. Evaluation tools used were: the Technology Acceptance Model (TAM) [261] in [88]; the System Usability Scale (SUS) [262] in [6] and [64]; the General Interest Structure Test (AIST) [263] in [180]; interviews in [178]; observations in [179] and [200]; recording participants' interactions and collecting think aloud protocols in [5]. • Task Support: Learners were supported in achieving their current learning goals in [170] and [177], as well as to accomplish their learning or authoring tasks in [5].…”

Section: Effects Measured By Evaluationmentioning

confidence: 99%

See 4 more Smart Citations

Evaluating Recommender Systems for Technology Enhanced Learning: A Quantitative Survey

Erdt

Fernández

Rensing

2015

IEEE Trans. Learning Technol.

119

View full text Add to dashboard Cite

The increasing number of publications on recommender systems for Technology Enhanced Learning (TEL) evidence a growing interest in their development and deployment. In order to support learning, recommender systems for TEL need to consider specific requirements, which differ from the requirements for recommender systems in other domains like e-commerce. Consequently, these particular requirements motivate the incorporation of specific goals and methods in the evaluation process for TEL recommender systems. In this article, the diverse evaluation methods that have been applied to evaluate TEL recommender systems are investigated. A total of 235 articles are selected from major conferences, workshops, journals and books where relevant work have been published between 2000 and 2014. These articles are quantitatively analysed and classified according to the following criteria: type of evaluation methodology, subject of evaluation, and effects measured by the evaluation. Results from the survey suggest that there is a growing awareness in the research community of the necessity for more elaborate evaluations. At the same time, there is still substantial potential for further improvements. This survey highlights trends and discusses strengths and shortcomings of the evaluation of TEL recommender systems thus far, thereby aiming to stimulate researchers to contemplate novel evaluation approaches.

show abstract

Section: Subject Of Evaluationmentioning

confidence: 99%

Section: Effects Measured By Evaluationmentioning

confidence: 99%

Section: Effects Measured By Evaluationmentioning

confidence: 99%

Section: Effects Measured By Evaluationmentioning

confidence: 99%

Section: Effects Measured By Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

Evaluating Recommender Systems for Technology Enhanced Learning: A Quantitative Survey

Erdt

Fernández

Rensing

2015

IEEE Trans. Learning Technol.

119

View full text Add to dashboard Cite

show abstract

Cross-Domain Co-Author Recommendation Based on Knowledge Graph Clustering

Munna

Delhibabu

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

User evaluation of a task for shortlisting papers from researcher’s reading list for citing in manuscripts

Raamkumar

Foo

Pang

2017

AJIM

View full text Add to dashboard Cite

Purpose Although many interventional approaches have been proposed to address the apparent gap between novices and experts for literature review (LR) search tasks, there have been very few approaches proposed for manuscript preparation (MP) related tasks. The purpose of this paper is to describe a task and an incumbent technique for shortlisting important and unique papers from the reading list (RL) of researchers, meant for citation in a manuscript. Design/methodology/approach A user evaluation study was conducted on the prototype system which was built for supporting the shortlisting papers (SP) task along with two other LR search tasks. A total of 119 researchers who had experience in authoring research papers participated in this study. An online questionnaire was provided to the participants for evaluating the task. Both quantitative and qualitative analyses were performed on the collected evaluation data. Findings Graduate research students prefer this task more than research and academic staff. The evaluation measures relevance, usefulness and certainty were identified as predictors for the output quality measure “good list”. The shortlisting feature and information cues were the preferred aspects while limited data set and rote steps in the study were ascertained as critical aspects from the qualitative feedback of the participants. Originality/value Findings point out that researchers are clearly interested in this novel task of SP from the final RL prepared during LR. This has implications for digital library, academic databases and reference management software where this task can be included to benefit researchers at the manuscript preparatory stage of the research lifecycle.

show abstract

COCOON CORE: CO-author REcommendations Based on Betweenness Centrality and Interest Similarity

Cited by 9 publications

References 16 publications

Evaluating Recommender Systems for Technology Enhanced Learning: A Quantitative Survey

Evaluating Recommender Systems for Technology Enhanced Learning: A Quantitative Survey

Cross-Domain Co-Author Recommendation Based on Knowledge Graph Clustering

User evaluation of a task for shortlisting papers from researcher’s reading list for citing in manuscripts

Contact Info

Product

Resources

About