Which Algorithms Suit Which Learning Environments? A Comparative Study of Recommender Systems in TEL

Kopeinik, Simone; Kowald, Dominik; Lex, Elisabeth

doi:10.1007/978-3-319-45153-4_10

Cited by 18 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This automatically generated information on collaboration processes can in turn be used in learning analytics systems, for example, to facilitate an exchange of ideas. Machine learning is also used in the context of recommender systems that aim at providing learners with the most useful learning materials according to their previous learning trajectory (e.g., Drachsler et al 2015;Kopeinik et al 2016;Moskaliuk et al 2011).…”

Section: Automatic Text Classificationmentioning

confidence: 99%

Using big data techniques for measuring productive friction in mass collaboration online environments

Holtz

Kimmerle

Creß

2018

Intern. J. Comput.-Support. Collab. Learn

View full text Add to dashboard Cite

The advent of the social web brought with it challenges and opportunities for research on learning and knowledge construction. Using the online-encyclopedia Wikipedia as an example, we discuss several methods that can be applied to analyze the dynamic nature of knowledge-related processes in mass collaboration environments. These methods can help in the analysis of the interactions between the two levels that are relevant in computer-supported collaborative learning (CSCL) research: The individual level of learners and the collective level of the group or community. In line with constructivist theories of learning, we argue that the development of knowledge on both levels is triggered by productive friction, that is, the prolific resolution of socio-cognitive conflicts. By describing three prototypical methods that have been used in previous Wikipedia research, we review how these techniques can be used to examine the dynamics on both levels and analyze how these dynamics can be predicted by the amount of productive friction. We illustrate how these studies make use of text classifiers, social network analysis, and cluster analysis in order to operationalize the theoretical concepts. We conclude by discussing implications for the analysis of dynamic knowledge processes from a learning sciences perspective.

show abstract

Section: Automatic Text Classificationmentioning

confidence: 99%

Using big data techniques for measuring productive friction in mass collaboration online environments

Holtz

Kimmerle

Creß

2018

Intern. J. Comput.-Support. Collab. Learn

View full text Add to dashboard Cite

show abstract

“…Research papers Model of human categorization [17,23,35] Activation processes in human memory [18,21,24,37] Informal learning se ings [5][6][7] Resource recommendations Research papers A ention-interpretation dynamics [15,34] Tag and time information [27,28] Recommendation evaluation Research papers Real-world folksonomies [20] Technology enhanced learning se ings [16] Hashtag recommendations…”

Section: Tag Recommendationsmentioning

confidence: 99%

“…Comparing Recommendation Algorithms in Technology Enhanced Learning Settings. Kopeinik et al [16] is another example of using TagRec for the evaluation of a variety of algorithms on di erent o ine datasets. e paper focused on technologyenhanced formal and informal learning environments, where due to fast changing domains and characteristic group learning settings, data is typically sparse.…”

Section: Recommendation Evaluationmentioning

confidence: 99%

The TagRec Framework as a Toolkit for the Development of Tag-Based Recommender Systems

Kowald

Kopeinik

Lex

2017

Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization

Self Cite

View full text Add to dashboard Cite

Recommender systems have become important tools to support users in identifying relevant content in an overloaded information space. To ease the development of recommender systems, a number of recommender frameworks have been proposed that serve a wide range of application domains. Our TagRec framework is one of the few examples of an open-source framework tailored towards developing and evaluating tag-based recommender systems. In this paper, we present the current, updated state of TagRec, and we summarize and re ect on four use cases that have been implemented with TagRec: (i) tag recommendations, (ii) resource recommendations, (iii) recommendation evaluation, and (iv) hashtag recommendations. To date, TagRec served the development and/or evaluation process of tag-based recommender systems in two large scale European research projects, which have been described in 17 research papers.us, we believe that this work is of interest for both researchers and practitioners of tag-based recommender systems.

show abstract

“…Approach and Methods. A very simple, though relatively effective, tag recommendation strategy is the Most Popular (MP) algorithm [19,22]. We however assume that a frequency-based, computationally simple recommendation strategy may be even more successful, if it is grounded on a thorough understanding of how humans process information.…”

mentioning

confidence: 99%

“…However, offline data studies are limited to evaluating the prediction of user behaviour. In our previous work [24,22], we have intensively investigated the suitability of two tag recommendation approaches via offline studies [22]: the first of these, known as BLL implements the Base Level Learning Equation [1], which models the frequency and recency of past tag use. The second algorithm, known as Minerva [18,36], incorporates tag use frequency as well as semantic context.…”

mentioning

confidence: 99%

Supporting collaborative learning with tag recommendations

Kopeinik

Lex

Seitlinger

et al. 2017

Proceedings of the Seventh International Learning Analytics &Amp; Knowledge Conference

Self Cite

View full text Add to dashboard Cite

show abstract

Which Algorithms Suit Which Learning Environments? A Comparative Study of Recommender Systems in TEL

Cited by 18 publications

References 27 publications

Using big data techniques for measuring productive friction in mass collaboration online environments

Using big data techniques for measuring productive friction in mass collaboration online environments

The TagRec Framework as a Toolkit for the Development of Tag-Based Recommender Systems

Supporting collaborative learning with tag recommendations

Contact Info

Product

Resources

About