Open Universiteit

Please use this identifier to cite or link to this item:
Title: data sets Simulations in articulating light-weight PRS
Authors: Van den Berg, Bert
Keywords: data set
statistical data
SPSS file
Issue Date: 13-Sep-2008
Series/Report no.: N/A
Abstract: Data sets used for step 1, 2 and 3 in order to research effectiveness and effiency of different Recommondation strategies used in a simulation of a Pesonalised Recommender System
Description: The data sets are output of 3 different steps in the development a simulations of a PRS as described in chapter 3.3: Simulations in articulating light-weight PRS A case for Pedagogy-oriented and Rating-based Hybrid Recommendation Strategies Rob Nadolski, Bert van den Berg, Adriana Berlanga, Hans Hummel, Hendrik Drachsler, Rob Koper & Peter Sloep Open University of the Netherlands, OTEC, Centre for Technology Enhanced Learning As the study consists of three incremental steps - each using a conceptual simula-tion model and a Netlogo (Wilensky, 1999) implementation - three separate method and results sections will be distinguished. A method section describes hy-potheses for the simulation study and its setup of each step. Netlogo is used to perform the simulation runs. The outcomes of such runs validate the version of the conceptual simulation model in that step, and guide further articulation of the conceptual simulation model. Our study started with a focussed expert discussion in which variables, their relationships, and associated literature with existing re-search were identified as input for all steps. In the first step, focus is given towards simplicity. The second step focuses on more reality, whereas the third step focuses on practical implementation issues. Each model will be elaborated in three parts: model variables, measurement variables, and recommendation strategies, followed by the setup of the simulation. Finally, conditions and treatments that are included in the simulation runs of that step will be described. Each conceptual simulation model is largely in line with the model described by Koper (2005). The main goal of the final version of the conceptual simulation model is that it represents the minimized set of LA- and learner characteristics that can support the included RS. Every condition in the simulation was replicated 12 times (i.e., N = 12 runs) to justify the use of classical statistic techniques on resulting data (Law and Kelton, 2000: p. 496), analyzed with SPSS version 15. Each condition included three treatment groups (O, P, OP) and one control group (C). Six conditions were included: goal (2) x sub domain (3). A low-end goal and a high-end goal were taken (see Tables 3.3.3 and 3.3.4). Either, 2, 3 or 4 sub do-mains were taken as they were all regarded to be representative for studies in higher distance education. In all six conditions, each group included 250 learners that could choose from 400 LAs. For all runs, only ‘graduates’ or ‘dropouts’ were allowed after run length. In other words, no participants were ‘still studying’ after run length. To check the robustness of the conceptual simulation model other conditions have been simulated as well.
Appears in Collections:4. LN: Software and Documentation

Files in This Item:
File Description SizeFormat 
step 1 data set.zipdata set of experment 1 1.56 MBzipView/Open
step 2 data set.zipdata set of experiment 21.92 MBzipView/Open
step 3 data set.zipdata set of experiment 31.89 MBzipView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.