Bodong Chen

Crisscross Landscapes

Notes: Teplovs2013-yi



Citekey: @Teplovs2013-yi

Teplovs, C., & Fujita, N. (2013). Socio-Dynamic Latent Semantic Learner Models. In D. D. Suthers, K. Lund, C. P. Rosé, C. Teplovs, & N. Law (Eds.), Productive Multivocality in the Analysis of Group Interactions (pp. 383–396). Springer US.






The units of interaction for our analyses are documents called “notes”. Patterns of interaction amongst participants are mediated by these documents. (p. 2)

Data Representations and Analytic Manipulations (p. 2)

The content of the notes is used to create high-dimensional vector representations via LSA. Relationships between these vectors, as well as relationships amongst participants, are represented using network graphs and highlighted adjacency matrices. (p. 2)

The importance of time-based analyses has also been noted (Haythornthwaite, 2001 ; Martínez, Dimitriadis, Rubia, Gomez, & de la Fuente, 2003 ). The study by de Laat et al. ( 2007 ) was the fi rst application of using SNA to illustrate how patterns change over time and the relationship of those patterns to teaching and learning. (p. 3)

Software (p. 4)

In this section we describe software designed to support the visualisation of learner models based on social and semantic networks. We present a description of the KSV, a prototypic software system on which our new software, KISSME, is based. (p. 4)

Perhaps some of the most interesting diagrams that can be produced using the KSV are based on the superposition of different link types on the same layout. An example of a representation that combines chronology, authorship, structural links and recently opened documents is shown in Fig. 21.2 (p. 5)

One of the key innovations of the KSV was the use of fl exible thresholds in the creation of network representations. This is what allowed us to create visualisations of LSA-based representations of texts. (p. 6)

Visualising Student Models: The Knowledge, Interaction and Semantic Student Model Explorer (p. 7)

For our purposes, all that we are using LSA for is to generate mathematical representations of the participants’ contributions to the discourse space. We can then use those mathematical representations in a variety of ways. (p. 8)

Our approach is somewhat different: we are interested in combining information about patterns of interaction among participants with information about the content of those contributions. We too take a Vygotskian approach: that optimal learning will take place when interactions occur between individuals who are neither too similar nor too dissimilar from each other, based on the semantics of what they have written. This approach of combining SNA and latent semantic network analy- sis is an example of the sort of “multidimensional” network championed by Contractor ( 2009 ). (p. 8)

We are interested in testing the Vygotskian hypothesis that uptake (Suthers, Dwyer, Medina & Vatrapu, 2010 ) is most likely to occur when the semantic relatedness of the corresponding contributor models is neither too high nor too low. We refer to this intermediate similarity of latent seman- tic learner models (LSLM) as “compatibility” in the next section where we apply this framework to a case study. (p. 9)

Case Study (p. 9)

We were interested in examining the relationship between the intensity of social interaction (reading each others’ notes) and the semantic similarity of what each participant had written. (p. 9)

If there were abundant reading events shared between two learners and their LSLM suggested they were compatible then we would predict that there might have been “pivotal moments” or a point in time at which the semantic structure of the com- munity changed in an important way. (p. 12)

This is a retrospective analysis, and therefore we cannot intervene in an attempt to engineer change. However, there is some preliminary evidence that there is a relationship between the intensity of interactions and learners who are semantically similar, but not too similar, to each other based on what they have written in the online discourse space. (p. 12)