Mihai Dascalu

Cohesion network analysis of CSCL participation

The broad use of computer-supported collaborative-learning (CSCL) environments (e.g., instant messenger–chats, forums, blogs in online communities, and massive open online courses) calls for automated tools to support tutors in the time-consuming process of analyzing collaborative conversations. In this article, the authors propose and validate the cohesion network analysis (CNA) model, housed within the ReaderBench platform. CNA, grounded in theories of cohesion, dialogism, and polyphony, is similar to social network analysis (SNA), but it also considers text content and discourse structure and, uniquely, uses automated cohesion indices to generate the underlying discourse representation. Thus, CNA enhances the power of SNA by explicitly considering semantic cohesion while modeling interactions between participants. The primary purpose of this article is to describe CNA analysis and to provide a proof of concept, by using ten chat conversations in which multiple participants debated the advantages of CSCL technologies. Each participant’s contributions were human-scored on the basis of their relevance in terms of covering the central concepts of the conversation. SNA metrics, applied to the CNA sociogram, were then used to assess the quality of each member’s degree of participation. The results revealed that the CNA indices were strongly correlated to the human evaluations of the conversations. Furthermore, a stepwise regression analysis indicated that the CNA indices collectively predicted 54% of the variance in the human ratings of participation. The results provide promising support for the use of automated computational assessments of collaborative participation and of individuals’ degrees of active involvement in CSCL environments.

Teaching iSTART to understand Spanish

iSTART is a web-based reading comprehension tutor. A recent translation of iSTART from English to Spanish has made the system available to a new audience. In this paper, we outline several challenges that arose during the development process, specifically focusing on the algorithms that drive the feedback. Several iSTART activities encourage students to use comprehension strategies to generate self-explanations in response to challenging texts. Unsurprisingly, analyzing responses in a new language required many changes, such as implementing Spanish natural language processing tools and rebuilding lists of regular expressions used to flag responses. We also describe our use of an algorithm inspired from genetics to optimize the Fischer Discriminant Function Analysis coefficients used to determine self-explanation scores.

Finding the Needle in a Haystack: Who are the Most Central Authors Within a Domain?

The speed at which new scientific papers are published has increased dramatically, while the process of tracking the most recent publications having a high impact has become more and more cumbersome. In order to support learners and researchers in retrieving relevant articles and identifying the most central researchers within a domain, we propose a novel 2-mode multilayered graph derived from Cohesion Network Analysis (CNA). The resulting extended CNA graph integrates both authors and papers, as well as three principal link types: co-authorship, co-citation, and semantic similarity among the contents of the papers. Our rankings do not rely on the number of published documents, but on their global impact based on links between authors, citations, and semantic relatedness to similar articles. As a preliminary validation, we have built a network based on the 2013 LAK dataset in order to reveal the most central authors within the emerging Learning Analytics domain.

Paper vs. slides

As different learning methods and educational scenarios highly influence the corresponding outcomes, our aim is to highlight quantifiable discrepancies in terms of the complexity gap between presentations and handouts versus full documents (i.e. academic papers), expressed as concrete factors that directly influence the perceived difficulty. Although there are multiple dependant variables that affect the interpretation of a given topic (e.g., order of presented materials, difference in personal styles if materials originate from multiple authors), we limit the scope of our analysis to solely identifying textual traits that can be automatically extracted from conference papers and their corresponding slide presentations. Our approach represents the starting point for adapting MOOC (Massive Open Online Courses) materials to their target audience in terms of: textual complexity, learner comprehension and content reusability. Therefore, this study performs a detailed comparison using a wide variety of textual complexity metrics as background, ranging from surface, syntactic, morphological and semantic factors in order to grasp the specificities of each material. In other words, our goal consists of providing a set of required metrics for adapting learning materials in order to best suit the underlying educational activities. Preliminary results reflect a strong correlation between the two alternative presentation forms of the same material (papers and corresponding slides) and a similar degree of perceived textual complexity, emphasizing the strong and unitary writing characteristics of the author.