One-digit multiplication errors are one of the most extensively analysed mathematical problems. Research work primarily emphasises the use of statistics whereas learning analytics can go one step further and use machine learning techniques to model simple learning misconceptions. Probabilistic programming techniques ease the development of probabilistic graphical models (bayesian networks) and their use for prediction of student behaviour that can ultimately influence decision processes.
This evidence was extracted from a paper coming from the 15th International Conference on Knowledge Technologies and Data-driven Business (i-KNOW 2015), held in Graz (Austria) last 21st – 22nd October 2015.
In this paper, authors describe a framework, named Social Semantic Server (SSS), that can constitute a flexible tool for the support of informal learning in different workplace scenarios.
The development of this tool is based on the assumption that “individual knowledge is constructed through collaborative knowledge building […][and that] a knowledge base is co-constructed by a community of learners as a result of their activities mediated by shared artefacts”. This implies that learners community can be considered as a Distributed Cognitive System, and that the process of meaning construction in this environment can be defined as “Meaning Making”.
SSS was developed considering several Design Principles, and among them several learning KPIs can be found, such as tracking of physical, time, social and semantic context of user-artefact and user-user interactions or tracking of history of network interactions. This network, thanks to Learning Analytics, can represent a good source of understanding what kind of information the users are searching for and new trends in the Meaning Making process.
In the second part of the conference paper, several services of SSS were described, namely metadata degrees of formality, tracking of users interaction, search engine, recommendations tool, knowledge structures, Q&A environment, access restrictions and collections and aggregation of learning inputs inside the framework.
The last part of the paper was dedicated to three case studies, which depict how SSS can represent a flexible tool for the generation of informal learning environments at the workplace. Three different IT tool were generated based on some of the SSS services described above, for the informal learning of healthcare professionals (Bits & Pieces), academic researchers (KnowBrain, currently under development) and future teachers training (Attacher). During these case studies, the context of the collected, generated or modified resources were tracked and analysed through dedicated KPIs, which were author, time of collection and the set of attached tags for Attacher, while for B&P and KnowBrain also categories, ratings and discussions were available. As indicated in the paper, “This contextual characteristics can be exploited to create networks of actors and artefacts, as well as to make Learning Analytics”.
Abstract: Understanding the behavior of learners within learning applications and analyzing the factors that may influence the learning process play a key role in designing and optimizing learning applications. In this work we focus on a specific application named “1x1 trainer” that has been designed for primary school children to learn one digit multiplications. We investigate the database of learners’ answers to the asked questions (N > 440,000) by applying the Markov chains. We want to understand whether the learners’ answers to the already asked questions can affect the way they will answer the subsequent asked questions and if so, to what extent. Through our analysis we first identify the most difficult and easiest multiplications for the target learners by observing the probabilities of the different answer types. Next we try to identify influential structures in the history of learners’ answers considering the Markov chain of different orders. The results are used to identify pupils who have difficulties with multiplications very soon (after couple of steps) and to optimize the way questions are asked for each pupil individually.