TinCan2PROV

Abstract

A popular way to log learning processes is by using the Experience API (abbreviated as xAPI), also referred to as Tin Can. While Tin Can is great for developers who need to log learning experiences in their applications, it is more challenging for data processors to interconnect and analyze the resulting data. An interoperable data model is missing to raise Tin Can to its full potential. We argue that in essence, these learning process logs are provenance. Therefore, the W3C PROV model can provide the much-needed interoperability. In this paper, we introduce a method to expose PROV using Tin Can statements. To achieve this, we made the following contributions: (1) a formal ontology of the xAPI vocabulary, (2) a context document to interpret xAPI statements as JSON-LD, (3) a mapping to convert xAPI JSON-LD statements into PROV, and (4) a tool implementing this mapping. We preliminarily evaluate the approach by converting 20 xAPI statements taken from the public Tin Can Learning Record Store to valid PROV. Where the conversion succeeded, it did so without loss of valid information, therefore suggesting that the conversion process is reversible, as long as the original JSON is valid.

The Handbook of Learning Analytics

“…With xAPI, developers can create a learning experience tracking service through a predefined interface and a set of storage and retrieval rules. De Nies, Salliau, Verborgh, Mannens, andVan de Walle (2015) propose to expose data models created using the xAPI specification as LD. This proposal provides an interoperable model of learning traces data, and allows for seamless exposing of learners' traces as semantically interoperable LD.…”