Automatic Tagging of Learning Objects Based on Their Usage in Web Portals
Data sets coming from the educational domain often suffer from sparsity. Hence, many learning objects are not accessible by the users as they are not able to find these objects using for example a text-based search. Furthermore, the lack of information ma
- PDF / 1,024,529 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 44 Downloads / 164 Views
Abstract. Data sets coming from the educational domain often suffer from sparsity. Hence, many learning objects are not accessible by the users as they are not able to find these objects using for example a textbased search. Furthermore, the lack of information makes it difficult or even impossible to recommend such hidden learning resources. In order to address the data sparsity problem, this paper presents a new way to enhance the objects’ semantic representations. This is done by automatically assigning tags and classifications to learning objects offered by educational web portals. This way, we aim to increase the accessibility of the learning objects as well as to enable their recommendation. In contrast to popular tagging approaches that usually base the tagging of a learning object on its content or on the tags already assigned to it, the approach proposed in this paper is solely based on the objects’ usage. Therefore, tags and classifications can be exchanged between the objects and also previously un-tagged objects that do not hold any textual content can be automatically assigned with tags and classifications. Keywords: Automatic tagging · Data mining · Educational web portals · Findability · Information retrieval · Technology enhanced learning
1
Introduction
Many educational web portals allow users and domain experts to manually enrich the learning resources with social metadata like free-text tags or classifications from a controlled vocabulary. Additionally to ratings and detailed comments which are rarely used in educational web portals [1], these tags and classifications provide powerful knowledge that can be used to improve the quality of searching and recommendations [2,3]. Especially when dealing with multimedia objects that provide little or no textual context (e.g. photos or videos), tags and classifications provide meaningful descriptors of the objects [4]. Nevertheless, data sets coming from the domain of technology enhanced learning (TEL) often suffer from sparsity in respect to semantic and social metadata describing the learning objects [1]. This hinders the accessibility of the learning resources since users cannot easily find them. Additionally, the sparsity impedes the recommendation of suitable learning resources. c Springer International Publishing Switzerland 2015 G. Conole et al. (Eds.): EC-TEL 2015, LNCS 9307, pp. 240–253, 2015. DOI: 10.1007/978-3-319-24258-3 18
Automatic Tagging of Learning Objects Based on Their Usage
241
We envision two scenarios to address the data sparsity problem, i.e. tag recommendation and automatic tagging. Tag recommendation supports the users by recommending tags they might want to add to a learning object. This simplifies the tagging process for the users and, thus, motivates them to add more tags [5,6]. Furthermore, users tend to add different tags to objects to describe the same concept which makes it difficult to retrieve and compare the objects. For example, a user searching for memorial will not find learning objects tagged with monument. In fact, in the dat
Data Loading...
