Many organisations, not only those in the eLearning industry, maintain large repositories of content. This content can include useful learning material such as training documents, educational courses and manuals. Our industry partners have identified that finding ways to reuse and remonetise such content is an on-going challenge. We have identified the use of Natural Language Processing (NLP) techniques as a possible solution to address this challenge. NLP is the area of computer science that studies how computers understand and analyse human (‘natural’), languages.

Applying Content Analysis
We are currently developing a content analysis tool based on NLP as part of our research on the ALMANAC tablet application. This tool is based on existing research outputs developed by our research partners Digital Enterprise Research Institute (DERI) at the National University of Ireland, Galway [1][2]. The tool will use a combination of NLP and machine learning techniques to automatically extract topics from a repository of text-based documents and linking those topics to the relevant documents. A major advantage of using NLP in this way is that manually tagging or labelling of files is unnecessary.

The content analysis tool is a web service that can be easily utilised as part of the ALMANAC tablet application or indeed other educational applications. It will provide an easy way to search for a topic of interest, explore related topics, and link to the documents about a particular topic. There will also be the option to augment the documents with additional resources such as badocams images and short topic descriptions from DBPedia – a linked-data version of Wikipedia.

NLP in Education is Growing
The use of NLP in educational applications is gaining momentum. Later this year, the 8th Workshop on Innovative Use of NLP for Building Educational Applications will be held in Atlanta, Georgia. Workshop themes include content analysis for automatic scoring and assessment, generation of tutorial responses, NLP tools for second language learning, and analysing a learner’s language and cognitive skill levels. The content analysis tool as used within the ALMANAC web tablet application will provide an ideal test case for the use of NLP in a learning context.


Caoilfhionn_BlogAbout the Author: Caoilfhionn Lane is a postdoctoral researcher at the Digital Enterprise Research Institute (DERI) at NUI Galway. Caoilfhionn works in the area of applied research, which involves adapting DERI research outputs to solve industry challenges. Prior to joining DERI, Caoilfhionn worked as a software engineer for Nortel and Cisco Systems.