I want to arrange documents for automatic e-learning which suggest new topics to students.
Yes, this has been done already. We are finishing a paper on the subject.
1. To operationalise the idea of a educational topic, we honed in on a headword in the glossary.
2. We prepared an exemplary glossary. We checked that the headwords in the glossary were in the text. We ensured that the definitions employed headwords in preference to expanded definitions.
3. We formed an ontology from the exemplary glossary. We used this to further refine the glossary, by e.g., considering the deletion of islanded headwords that were not referenced by or pointing to other headwords.
4. We used the ontology to draw a concept map for the course, which we slowly refined. The map let us identify the foundation headwords and identify the capstone headwords. It also showed us where long and short chains of dependency (threads and bushes) existed. In particular, the map showed us the headword hierarchy: which headwords depended on other headwords being defined beforehand.
5. Our prototype (currently being tested) recommends a reading order for the student, based on presenting first the foundation headwords, then the superior headwords and finally the capstone concepts.
Another suggestion would be to use the generated topics to model the students' knowledge about a topic and use similarity algorithms to suggest similar topics to similar levels of knowledge.
Great question!!!
1) Specify the system boundaries around the content and within the context.
2) Bifurcate domain-agnostic and domain-specific elements.
3) Use middle-range theory to identify salient factors for and to build the model.
4) Use one/both of the following as the basis for the foundations and architecture of the reduced domain, I would suggest using:
1) A declarative programming language AND/OR
2) Semantic mark-up protocols like OWL and RDF
Have a look at the EnPsych Project, which itself failed miserably BUT generated a lot of ideas about how a future project should run.
Really interested to hear how it all goes :)
p.s. although that might sound a bit complex, I think it is actually just a bit more detail to Kawa's point, but hopefully it will provide you with some good leads.
Incidentally, I am currently working on a new Operating System (AESOS) based on the programming language Erlang, but augmented to provide the benefits of declarative programming and optimised for semantic functionality, and dependability.
Topic models are a suite of algorithms that uncover the hidden thematic structure in document collections. These algorithms help us develop new ways to search, browse and summarize large archives of texts. Hence in India like countries wants of language ‘C’ or ‘C ++’. And it can be a talk on dynamic and correlated topic models applied to the any arts or science content.
- Badges
- Science topic
- Similar topics
- Filing