Exploring scholarly publications using DBPedia concepts: an experiment


This post is about a recent prototype I developed, which allows to explore a sample collection of Springer Nature publications using subject tags automatically extracted from DBPedia.

DBpedia is a crowd-sourced community effort to extract structured content from the information created in various Wikimedia projects. This structured information resembles an open knowledge graph (OKG) which is available for everyone on the Web.

Datasets

The dataset I used is the result of a collaboration with Beyza Yaman, a researcher working with the DBpedia team in Leipzig, who used the SciGraph datasets as input to the DBPedia-Spotlight entity-mining tool.

By using DBPedia-Spotlight we automatically associated DBpedia subjects terms to a  subset of abstracts available in the SciGraph dataset (around 90k abstract from 2017 publications).

The prototype allows to search the Springer Nature publications using these subject terms.

Also, DBpedia subjects include definitions and semantic relationships (which we are currently not using, but one can imagine how they could be raw material for generating more thematic 'pathways').

Results: serendipitous discovery of scientific publications

The results are pretty encouraging: despite the fact that the concepts extracted sometimes are only marginally relevant (or not relevant at all), the breadth and depth of the DBpedia classification makes the interactive exploration quite interesting and serendipitous.

You can judge for yourself: the tool is available herehttps://dbpedialinks.michelepasin.org/

The purpose of this prototype is to evaluate the quality of the tagging and generate ideas for future applications. So any kind of feedback or ideas is very welcome!

We are working with Beyza to write up the results of this investigation as a research paper. The data and software is already freely available on github.

A couple of screenshots:

Eg see the topic 'artificial intelligence'

Screen Shot 2018-11-23 at 17.15.07.png

One can add more subjects to a search in order to 'zoom in' into a results set, eg by adding 'China' to the search:

Screen Shot 2018-11-23 at 17.16.38

Implementation details

Cite this blog post:


Michele Pasin. Exploring scholarly publications using DBPedia concepts: an experiment. Blog post on www.michelepasin.org. Published on Nov. 23, 2018.

Comments via Github:


See also:

2022


paper  Generating large-scale network analyses of scientific landscapes in seconds using Dimensions on Google BigQuery

International Conference on Science, Technology and Innovation Indicators (STI 2022), Granada, Sep 2022.




2019


paper  Modeling publications in SN SciGraph 2012-2019

Workshop on Scholarly Digital Editions, Graph Data-Models and Semantic Web Technologies, Université de Lausanne, Jun 2019.



paper  Interlinking SciGraph and DBpedia datasets using Link Discovery and Named Entity Recognition Techniques

Second biennial conference on Language, Data and Knowledge (LDK 2019), Leipzig, Germany, May 2019.


2017


paper  Using Linked Open Data to Bootstrap a Knowledge Base of Classical Texts

WHiSe 2017 - 2nd Workshop on Humanities in the Semantic web (colocated with ISWC17), Vienna, Austria, Oct 2017.




2010


paper  How do philosophers think their own discipline? Reports from a knowledge elicitation experiment

European Philosophy and Computing conference, ECAP10, Munich, Germany, Oct 2010.


2007


blog  DBpedia rocks