This talk presents our recent work in developing new ways to classify web content and to enable collaborative taxonomy development. I will show how to use modern web development techniques - using VueJS, Laravel and Google Chrome extensions - to enable real world applications based on the PoolParty Semantic Suite.
Being one of several publishers of the German Yellow Pages, we have the need to categorise new, very large datasets. We discuss our process from a rule-based system using a knowledge graph towards a machine-learning approach as well as benefits of a mixed approach.
With the help of real-world data we explain how each of these approaches work.
SciGraph is a Linked Open Data graph published by SpringerNature which contains information about conferences and conferencepublications. In this paper, we discuss how this dataset can be utilized tobuild a conference recommendation system, yielding a recall@10 of up to0.662, and a MAP of up to 0.540, generating recommendations based onauthors, abstracts, and keywords. Furthermore, we show how the datasetcan be linked to WikiCFP to recommend upcoming conferences.
In the Big Data era, the amount of digital data is increasing exponentially. Knowledge graphs are gaining attention to handle the variety dimension of Big Data, allowing machines to understand the semantics present in data. For example, knowledge graphs such as STITCH, SIDER, and Drug-Bank have been developed in the Biomedical domain. As the number of data increases, it is critical to perform analysis of data. Interaction network analysis is especially important in knowledge graphs, e.g., to detect drug-target interaction.