Document Enrichment using DBPedia Ontology for Short Text Classification
Jernej Flisar, Vili Podgorelec · 2018
Every day, millions of short-texts are generated for which effective tools for organization and retrieval are required. Because of the short length of these documents and of their extremely sparse representations, the traditional text classification methods are not effective. We propose a new approach that uses DBpedia Spotlight annotation tools, to identify relevant entities in text and enrich short text documents with concepts derived from those entities, represented in DBpedia ontology. Our experiments show that the proposed document enrichment approach is beneficial for classification of short texts, and is robust with respect to concept drifts and input sources. We report experimental results in three challenging collections, using a variety of classification methods. The results show that the use of DBpedia ontology significantly improves the classification performance of classifiers in short-text classification.