Towards the Representation of Hashtags in Linguistic Linked Open Data Format

Thierry Declerck, Piroska Lendvai

In: Piek Vossen, German Rigau, Petya Osenova, Kiril Simov (editor). Proceedings of the Second Workshop on Natural Language Processing and Linked Open Data. Workshop on Natural Language Processing and Linked Open Data (NLP&LOD-15) located at RANLP 2015 September 11 Hissar Bulgaria INCOMA Ltd Shoumen, BULGARIA 9/2015.


A pilot study is reported on developing the basic Linguistic Linked Open Data (LLOD) infrastructure for hashtags from social media posts. Our goal is the encoding of linguistically and semantically enriched hashtags in a formally compact way using the machine-readable OntoLex model. Initial hashtag processing consists of data-driven decomposition of multi-element hashtags, the linking of spelling variants, and part-of-speech analysis of the elements. Then we explain how the OntoLex model is used both to encode and to enrich the hashtags and their elements by linking them to existing semantic and lexical LOD resources: DBpe-dia and Wiktionary.


hashtag_lod@ranlp2015_final.pdf (pdf, 667 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz