Information Extraction from Twitter Using DBpedia Ontology: Indonesia Tourism Places

As the popular microblogs of social media, Twitter provides a number of short messages of interesting information, like the mention of entities to promote local cultures and tourism places in order for others to know and visit the places. However, the entities mentioned within the tweet may be inter...

Full description

Saved in:
Bibliographic Details
Published in2019 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) pp. 91 - 96
Main Authors Rosyiq, Ahmad, Hayah, Aina Rahmah, Hidayanto, Achmad Nizar, Naisuty, Meisuchi, Suhanto, Agus, Avuning Budi, Nur Fitriah
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2019
Subjects
DBpedia
Information Extraction
Named Entity Recognition
Ontology
Twitter
Wikipedia
Online AccessGet full text

Cover

More Information
Summary:As the popular microblogs of social media, Twitter provides a number of short messages of interesting information, like the mention of entities to promote local cultures and tourism places in order for others to know and visit the places. However, the entities mentioned within the tweet may be interpreted differently and vary depending on the context of the tweet. To find the appropriate context of the entities, we need the system that can perform semantic annotation for every entity, especially for the tourism places. In this paper, we provide Named Entity Recognition used to define the candidate entities of the places. Furthermore, by using DBpedia Ontology as a semantic annotation resources we construct the information extraction from the context and semantic of the entities to collect the URI of Wikipedia page of the place. The experiment result showed the system was capable to extract the mentioned place and annotated the URI of Wikipedia with high accuracy which defined by 0.95 of Precision, 0.79 of Recall, and 0.87 of F-Measure.
DOI:10.1109/ICIMCIS48181.2019.8985194