Predicting Locations in Tweets

Thi Bich Ngoc Hoang (1, 2) , Véronique Moriceau (3) , Josiane Mothe (1, 4)

1 IRIT-SIG - Systèmes d’Informations Généralisées
2 The university of Danang
3 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
4 UT2J - Université Toulouse - Jean Jaurès

Five hundred millions of tweets are posted daily, making Twitter a major social media from which topical information on events can be extracted. Events are represented by time, location and entity-related information. This paper focuses on location which is an important clue for both users and geo-spatial applications. We address the problem of predicting whether a tweet contains a location or not, as location prediction is a useful pre-processing step for location extraction, by defining a number of features to represent tweets and conducting intensive evaluation of machine learning parameters. We found that: (1) not only words appearing in a geography gazetteer are important but the occurrence of a preposition right before a proper noun also is. (2) it is possible to improve precision on location extraction if the occurrence of a location is predicted.

Mots clés: Social media; Location extraction; Location prediction; Tweets

Domaines: Réseaux sociaux et d'information [cs.SI]; Traitement du texte et du document

Thi Bich Ngoc Hoang, Véronique Moriceau, Josiane Mothe. Predicting Locations in Tweets. CINCLing 2017 : 18th International Conference on Intelligent Text Processing and Computational Linguistics, Apr 2017, Budapest, Hungary. ⟨hal-02624131⟩