Can we Predict Locations in Tweets? A Machine Learning Approach - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal of Computational Linguistics and Applications Année : 2018

Can we Predict Locations in Tweets? A Machine Learning Approach

Résumé

Five hundred millions of tweets are posted daily, makingTwitter a major social media from which topical informationon 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. Location prediction is a useful preprocessing step for location extraction. We defined a number of features to represent tweets and conducted intensive evaluation ofmachine 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.
Fichier principal
Vignette du fichier
hoang_26155.pdf (172.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02901421 , version 1 (17-07-2020)

Identifiants

  • HAL Id : hal-02901421 , version 1
  • OATAO : 26155

Citer

Thi Bich Ngoc Hoang, Véronique Moriceau, Josiane Mothe. Can we Predict Locations in Tweets? A Machine Learning Approach. International Journal of Computational Linguistics and Applications, 2018, 9, pp.0. ⟨hal-02901421⟩
72 Consultations
95 Téléchargements

Partager

Gmail Facebook X LinkedIn More