Word Similarity Based Model for Tweet Stream Prospective Notification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Word Similarity Based Model for Tweet Stream Prospective Notification

Résumé

The prospective notification on tweet streams is a challenge task in which the user wishes to receive timely, relevant, and non-redundant update notification to remain up-to-date. To be effective the system attempts to optimize the aforementioned properties (timeliness, relevance, novelty and redundancy) and find a trade-off between pushing too many and pushing too few tweets. We propose an adaptation of the extended Boolean model based on word similarity to estimate the relevance score of tweets. We take advantage of the word2vec model to capture the similarity between query terms and tweet terms. Experiments on the TREC MB RTF 2015 dataset show that our approach outperforms all considered baselines.
Fichier principal
Vignette du fichier
chellal_22045.pdf (338.87 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02611135 , version 1 (18-05-2020)

Identifiants

Citer

Abdelhamid Chellal, Mohand Boughanem, Bernard Dousset. Word Similarity Based Model for Tweet Stream Prospective Notification. 39th European Conference on Information Retrieval (ECIR 2017), Apr 2017, Aberdeen, United Kingdom. pp.655--661, ⟨10.1007/978-3-319-56608-5_62⟩. ⟨hal-02611135⟩
30 Consultations
50 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More