Communication publiée dans un ouvrage (Colloques, congrès, conférences scientifiques et actes)
PERSEUS: A Personalization Framework for Sentiment Categorization with Recurrent Neural Network
GUO, Siwen; Höhn, Sviatlana; Xu, Feiyu et al.
2018In International Conference on Agents and Artificial Intelligence , Funchal 16-18 January 2018
Peer reviewed
 

Documents


Texte intégral
65841.pdf
Postprint Éditeur (365.69 kB)
Best Student Paper Award
Télécharger

Tous les documents dans ORBilu sont protégés par une licence d'utilisation.

Envoyer vers



Détails



Mots-clés :
Sentiment Analysis; Opinion Mining; Personalized Memories; Neural Networks
Résumé :
[en] This paper introduces the personalization framework PERSEUS in order to investigate the impact of individuality in sentiment categorization by looking into the past. The existence of diversity between individuals and certain consistency in each individual is the cornerstone of the framework. We focus on relations between documents for user-sensitive predictions. Individual’s lexical choices act as indicators for individuality, thus we use a concept-based system which utilizes neural networks to embed concepts and associated topics in text. Furthermore, a recurrent neural network is used to memorize the history of user’s opinions, to discover user-topic dependence, and to detect implicit relations between users. PERSEUS also offers a solution for data sparsity. At the first stage, we show the benefit of inquiring a user-specified system. Improvements in performance experimented on a combined Twitter dataset are shown over generalized models. PERSEUS can be used in addition to such generalized systems to enhance the understanding of user’s opinions.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
GUO, Siwen ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)
Höhn, Sviatlana;  AI Minds > Vianden, Luxembourg
Xu, Feiyu;  Lenovo > Beijing, China
SCHOMMER, Christoph  ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
PERSEUS: A Personalization Framework for Sentiment Categorization with Recurrent Neural Network
Date de publication/diffusion :
janvier 2018
Nom de la manifestation :
10th International Conference on Agents and Artificial Intelligence
Lieu de la manifestation :
Funchal, Portugal
Date de la manifestation :
from 16-01-2018 to 18-01-2018
Manifestation à portée :
International
Titre de l'ouvrage principal :
International Conference on Agents and Artificial Intelligence , Funchal 16-18 January 2018
Pagination :
9
Peer reviewed :
Peer reviewed
Disponible sur ORBilu :
depuis le 24 janvier 2018

Statistiques


Nombre de vues
383 (dont 98 Unilu)
Nombre de téléchargements
226 (dont 40 Unilu)

citations Scopus®
 
4
citations Scopus®
sans auto-citations
3

Bibliographie


Publications similaires



Contacter ORBilu