Page: 1 2 3 4 5 6 7 8 9 10... 48
101 |
Location extraction from tweets
|
|
|
|
In: ISSN: 0306-4573 ; Information Processing and Management ; https://hal.archives-ouvertes.fr/hal-02640811 ; Information Processing and Management, Elsevier, 2018, 54 (2), pp.129-144. ⟨10.1016/j.ipm.2017.11.001⟩ (2018)
|
|
BASE
|
|
Show details
|
|
103 |
Attribution and Artificial Intelligence: Embedding Provenance with Material Metadata
|
|
|
|
In: Architecture Publications (2018)
|
|
BASE
|
|
Show details
|
|
104 |
Special issue on Sensing, Data Analysis and Platforms for Ubiquitous Intelligence
|
|
|
|
BASE
|
|
Show details
|
|
105 |
The Relation of Personality and Intelligence—What Can the Brunswik Symmetry Principle Tell Us?
|
|
|
|
In: Journal of Intelligence ; Volume 6 ; Issue 3 (2018)
|
|
BASE
|
|
Show details
|
|
106 |
The Great Debate: General Ability and Specific Abilities in the Prediction of Important Outcomes
|
|
|
|
In: Journal of Intelligence ; Volume 6 ; Issue 3 (2018)
|
|
BASE
|
|
Show details
|
|
107 |
The Relation of Personality and Intelligence—What Can the Brunswik Symmetry Principle Tell Us?
|
|
|
|
BASE
|
|
Show details
|
|
108 |
Semantic reranking of CRF label sequences for verbal multiword expression identification ; Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop
|
|
|
|
BASE
|
|
Show details
|
|
109 |
Precision immunoprofiling by image analysis and artificial intelligence
|
|
|
|
BASE
|
|
Show details
|
|
110 |
Enhancing Your Intelligence Agency Information Resource IQ: PT. 1: The Office of the Director of National Intelligence
|
|
|
|
In: Libraries Faculty and Staff Presentations (2018)
|
|
BASE
|
|
Show details
|
|
111 |
Troping the Enemy: Metaphor, Culture, and the Big Data Black Boxes of National Security
|
|
|
|
In: Secrecy and Society (2018)
|
|
BASE
|
|
Show details
|
|
112 |
The relation of personality and intelligence - what can the Brunswik symmetry principle tell us?
|
|
|
|
BASE
|
|
Show details
|
|
113 |
A Semi-supervised Corpus Annotation for Saudi Sentiment Analysis Using Twitter
|
|
|
|
BASE
|
|
Show details
|
|
114 |
Pensamiento crítico de los jóvenes ciudadanos frente a las noticias en Chile
|
|
|
|
In: Comunicar: Revista científica iberoamericana de comunicación y educación, ISSN 1134-3478, Nº 54, 2018, pags. 101-110 (2018)
|
|
BASE
|
|
Show details
|
|
117 |
ImproteK: introducing scenarios into human-computer music improvisation
|
|
|
|
In: ACM Computers in Entertainment ; https://hal.archives-ouvertes.fr/hal-01380163 ; ACM Computers in Entertainment, 2017, ⟨10.1145/3022635⟩ (2017)
|
|
BASE
|
|
Show details
|
|
118 |
Facial Expression Emotion Detection for Real-time Embedded Systems
|
|
|
|
BASE
|
|
Show details
|
|
119 |
FrenchSentiClass : an Automated System for French Sentiment Classification ; FrenchSentiClass : un Système Automatisé pour la Classification de Sentiments en Français
|
|
|
|
In: Actes de l’atelier DEFT de la conférence TALN 2017 ; DEFT: Défi Fouille de Texte ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-01563411 ; DEFT: Défi Fouille de Texte, Jun 2017, Orléans, France (2017)
|
|
Abstract:
National audience ; This paper describes the system we used on the tasks of the text mining challenge (DEFT 2017). This thirteenth edition of this challenge concerned the analysis of opinions and figurative language in French tweets. Three tasks have been proposed : (i) the first one concerns the classification of non-figurative tweets according to their polarity ; (ii) the second one concerns the identification of figurative language, while (iii) the third one concerns the classification of figurative and non-figurative tweets according to their polarity. We proposed an automated system based on Support Vector Machines (SVM). The system automatically chooses on each step the best preprocessing, syntactic features and sentiment lexicons by cross validation on the training set. Furthermore, it performs an evaluation of feature subset selection and a tuning SVM complexity parameter. Therefore, this system can significantly reduce the time necessary to explore the data and choose the best feature representation. ; Ce papier décrit le système FrenchSentiClass que nous avons utilisé pour les tâches du défi de fouilles de texte (DEFT 2017). Cette treizième édition du défi a porté sur l'analyse de l'opinion et du langage figuratif dans des tweets rédigés en Français. Le défi propose trois tâches : (i) la première concerne la classification des tweets non figuratifs selon leur polarité ; (ii) la deuxième concerne l'identification du langage figuratif et (iii) la troisième concerne la classification des tweets figuratifs et non figuratifs selon leur polarité. Nous avons proposé un système automatisé basé sur les Machines à Vecteurs de Support (SVM). Le système choisit automatiquement à chaque niveau les meilleurs prétraitements, descripteurs syntaxiques et lexiques de sentiments en validation croisée sur l'ensemble d'apprentissage. Il effectue aussi une évaluation de l'apport de la sélection d'attributs et un tuning du paramètre de complexité du modèle SVM. Par conséquent, ce système permet de réduire considérablement le temps d'exploration des données et du choix de la meilleur représentation de descripteurs. ABSTRACT FrenchSentiClass : an Automated System for French Sentiment Classification This paper describes the system we used on the tasks of the text mining challenge (DEFT 2017). This thirteenth edition of this challenge concerned the analysis of opinions and figurative language in French tweets. Three tasks have been proposed : (i) the first one concerns the classification of non-figurative tweets according to their polarity ; (ii) the second one concerns the identification of figurative language, while (iii) the third one concerns the classification of figurative and non-figurative tweets according to their polarity. We proposed an automated system based on Support Vector Machines (SVM). The system automatically chooses on each step the best preprocessing, syntactic features and sentiment lexicons by cross validation on the training set. Furthermore, it performs an evaluation of feature subset selection and a tuning SVM complexity parameter. Therefore, this system can significantly reduce the time necessary to explore the data and choose the best feature representation. MOTS-CLÉS : Analyse d'opinions, détection de polarité, langage figuratif.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; Analyse d’opinions; Détection de polarité; Figurative language; Langage figuratif; Opinion analysis; Polarity detection
|
|
URL: https://hal-lirmm.ccsd.cnrs.fr/lirmm-01563411 https://hal-lirmm.ccsd.cnrs.fr/lirmm-01563411/file/deft2017-frenchsenticlassEquipe4.pdf https://hal-lirmm.ccsd.cnrs.fr/lirmm-01563411/document
|
|
BASE
|
|
Hide details
|
|
120 |
La cartographie des traces textuelles comme méthodologie d’enquête en sciences sociales
|
|
|
|
In: https://hal-sciencespo.archives-ouvertes.fr/tel-03626011 ; Sociologie. École normale supérieure, 2017 (2017)
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9 10... 48
|
|