, La colère (anger)

L. Mépris,

, La satisfaction (contentment)

L. Dégoût,

, La gêne (embarrassment)

, L'excitation (excitement)

, La peur (fear)

L. Culpabilité,

L. ,

L. Soulagement,

, La satisfaction (satisfaction)

. Le,

, La honte (shame)

A. Sho and U. Osamu, A method for automatically generating the emotional vectors of emoticons using weblog articles, Proceedings of the 10th WSEAS international conference on Applied computer and applied computational science, p.47, 2011.

J. Langshaw and A. , How to do things with words, p.36, 1975.

B. Jason, « The opennlp project, p.68, 2005.

B. Francesco, B. Miguel, R. Francesco, and S. Horacio, « Multimodal emoji prediction, p.52, 2018.

B. Francesco, B. Miguel, and S. Horacio, « Are emojis predictable ?, vol.83, p.51, 2017.

B. Francesco, J. Camacho-collados, R. Francesco, L. Espinosa, A. Miguel et al., Proceedings of The 12th International Workshop on Semantic Evaluation, vol.2, p.51, 2018.

B. Francesco, M. Luis, K. Pradeep, B. William, and S. Horacio, « Exploring emoji usage and prediction through a temporal variation lens, p.52, 2018.

B. Francesco, R. Francesco, and S. Horacio, What does this Emoji Mean ? A Vector Space Skip-Gram Model for Twitter Emojis. » In : LREC. 2016 (cf, p.45

B. Nikhil, K. Satheeshkumar, W. Pidong, K. Shivasankari, and N. Arun, Systems and methods for suggesting emoji. US Patent App. 15/384,950, p.66, 2017.

S. John and . Bridle, Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition, Neurocomputing. Springer, p.51, 1990.

C. Rui, Z. Chao, W. Chong, Z. Lei, and M. A. Wei-ying, Musicsense : contextual music recommendation using emotional allocation modeling, Proceedings of the 15th ACM international conference on Multimedia, p.57, 2007.

C. Spencer, T. Mensink, G. M. Cees, . Snoek, and . Image2emoji, Zero-shot Emoji Prediction for Visual Media, pp.1311-1314, 2015.

C. Spencer, S. Stacey, G. Pierre, M. Thomas, G. M. Et-cees et al., New Modality : Emoji Challenges in Prediction, Anticipation, and Retrieval, vol.21, p.52, 2019.

C. François, Deep learning library for theano and tensorflow, T1 (cf, p.111, 2015.

D. E. Ferdinand and . Saussure, Grande Bibliothèque Payot, 1916. 269 p. (cf, pp.31-33

D. Bhuwan, Z. Zhong, F. Dylan, M. Michael, W. William et al., Character-based distributed representations for social media, vol.50, p.46, 2016.

D. John, E. Hazan, and S. Yoram, Adaptive subgradient methods for online learning and stochastic optimization, Journal of Machine Learning Research, vol.12, p.114, 2011.

E. Ben, R. Tim, A. Isabelle, M. Bo?njak, and R. Sebastian, Learning Emoji Representations from their Description, vol.48, p.41, 2016.

P. Ekman, The Handbook of Cognition and Emotion Pp, vol.97, p.86, 1999.

F. Bjarke, M. Alan, S. Anders, R. Iyad, and L. Sune, Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm, vol.106, p.51, 2017.

L. Joseph, J. Fleiss, . Cohen, S. Brian, and . Everitt, Large sample standard errors of kappa and weighted kappa, Psychological Bulletin, vol.72, p.48, 1969.

F. David, « The viterbi algorithm, Proceedings of the IEEE, vol.61, p.61, 1973.

H. Jerome and . Friedman, Greedy function approximation : a gradient boosting machine, Annals of statistics, p.110, 2001.

. Xavier-glorot and B. Yoshua, Understanding the difficulty of training deep feedforward neural networks », Proceedings of the thirteenth international conference on artificial intelligence and statistics, p.113, 2010.

A. Graves, M. Abdel-rahman, and G. Hinton, IEEE international conference on acoustics, speech and signal processing, IEEE, p.117, 2013.

G. Gaël, O. Magalie, and B. Patrice, « From emojis to sentiment analysis, WACAI 2016, p.36, 2016.

G. Gaël, O. Magalie, and B. Patrice, « Une plateforme de recommandation automatique d'emojis, Traitement Automatique du Langage Naturel, p.128, 2017.

G. David, A. Ben, L. Wei, G. Louise, and W. Yorick, « A closer look at skip-gram modelling. » In : LREC, p.96, 2006.

H. Hussam, B. Patrice, and B. Frederic, « Sentiment lexiconbased features for sentiment analysis in short text, 274249633_Sentiment_Lexicon-Based _ Features _ for _ Sentiment _ Analysis _ in _ Short _ Text / links / 5530bdce0cf2f2a588ab2b65.pdf, vol.71, p.69, 2015.

H. E. Kaiming, Z. Xiangyu, . Shaoqing, and S. Et-jian, Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, p.52, 2016.

H. Sepp and S. Jürgen, « LSTM can solve hard long time lag problems, Advances in neural information processing systems, vol.114, p.51, 1997.

H. Alexander, B. Daniella, F. Flavius, B. Malissa, F. Et-uzay et al., Exploiting emoticons in sentiment analysis, Proceedings of the 28th Annual ACM Symposium on Applied Computing, pp.703-710, 2013.

H. Zhiheng, X. U. Wei, and Y. U. Kai, « Bidirectional LSTM-CRF models for sequence tagging, vol.118, p.51, 2015.

J. Paul, « The distribution of the flora in the alpine zone, New phytologist, vol.1, p.46, 1912.

J. Roman and . Essais-de-linguistique-générale, , vol.143, p.33, 1963.

T. Ahmed, J. , M. Hayati, and A. , Relevance of Emoticons in Computer-Mediated Communication Contexts : An Overview, vol.9, 1911.

J. Armand, G. Edouard, B. Piotr, and M. Tomas, « Bag of tricks for efficient text classification, p.52, 2016.

K. E. Guolin, M. Qi, F. Thomas, W. Taifeng, C. Wei et al., A highly efficient gradient boosting decision tree, Advances in Neural Information Processing Systems, p.111, 2017.

K. Caroline, « Do you know what I mean > :( : A linguistic study of the understanding ofemoticons and emojis in text messages, vol.2, p.783789, 2015.

R. Kelly and L. W. , Characterising the inventive appropriation of emoji as relationally meaningful in mediated close personal relationships, Experiences of Technology Appropriation : Unanticipated Users, Usage, Circumstances, and Design, 2015.

K. Jack and W. Jacob, Stochastic estimation of the maximum of a regression function, The Annals of Mathematical Statistics, vol.23, p.114, 1952.

K. Yoon, Convolutional neural networks for sentence classification, vol.145, p.111, 2014.

P. Diederik, . Kingma, B. A. Jimmy, and . Adam, A method for stochastic optimization, vol.114, p.113, 2014.

K. Petra, J. Novak, . Smailovi?, S. Borut, and M. Igor, Sous la dir. de Matjaz PERC, Sentiment of Emojis, vol.10, p.12, 2015.

L. Yann and B. Yoshua, « Convolutional networks for images, speech, and time series, The handbook of brain theory and neural networks, vol.3361, p.46, 1995.

N. Geoffrey and . Leech, Principles of pragmatics. Routledge, p.36, 2016.

I. Vladimir and . Levenshtein, Binary codes capable of correcting deletions, insertions, and reversals ». In : Soviet physics doklady, vol.63, p.62, 1966.

L. I. Jiwei, M. Luong, and J. Dan, « A hierarchical neural autoencoder for paragraphs and documents, p.51, 2015.

L. I. Xiang, Y. Rui, and Z. Ming, Joint emoji classification and embedding learning, Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference on Web and Big Data, vol.83, p.51, 2017.

L. Rensis, « A technique for the measurement of attitudes. » In : Archives of psychology (1932) (cf, vol.146, p.135

L. Van-der-maaten and G. Hinton, Visualizing data using t-SNE, vol.9, p.88, 2008.

M. James, Some methods for classification and analysis of multivariate observations, Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. T. 1. 14, vol.94, p.89, 1967.

M. Paolo and A. Paolo, « Trust-aware recommender systems, Proceedings of the 2007 ACM conference on Recommender systems, p.127, 2007.

M. Tomas, C. Kai, C. Greg, and D. Jeffrey, « Efficient estimation of word representations in vector space, vol.46, p.108, 2013.

M. Tomas, S. Ilya, C. Kai, S. Greg, J. Corrado et al., Distributed representations of words and phrases and their compositionality, vol.48, p.109, 2013.

A. George, . Miller, and . Wordnet, Communications of the ACM, vol.38, p.92, 1995.

M. Hannah, T. Jacob, C. Shuo, J. Isaac, L. Terveen et al., Blissfully happy" or "ready to fight" : Varying Interpretations of Emoji, 2016.

N. Roberto, P. Simone-paolo, and . Babelnet, Building a very large multilingual semantic network, Proceedings of the 48th annual meeting of the association for computational linguistics, p.48, 2010.

Y. Andrew, M. Ng, and W. Et-yair, On spectral clustering : Analysis and an algorithm, Advances in neural information processing systems, p.99, 2002.

T. Huu, N. Ralph, and G. , « Relation extraction : Perspective from convolutional neural networks », Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing, p.109, 2015.

O. John, . Donovan, and S. Barry, « Trust in recommender systems, Proceedings of the 10th international conference on Intelligent user interfaces, p.105, 2005.

P. Umashanthi, E. Jacob, and . Emoticons-vs, Emojis on Twitter : A Causal Inference Approach, vol.79, p.38, 2015.

J. Michael, . Pazzani, and B. Daniel, « Content-based recommendation systems, The adaptive web, p.105, 2007.

C. Sanders and P. , Logic as semiotic : The theory of signs, p.31, 1902.

P. Robert, « The multifactor-analytic theory of emotion, Journal of Psychology, vol.50, p.47, 1960.

P. Robert, « The nature of emotions : Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice, American scientist, vol.89, p.98, 2001.

P. Henning, C. Domin, R. Michael, and . Beyond, Just Text : Semantic Emoji Similarity Modeling to Support Expressive Communication, ACM Transactions on Computer-Human Interaction (TOCHI), vol.24, p.122, 2017.

Y. Lorien and . Pratt, Discriminability-based transfer between neural networks », p.147, 1993.

R. Dragomir, . Radev, Q. I. Hong, H. Wu, and . Weiguo, Evaluating Webbased Question Answering Systems. » In : LREC. 2002 (cf, vol.117, p.51

R. Yanghui, L. I. Qing, M. Xudong, and W. Liu, « Sentiment topic models for social emotion mining, Information Sciences, vol.266, 2014.

J. R. , Using emoticons to reduce dependency in machine learning techniques for sentiment classification, Proceedings of the ACL student research workshop, pp.43-48, 2005.

R. Radim and S. Petr, « Software framework for topic modelling with large corpora, Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. Citeseer. 2010 (cf, vol.109, p.93

R. Francesco, R. Lior, and S. Bracha, « Introduction to recommender systems handbook, Recommender systems handbook. Springer, vol.146, p.128, 2011.

A. Rosenberg, H. Julia, and . «-v-measure, A conditional entropy-based external cluster evaluation measure, Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL), p.99, 2007.

J. Rogers and S. , Speech acts : An essay in the philosophy of language, p.36, 1969.

S. Guy and G. Asela, « Evaluating recommendation systems, Recommender systems handbook, vol.139, p.128, 2011.

S. Karianne, G. Anette, and K. Anne, The Communicative Functions of Emoticons in Workplace E-Mails : :-) », vol.19, pp.780-797

S. Richard, A. Perelygin, J. Y. Wu, J. C. , C. D. Manning et al., « Recursive deep models for semantic compositionality over a sentiment treebank, Proceedings of the conference on empirical methods in natural language processing (EMNLP). T. 1631. Citeseer, p.1642, 2013.

S. Richard and . Sutton, Learning to predict by the methods of temporal differences, Machine learning, vol.3, p.147, 1988.

, SwiftKey Emoji Report. Avr, vol.39, p.38, 2015.

T. Duyu, W. Furu, Q. Bing, M. Zhou, and L. Ting, « Building large-scale twitter-specific sentiment lexicon : A representation learning approach, Proceedings of coling 2014, the 25th international conference on computational linguistics : Technical papers, p.47, 2014.

E. Research and T. Emoji_report, , vol.38, p.35, 2015.

T. Mike, B. Kevan, P. Georgios, C. Di, and K. Arvid, « Sentiment strength detection in short informal text, Journal of the American Society for Information Science and Technology, vol.61, pp.69-71, 2010.

T. Tian, D. Marco, T. Isabelle, and C. Pedro, « Etiquetage morpho-syntaxique de tweets avec des CRF, TALN 2015, p.91, 2015.

T. Tijmen and H. Geoffrey, 5-rmsprop : Divide the gradient by a running average of its recent magnitude, COURSERA : Neural networks for machine learning, vol.6, p.113, 2012.

C. C. Tossell, K. Philip, C. Shepard, L. H. Barg-walkow, R. Ahmad et al., « A longitudinal study of emoticon use in text messaging from smartphones, Computers in Human Behavior, vol.28, issue.2, p.37, 2012.

V. Nguyen-xuan, J. Epps, and B. James, « Information theoretic measures for clusterings comparison : Variants, properties, normalization and correction for chance, Journal of Machine Learning Research, vol.11, p.99, 2010.

V. L. Ulrike, A tutorial on spectral clustering, Statistics and computing, vol.17, p.100, 2007.

V. Soroush, P. Vijayaraghavan, R. Deb, and . Tweet2vec, Learning tweet embeddings using character-level cnn-lstm encoder-decoder, Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, vol.50, p.46, 2016.

J. Christopher, . Watkins, D. Peter, and . «-q-learning, Machine learning, vol.8, p.147, 1992.

W. Sanjaya, B. Lakshika, S. Amit, and D. Derek,

, « A semantics-based measure of emoji similarity, Proceedings of the International Conference on Web Intelligence, p.48, 2017.

X. Ruobing, L. Zhiyuan, Y. Rui, and S. Maosong, Neural emoji recommendation in dialogue systems, vol.53, p.51, 2016.

X. Ruobing, L. Zhiyuan, Y. Rui, and S. Maosong, « Neural emoji recommendation in dialogue systems, p.73, 2016.

X. U. Kelvin, B. A. Jimmy, K. Ryan, C. Kyunghyun, C. Aaron et al., attend and tell : Neural image caption generation with visual attention, International conference on machine learning, p.124, 2015.

Y. E. Mao, L. Xingjie, and L. Wang-chien, Exploring social influence for recommendation : a generative model approach, Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, p.57, 2012.

Z. Luda and Z. Connie, Using neural networks to predict emoji usage from twitter data, vol.106, p.51, 2017.

, plusieurs choix de départ ont été faits en gardant en tête le déploiement final visible en figure B.1, tout particulièrement pour la recommandation par catégories d'emojis (voir Chapitre 5)

, Système en Java : l'application Mood Messenger étant en Java, l'intégration du système de recommandation doit se faire par ce langage de programmation

, Ré-utilisabilité du modèle : le modèle de prédiction appris doit être utilisable directement dans l'application finale

, Optimisations d'espace disque et de ressources de calcul : l'utilisation de la batterie doit être limitée et l'augmentation de la taille de l'application finale doit être moindre

, Ces trois points résultent d'obstacles réels provenant de la nature même de l'application finale. En effet, une messagerie SMS n'est pas attendue comme étant une application lourde

B. , Déploiement Le déploiement de l'application est pensé en amont, avant les expérimentations, afin de répondre aux besoins du langage et de la ré-utilisation du modèle. En effet, le modèle de prédiction appris en Python doit être réutilisable en Java, c'est pourquoi l'interface de programmation (API) Keras 6 a été choisie : les modèles appris sous Keras fonctionnent directement sous DeepLearning4J 7 , l'interface de programmation open source dédiées à l'apprentissage profond en Java. Un modèle appris en python sera alors immédiatement utilisable sous Java

, La choix de DeepLearning4J n'est toutefois pas final et a été remplacé par l'utilisation directe de TensorFlow 8 . L'utilisation de TensorFlow au lieu de DeepLear-ning4J permet une réduction des dépendances en passant du nombre élevé de dépendances DL4J au seul import de la classe d'interface Java pour les inférences de TensorFlow. Cette dernière nécessite l'utilisation du Native Development Kit (NDK) pour lire la version native en C++ de Tensorflow

, Lors de chaque requête entrante, le pré-traitement effectué précédemment à l'aide de librairies Python comme NLTK ou Scikit-Learn doit être reproduit en 6