%0 Conference Proceedings %T Implicit and Explicit Aspect Extraction in Financial Microblogs %+ Insight Centre for Data Analytics [Galway] (INSIGHT) %+ National University of Ireland Maynooth (Maynooth University) %A Gaillat, Thomas %A Stearns, Bernardo %A Sridhar, Gopal %A Mcdermott, Ross %A Zarrouk, Manel %A Davis, Brian %< avec comité de lecture %( Proceedings of the First Workshop on Economics and Natural Language Processing, %B 1st Workshop on Economics and Natural Language Processing (ECONLP 2018) %C Melbourne, Australia %I Association for Computational Linguistics %V 56 %N 1 %P 55-61 %8 2018-07-20 %D 2018 %R 10.5281/zenodo.1326536 %Z Humanities and Social Sciences/Library and information sciences %Z Humanities and Social Sciences/LinguisticsConference papers %X This paper focuses on aspect extraction which is a sub-task of Aspect-based Sentiment Analysis. The goal is to report an extraction method of financial aspects in microblog messages. Our approach uses a stock-investment taxonomy for the identification of explicit and implicit aspects. We compare supervised and unsupervised methods to assign predefined categories at message level. Results on 7 aspect classes show 0.71 accuracy, while the 32 class classification gives 0.82 accuracy for messages containing explicit aspects and 0.35 for implicit aspects. %G English %2 https://univ-rennes2.hal.science/hal-02280371/document %2 https://univ-rennes2.hal.science/hal-02280371/file/W18-3108.pdf %L hal-02280371 %U https://univ-rennes2.hal.science/hal-02280371 %~ SHS %~ AO-LINGUISTIQUE %~ UNIV-RENNES2 %~ UNIV-RENNES