Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/20.500.14279/26524
Τίτλος: | Dialog Speech Sentiment Classification for Imbalanced Datasets | Συγγραφείς: | Nicolaou, Sergis Mavrides, Lambros Tryfou, Georgina Tolias, Kyriakos Panousis, Konstantinos P. Chatzis, Sotirios P. Theodoridis, Sergios |
Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Λέξεις-κλειδιά: | Acoustic classification;Bi-modal processing;Sentiment analysis;Text classification | Ημερομηνία Έκδοσης: | Σεπ-2021 | Πηγή: | 23rd International Conference on Speech and Computer, 2021, 27-30 September, Virtual Conference | Conference: | International Conference on Speech and Computer | Περίληψη: | Speech is the most common way humans express their feelings, and sentiment analysis is the use of tools such as natural language processing and computational algorithms to identify the polarity of these feelings. Even though this field has seen tremendous advancements in the last two decades, the task of effectively detecting under represented sentiments in different kinds of datasets is still a challenging task. In this paper, we use single and bi-modal analysis of short dialog utterances and gain insights on the main factors that aid in sentiment detection, particularly in the underrepresented classes, in datasets with and without inherent sentiment component. Furthermore, we propose an architecture which uses a learning rate scheduler and different monitoring criteria and provides state-of-the-art results for the SWITCHBOARD imbalanced sentiment dataset. | URI: | https://hdl.handle.net/20.500.14279/26524 | ISBN: | 978-3-030-87802-3 | DOI: | 10.1007/978-3-030-87802-3_42 | Rights: | © Springer | Type: | Conference Papers | Affiliation: | Impactech LTD Cyprus University of Technology Aalborg University |
Εμφανίζεται στις συλλογές: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
CORE Recommender
Αυτό το τεκμήριο προστατεύεται από άδεια Άδεια Creative Commons