2019/08/29 by Alexandre Garcia, Garcia, Alexandre, Pierre Colombo +6
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Sentiment Analysis and Opinion Mining #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1908.11216
openalex publication_date 2019/08/29 · openalex created_date 2019/09/05 · openalex updated_date 2026/07/28
The task of predicting fine grained user opinion based on spontaneous spoken\nlanguage is a key problem arising in the development of Computational Agents as\nwell as in the development of social network based opinion miners.\nUnfortunately, gathering reliable data on which a model can be trained is\nnotoriously difficult and existing works rely only on coarsely labeled\nopinions. In this work we aim at bridging the gap separating fine grained\nopinion models already developed for written language and coarse grained models\ndeveloped for spontaneous multimodal opinion mining. We take advantage of the\nimplicit hierarchical structure of opinions to build a joint fine and coarse\ngrained opinion model that exploits different views of the opinion expression.\nThe resulting model shares some properties with attention-based models and is\nshown to provide competitive results on a recently released multimodal fine\ngrained annotated corpus.\n