From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining
This addresses the challenge of reliable fine-grained opinion mining for computational agents and social networks, though it appears incremental by combining existing approaches.
The paper tackles the problem of predicting fine-grained user opinions from spontaneous spoken language by bridging the gap between existing fine-grained models for written text and coarse-grained models for multimodal data. The result is a hierarchical multimodal model that achieves competitive performance on a recently released annotated corpus.
The task of predicting fine grained user opinion based on spontaneous spoken language is a key problem arising in the development of Computational Agents as well as in the development of social network based opinion miners. Unfortunately, gathering reliable data on which a model can be trained is notoriously difficult and existing works rely only on coarsely labeled opinions. In this work we aim at bridging the gap separating fine grained opinion models already developed for written language and coarse grained models developed for spontaneous multimodal opinion mining. We take advantage of the implicit hierarchical structure of opinions to build a joint fine and coarse grained opinion model that exploits different views of the opinion expression. The resulting model shares some properties with attention-based models and is shown to provide competitive results on a recently released multimodal fine grained annotated corpus.