A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews

Edison Marrese-Taylor, Cristian Rodriguez, Jorge Balazs, Stephen Gould, Yutaka Matsuo


Abstract
Despite the recent advances in opinion mining for written reviews, few works have tackled the problem on other sources of reviews. In light of this issue, we propose a multi-modal approach for mining fine-grained opinions from video reviews that is able to determine the aspects of the item under review that are being discussed and the sentiment orientation towards them. Our approach works at the sentence level without the need for time annotations and uses features derived from the audio, video and language transcriptions of its contents.We evaluate our approach on two datasets and show that leveraging the video and audio modalities consistently provides increased performance over text-only baselines, providing evidence these extra modalities are key in better understanding video reviews.
Anthology ID:
2020.challengehml-1.2
Volume:
Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)
Month:
July
Year:
2020
Address:
Seattle, USA
Venues:
ACL | Challenge-HML | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8–18
Language:
URL:
https://aclanthology.org/2020.challengehml-1.2
DOI:
10.18653/v1/2020.challengehml-1.2
Bibkey:
Cite (ACL):
Edison Marrese-Taylor, Cristian Rodriguez, Jorge Balazs, Stephen Gould, and Yutaka Matsuo. 2020. A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews. In Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML), pages 8–18, Seattle, USA. Association for Computational Linguistics.
Cite (Informal):
A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews (Marrese-Taylor et al., Challenge-HML 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.challengehml-1.2.pdf
Video:
 http://slideslive.com/38931259
Data
Youtubean