@inproceedings{marrese-taylor-etal-2020-multi,
title = "A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews",
author = "Marrese-Taylor, Edison and
Rodriguez, Cristian and
Balazs, Jorge and
Gould, Stephen and
Matsuo, Yutaka",
booktitle = "Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.challengehml-1.2",
doi = "10.18653/v1/2020.challengehml-1.2",
pages = "8--18",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marrese-taylor-etal-2020-multi">
<titleInfo>
<title>A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edison</namePart>
<namePart type="family">Marrese-Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristian</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Balazs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Gould</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutaka</namePart>
<namePart type="family">Matsuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">marrese-taylor-etal-2020-multi</identifier>
<identifier type="doi">10.18653/v1/2020.challengehml-1.2</identifier>
<location>
<url>https://aclanthology.org/2020.challengehml-1.2</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>8</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
%A Marrese-Taylor, Edison
%A Rodriguez, Cristian
%A Balazs, Jorge
%A Gould, Stephen
%A Matsuo, Yutaka
%S Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F marrese-taylor-etal-2020-multi
%X 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.
%R 10.18653/v1/2020.challengehml-1.2
%U https://aclanthology.org/2020.challengehml-1.2
%U https://doi.org/10.18653/v1/2020.challengehml-1.2
%P 8-18
Markdown (Informal)
[A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews](https://aclanthology.org/2020.challengehml-1.2) (Marrese-Taylor et al., Challenge-HML 2020)
ACL