Context-Dependent Sentiment Analysis in User-Generated Videos

Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Navonil Majumder, Amir Zadeh, Louis‐Philippe Morency · 2017

Read Context-Dependent Sentiment Analysis in User-Generated Videos by Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Navonil Majumder, Amir Zadeh, Louis‐Philippe Morency (2017) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/openalex-w2740550900.txt.

Description

Soujanya Poria, Erik Cambria, and Devamanyu Hazarika, with colleagues, presented this work at the 2017 meeting of the Association for Computational Linguistics. It concerns sentiment analysis of user-generated videos, like product and movie reviews on YouTube. Videos carry feelings in words, voice, and face at once. That richness makes them valuable, and harder, for opinion mining.

Earlier systems judged each spoken segment on its own. This work instead tracks how segments relate, since one remark's meaning depends on what came before. It labels sentiment utterance by utterance through the whole video. Combining text with vocal and visual cues gives a sturdier read of the speaker's state. Understanding sentiment dynamics helps buyers weigh reviews and helps companies hear customers. The paper pushes video opinion mining from single snapshots toward flowing context.

Catalog record

CREATORSoujanya Poria, Erik Cambria, Devamanyu Hazarika, Navonil Majumder, Amir Zadeh, Louis‐Philippe Morency
YEAR2017
COLLECTIONPAPERS
FORMATTXT
FILE SIZE45 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEOpenAlex / Annual Meeting of the Association for Computational Linguistics (ACL)

Source: https://doi.org/10.18653/v1/p17-1081

Browse the full library · About the Tower of Babel