Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Wenchang, Lalor, John P., Chen, Yixing, Kanuri, Vamsi K.
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2305.01710
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918124490588160
author Li, Wenchang
Lalor, John P.
Chen, Yixing
Kanuri, Vamsi K.
author_facet Li, Wenchang
Lalor, John P.
Chen, Yixing
Kanuri, Vamsi K.
contents Sentiment analysis is integral to understanding the voice of the customer and informing businesses' strategic decisions. Conventional sentiment analysis involves three separate tasks: aspect-category detection, aspect-category sentiment analysis, and rating prediction. However, independently tackling these tasks can overlook their interdependencies and often requires expensive, fine-grained annotations. This paper introduces unified sentiment analysis, a novel learning paradigm that integrates the three aforementioned tasks into a coherent framework. To achieve this, we propose the Distantly Supervised Pyramid Network (DSPN), which employs a pyramid structure to capture sentiment at word, aspect, and document levels in a hierarchical manner. Evaluations on multi-aspect review datasets in English and Chinese show that DSPN, using only star rating labels for supervision, demonstrates significant efficiency advantages while performing comparably well to a variety of benchmark models. Additionally, DSPN's pyramid structure enables the interpretability of its outputs. Our findings validate DSPN's effectiveness and efficiency, establishing a robust, resource-efficient, unified framework for sentiment analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2305_01710
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision
Li, Wenchang
Lalor, John P.
Chen, Yixing
Kanuri, Vamsi K.
Computation and Language
Sentiment analysis is integral to understanding the voice of the customer and informing businesses' strategic decisions. Conventional sentiment analysis involves three separate tasks: aspect-category detection, aspect-category sentiment analysis, and rating prediction. However, independently tackling these tasks can overlook their interdependencies and often requires expensive, fine-grained annotations. This paper introduces unified sentiment analysis, a novel learning paradigm that integrates the three aforementioned tasks into a coherent framework. To achieve this, we propose the Distantly Supervised Pyramid Network (DSPN), which employs a pyramid structure to capture sentiment at word, aspect, and document levels in a hierarchical manner. Evaluations on multi-aspect review datasets in English and Chinese show that DSPN, using only star rating labels for supervision, demonstrates significant efficiency advantages while performing comparably well to a variety of benchmark models. Additionally, DSPN's pyramid structure enables the interpretability of its outputs. Our findings validate DSPN's effectiveness and efficiency, establishing a robust, resource-efficient, unified framework for sentiment analysis.
title From Stars to Insights: Exploration and Implementation of Unified Sentiment Analysis with Distant Supervision
topic Computation and Language
url https://arxiv.org/abs/2305.01710