Weakly Supervised Open-Domain Aspect-Based Sentiment Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AGX29LCHB" target="_blank" >RIV/00216208:11320/26:GX29LCHB - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1145/3747849" target="_blank" >http://dx.doi.org/10.1145/3747849</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3747849" target="_blank" >10.1145/3747849</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Weakly Supervised Open-Domain Aspect-Based Sentiment Analysis

Popis výsledku v původním jazyce

Aspect-Based Sentiment Analysis (ABSA) comprises several subtasks: aspect term extraction (ATE), opinion term extraction (OTE), aspect term sentiment extraction (ATSE), aspect-opinion pair extraction (AOPE), and aspect sentiment triplet extraction (ASTE). Existing unified frameworks for ABSA rely heavily on large-scale annotated data, limiting scalability across domains. We propose UAOS, a double-layer unified span extraction framework that performs all five ABSA subtasks under weak supervision. Our approach first extracts aspect-opinion pairs using universal dependency-based rules from unannotated corpora. Sentiment labels for these pairs are generated via a novel zero-shot, domain-agnostic prompt-based method. The resulting weak labels train a unified span extraction architecture equipped with canonical correlation analysis for early stopping and a self-training mechanism to mitigate noise and bias in supervision. Extensive experiments on four ABSA benchmarks demonstrate that UAOS achieves competitive or superior performance compared to fully supervised baselines. It improves upon the state-of-the-art ODAO by +1.54 F1 for ATE, +0.56 for OTE, and +0.82 for AOPE. In ATSE and ASTE, where no weakly supervised baselines exist, UAOS outperforms several supervised models, setting new benchmarks. To assess domain generalizability, we evaluate UAOS on a psychology/education-domain dataset of student reflections spanning four instructional conditions. Without in-domain fine-tuning, it achieves macro F1 scores of 71.05 (ATE), 74.39 (OTE), 68.24 (AOPE), and 60.56 (ASTE). These results highlight the model’s ability to generalize to out-of-distribution, non-commercial text, underscoring its scalability for low-resource ABSA applications. © 2025 Copyright held by the owner/author(s).

Název v anglickém jazyce

Weakly Supervised Open-Domain Aspect-Based Sentiment Analysis

Popis výsledku anglicky

Aspect-Based Sentiment Analysis (ABSA) comprises several subtasks: aspect term extraction (ATE), opinion term extraction (OTE), aspect term sentiment extraction (ATSE), aspect-opinion pair extraction (AOPE), and aspect sentiment triplet extraction (ASTE). Existing unified frameworks for ABSA rely heavily on large-scale annotated data, limiting scalability across domains. We propose UAOS, a double-layer unified span extraction framework that performs all five ABSA subtasks under weak supervision. Our approach first extracts aspect-opinion pairs using universal dependency-based rules from unannotated corpora. Sentiment labels for these pairs are generated via a novel zero-shot, domain-agnostic prompt-based method. The resulting weak labels train a unified span extraction architecture equipped with canonical correlation analysis for early stopping and a self-training mechanism to mitigate noise and bias in supervision. Extensive experiments on four ABSA benchmarks demonstrate that UAOS achieves competitive or superior performance compared to fully supervised baselines. It improves upon the state-of-the-art ODAO by +1.54 F1 for ATE, +0.56 for OTE, and +0.82 for AOPE. In ATSE and ASTE, where no weakly supervised baselines exist, UAOS outperforms several supervised models, setting new benchmarks. To assess domain generalizability, we evaluate UAOS on a psychology/education-domain dataset of student reflections spanning four instructional conditions. Without in-domain fine-tuning, it achieves macro F1 scores of 71.05 (ATE), 74.39 (OTE), 68.24 (AOPE), and 60.56 (ASTE). These results highlight the model’s ability to generalize to out-of-distribution, non-commercial text, underscoring its scalability for low-resource ABSA applications. © 2025 Copyright held by the owner/author(s).

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

ACM Transactions on Knowledge Discovery from Data

ISSN

1556-4681

e-ISSN

—

Svazek periodika

19

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

17

Strana od-do

139

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105018459343