Weakly Supervised Open-Domain Aspect-Based Sentiment Analysis
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
Weakly Supervised Open-Domain Aspect-Based Sentiment Analysis
Original language description
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).
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
ACM Transactions on Knowledge Discovery from Data
ISSN
1556-4681
e-ISSN
—
Volume of the periodical
19
Issue of the periodical within the volume
7
Country of publishing house
US - UNITED STATES
Number of pages
17
Pages from-to
139
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-105018459343