Opinion Holder and Target Extraction for Verb-based Opinion Predicates – The Problem is Not Solved

Wiegand, Michael; Schulder, Marc; Ruppenhofer, Josef

doi:10.18653/v1/w15-2921

Cited by 8 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study in question represents leading research for opinion holder extraction in Arabic news sources, independent from any lexical parsers. Wiegand et al [16] utilized a convolutional kernel classifier, and introduced a new corpus focusing on the roles of opinion verbs from the subjectivity lexicon. Subsequently, they demonstrated the potential benefits of this corpus.…”

Section: Related Workmentioning

confidence: 99%

Dataset Construction and Opinion Holder Detection Using Pre-trained Models

Mahmud,

Shimada

2023

International Journal of Service and Knowledge Management

View full text Add to dashboard Cite

With the growing prevalence of the Internet, increasingly more people and entities express opinions on online platforms, such as Facebook, Twitter, and Amazon. As it is becoming impossible to detect online opinion trends manually, an automatic approach to detect opinion holders is essential as a means to identify specific concerns regarding a particular topic, product, or problem. Opinion holder detection comprises two steps: the presence of opinion holders in text and identification of opinion holders. The present study examines both steps. Initially, we approach this task as a binary classification problem: INSIDE or OUTSIDE. Then, we consider the identification of opinion holders as a sequence labeling task and prepare an appropriate English-language dataset. Subsequently, we employ three pre-trained models for the opinion holder detection task: BERT, DistilBERT, and contextual string embedding (CSE). For the binary classification task, we employ a logistic regression model on the top layers of the BERT and DistilBERT models. We compare the models' performance in terms of the F1 score and accuracy. Experimental results show that DistilBERT obtained superior performance, with an F1 score of 0.901 and an accuracy of 0.924. For the opinion holder identification task, we utilize both feature-and fine-tuning-based architectures. Furthermore, we combined CSE and the conditional random field (CRF) with BERT and Distil-BERT. For the feature-based architecture, we utilize five models: CSE+CRF, BERT+CRF, (BERT&CSE)+CRF, DistilBERT+CRF, and (DistilBERT&CSE)+CRF. For the fine-tuningbased architecture, we utilize six models: BERT, BERT+CRF, (BERT&CSE)+CRF, Distil-BERT, DistilBERT+CRF, and (DistilBERT&CSE)+CRF. All language models are evaluated in terms of F1 score and processing time. The experimental results indicate that both the feature-and fine-tuning-based (DistilBERT&CSE)+CRF models jointly yielded the optimal performance, with an F1 score of 0.9453. However, feature-based CSE+CRF incurred the lowest processing time of 49 s while yielding a comparable F1 score to that obtained by the optimal-performing models.

show abstract

Section: Related Workmentioning

confidence: 99%

Dataset Construction and Opinion Holder Detection Using Pre-trained Models

Mahmud,

Shimada

2023

International Journal of Service and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…Noun-based opinion identification was first developed by Riloff et al [21], who used bootstrapping algorithms that exploit extraction patterns to learn sets of subjective nouns, while Zhang et al [7] focused on noun and noun phrase identification, which implies opinions by using an opinion lexicon. In addition to noun-based aspect extraction, some studies have developed a verb-based approach to extract aspects [2], [8], [10], [22]. Other studies have also stated that a verb can implicitly represent opinions [8], [23]- [25].…”

Section: Related Workmentioning

confidence: 99%

“…Other studies have also stated that a verb can implicitly represent opinions [8], [23]- [25]. However, there are numerous challenges in deriving aspects and their associated opinion words based on nouns and verbs [2], [8], [10], [22].…”

Section: Related Workmentioning

confidence: 99%

Clue Propagation Based on Non-Adjective Opinion Words for Handling Disconnected Propagation in Product Reviews

2022

View full text Add to dashboard Cite

Recently, much research has focused on explicit aspect extraction. User reviews in the textual form are unstructured data, creating a very high complexity when processed for sentiment analysis. Previous propagation approaches proposed in this area mainly focused only on adjectiveand-noun-based relations. By using only a small seed of opinion words, there is a possibility that the propagation can be disconnected, resulting in several aspects and opinions remaining unextracted. To overcome the aforementioned problem, we propose clue propagation method by using several clues to successfully identify aspects and opinions to extract explicit aspects, including noun-and-verb-based relations. The utilization of more than one clue in the propagation prevented premature termination, extending the scope of the extraction. We evaluated our proposed method by comparing it with several state-of-the-art methods. Empirically, the experimental results showed that the added more clues in clue propagation method could extract aspects and opinions that were not extracted in previous studies. Clue propagation can overcome the possibility of disconnected properties in the propagation method.INDEX TERMS aspect-based sentiment analysis, aspect extraction, explicit aspect, clue propagation, noun-and-verb-based relations.

show abstract

“…focus on clause representation to support accurate connective prediction, a task which is important for coherence modeling (Pishdad et al, 2020), finegrained opinion mining (Wiegand et al, 2015), argument mining (Kuribayashi et al, 2019;Jo et al, 2020) and argumentation (Park and Cardie, 2014). We present a case for a model that learns from a novel graph we refer to as a dependency-anchor graph, which retains information from dependency parses and constituency parses of input sentences that is critical for identification of the core proposition of a clause, while omitting structural information that is less relevant.…”

Section: P1mentioning

confidence: 99%

Learning Clause Representation from Dependency-Anchor Graph for Connective Prediction

Gao

Huang²,

Passonneau

2021

Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)

View full text Add to dashboard Cite

Semantic representation that supports the choice of an appropriate connective between pairs of clauses inherently addresses discourse coherence, which is important for tasks such as narrative understanding, argumentation, and discourse parsing. We propose a novel clause embedding method that applies graph learning to a data structure we refer to as a dependencyanchor graph. The dependency anchor graph incorporates two kinds of syntactic information, constituency structure and dependency relations, to highlight the subject and verb phrase relation. This enhances coherencerelated aspects of representation. We design a neural model to learn a semantic representation for clauses from graph convolution over latent representations of the subject and verb phrase. We evaluate our method on two new datasets: a subset of a large corpus where the source texts are published novels, and a new dataset collected from students' essays. The results demonstrate a significant improvement over tree-based models, confirming the importance of emphasizing the subject and verb phrase. The performance gap between the two datasets illustrates the challenges of analyzing student's written text, plus a potential evaluation task for coherence modeling and an application for suggesting revisions to students.

show abstract

Opinion Holder and Target Extraction for Verb-based Opinion Predicates – The Problem is Not Solved

Cited by 8 publications

References 19 publications

Dataset Construction and Opinion Holder Detection Using Pre-trained Models

Dataset Construction and Opinion Holder Detection Using Pre-trained Models

Clue Propagation Based on Non-Adjective Opinion Words for Handling Disconnected Propagation in Product Reviews

Learning Clause Representation from Dependency-Anchor Graph for Connective Prediction

Contact Info

Product

Resources

About