Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis

Chen, Chenhua; Teng, Zhiyang; Wang, Zhongqing; Zhang, Yue

doi:10.18653/v1/2022.acl-long.145

Cited by 61 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use IARM (Majumder et al 2018), MIAD (Hazarika et al 2018), StageI+StageII (Ma et al 2019), CDT (Sun et al 2019) as baselines for their modeling aspect-related information using LSTMs. We also use Joint+PRET (Zhou et al 2020), RepWalk (Zheng et al 2020), BERT-SPC (Song et al 2019), CapsNet (Jiang et al 2019), SDGCN (Zhao, Hou, and Wu 2020), InterGCN (Liang et al 2020), R-GAT (Wang et al 2020), T-GCN (Tian, Chen, and Song 2021), RGAT (Bai, Liu, and Zhang 2021), RMN (Zeng et al 2022), dot-GCN (Chen et al 2022), CHGMAN (Niu et al 2022) and APSCL (Li, Li, and Xiao 2023) as baselines, as they focus on inter-aspect relations or aspect-oriented tree structure using GCNs and BERT.…”

Section: Baselinesmentioning

confidence: 99%

“…3) Aspect-oriented tree construction. In addition to using existing dependency trees to model relational information, some researchers transform dependency trees into aspect-oriented tree structures to enhance GCN structure and better capture aspect-related information (Wang et al 2020;Zhou et al 2021;Chen et al 2022). For example, Wang et al (2020) reshaped and pruned a dependency parsing tree to construct an aspect-oriented tree to capture aspect-related information; Chen et al (2022) used reinforcement learning and regularization to induce discrete opinion trees to shorten the distance of corresponding opinion words.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification

Zheng,

2024

AAAI

View full text Add to dashboard Cite

Most of the existing aspect-based sentiment analysis (ABSA) models only predict the sentiment polarity of a single aspect at a time, focusing primarily on enhancing the representation of this single aspect based on the other contexts or aspects. This one-to-one paradigm ignores the fact that multi-aspect, multi-sentiment sentences contain not only distinct specific descriptions for distinct specific aspects, but also shared global context information for multiple aspects. To fully consider these issues, we propose a one-to-many ABSA framework, called You Only Read Once (YORO), that can simultaneously model representations of all aspects based on their specific descriptions and better fuse their relationships using globally shared contextual information in the sentence. Predicting the sentiment polarity of multiple aspects simultaneously is beneficial to improving the efficacy of calculation and prediction. Extensive experiments are conducted on three public datasets (MAMS, Rest14, and Lap14). Experimental results demonstrate the effectiveness of YORO in handling multi-aspect, multi-sentiment scenarios and highlight the promise of one-to-many ABSA in balancing efficiency and accuracy.

show abstract

Section: Baselinesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification

Zheng,

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…We follow Chen et al (2017) and use Accuracy and Macro-F1 score as evaluation metrics. We compare our approach with state-of-the-art models that require training, namely DGEDT (Tang et al 2020) and dotGCN (Chen et al 2022).…”

Section: Aspect-based Sentiment Analysismentioning

confidence: 99%

Stance Detection with Collaborative Role-Infused LLM-Based Agents

Lan,

Gao,

Jin

et al. 2024

ICWSM

View full text Add to dashboard Cite

Stance detection automatically detects the stance in a text towards a target, vital for content analysis in web and social media research. Despite their promising capabilities, LLMs encounter challenges when directly applied to stance detection. First, stance detection demands multi-aspect knowledge, from deciphering event-related terminologies to understanding the expression styles in social media platforms. Second, stance detection requires advanced reasoning to infer authors' implicit viewpoints, as stances are often subtly embedded rather than overtly stated in the text. To address these challenges, we design a three-stage framework COLA (short for Collaborative rOle-infused LLM-based Agents) in which LLMs are designated distinct roles, creating a collaborative system where each role contributes uniquely. Initially, in the multidimensional text analysis stage, we configure the LLMs to act as a linguistic expert, a domain specialist, and a social media veteran to get a multifaceted analysis of texts, thus overcoming the first challenge. Next, in the reasoning-enhanced debating stage, for each potential stance, we designate a specific LLM-based agent to advocate for it, guiding the LLM to detect logical connections between text features and stance, tackling the second challenge. Finally, in the stance conclusion stage, a final decision maker agent consolidates prior insights to determine the stance. Our approach avoids extra annotated data and model training and is highly usable. We achieve state-of-the-art performance across multiple datasets. Ablation studies validate the effectiveness of each role design in handling stance detection. Further experiments have demonstrated the explainability and the versatility of our approach. Our approach excels in usability, accuracy, effectiveness, explainability and versatility, highlighting its value.

show abstract

“…Models. The TSA models that we benchmark on METS-CoV-TSA could be classified into 4 categories: 1 statistical machine learning model: SVM (Vo and Zhang, 2015); 7 traditional neural network models: ASGCN , LSTM (Hochreiter and Schmidhuber, 1997), TD-LSTM (Tang et al, 2016b), MemNet (Tang et al, 2016a), IAN (Ma et al, 2017), MGAN (Fan et al, 2018) and TNet-LF ; 6 general domain PLM (BERT-base-uncased): AEN , LCF (Zeng et al, 2019), BERT-SPC (Devlin et al, 2019), depGCN , kumaGCN (Chen et al, 2020b) and dotGCN (Chen et al, 2022); and 4 models (BERT-SPC, depGCN , kumaGCN and dotGCN) with COVID-19 related PLM (COVID-TWITTER-BERT).…”

Section: Targeted Sentiment Analysismentioning

confidence: 99%

METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets

Zhou¹,

Wang²,

Chong³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The COVID-19 pandemic continues to bring up various topics discussed or debated on social media. In order to explore the impact of pandemics on people's lives, it is crucial to understand the public's concerns and attitudes towards pandemicrelated entities (e.g., drugs, vaccines) on social media. However, models trained on existing named entity recognition (NER) or targeted sentiment analysis (TSA) datasets have limited ability to understand COVID-19-related social media texts because these datasets are not designed or annotated from a medical perspective. This paper releases METS-CoV, a dataset containing medical entities and targeted sentiments from COVID-19-related tweets. METS-CoV contains 10,000 tweets with 7 types of entities, including 4 medical entity types (Disease, Drug, Symptom, and Vaccine) and 3 general entity types (Person, Location, and Organization). To further investigate tweet users' attitudes toward specific entities, 4 types of entities (Person, Organization, Drug, and Vaccine) are selected and annotated with user sentiments, resulting in a targeted sentiment dataset with 9,101 entities (in 5,278 tweets). To the best of our knowledge, METS-CoV is the first dataset to collect medical entities and corresponding sentiments of COVID-19-related tweets. We benchmark the performance of classical machine learning models and state-of-the-art deep learning models on NER and TSA tasks with extensive experiments. Results show that the dataset has vast room for improvement for both NER and TSA tasks. With rich annotations and comprehensive benchmark results, we believe METS-CoV is a fundamental resource for building better medical social media understanding tools and facilitating computational social science research, especially on epidemiological topics. Our data, annotation guidelines, benchmark models, and source code are publicly available (https://github.com/YLab-Op en/METS-CoV) to ensure reproducibility.

show abstract

Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis

Cited by 61 publications

References 0 publications

You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification

You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification

Stance Detection with Collaborative Role-Infused LLM-Based Agents

METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets

Contact Info

Product

Resources

About