Multi-Entity Aspect-Based Sentiment Analysis With Context, Entity and Aspect Memory

Yang, Jun; Yang, Runqi; Wang, Chongjun; Xie, Jin

doi:10.1609/aaai.v32i1.12059

Cited by 25 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, aspect words [15], objects [16] and even the Opinion Target Expression (OTE) based aspects can also be extracted in ATE. While as, in the second phase of Aspect Term Categorization (ATC), emotion polarity is classified as a predefined attribute, object, or entity [17]. In addition to this, ATC is also responsible for extracting the connections, linkages and context-specific linkages across diverse data items such as target, object, aspect and sentiment words so that the accuracy of sentiment classification is enhanced [18].…”

Section: B Organization Of the Surveymentioning

confidence: 99%

Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches

Kumar¹,

Gupta

et al. 2023

IJRITCC

View full text Add to dashboard Cite

Sentiment analysis (SA) is also known as opinion mining, it is the process of gathering and analyzing people's opinions about a particular service, good, or company on websites like Twitter, Facebook, Instagram, LinkedIn, and blogs, among other places. This article covers a thorough analysis of SA and its levels. This manuscript's main focus is on aspect-based SA, which helps manufacturing organizations make better decisions by examining consumers' viewpoints and opinions of their products. The many approaches and methods used in aspect-based sentiment analysis are covered in this review study (ABSA). The features associated with the aspects were manually drawn out in traditional methods, which made it a time-consuming and error-prone operation. Nevertheless, these restrictions may be overcome as artificial intelligence develops. Therefore, to increase the effectiveness of ABSA, researchers are increasingly using AI-based machine learning (ML) and deep learning (DL) techniques. Additionally, certain recently released ABSA approaches based on ML and DL are examined, contrasted, and based on this research, gaps in both methodologies are discovered. At the conclusion of this study, the difficulties that current ABSA models encounter are also emphasized, along with suggestions that can be made to improve the efficacy and precision of ABSA systems.

show abstract

Section: B Organization Of the Surveymentioning

confidence: 99%

Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches

Kumar¹,

Gupta

et al. 2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity towards a given aspect in the sentence. Many previous works (Yang et al, 2018; The food is great but the service and the environment are dreadful". Two separate ellipses encircle its two clauses.…”

Section: Introductionmentioning

confidence: 99%

BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis

Liang¹,

Wei²,

Mao³

et al. 2022

Findings of the Association for Computational Linguistics: ACL 2022

View full text Add to dashboard Cite

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity inference. It is challenging because a sentence may contain multiple aspects or complicated (e.g., conditional, coordinating, or adversative) relations. Recently, exploiting dependency syntax information with graph neural networks has been the most popular trend. Despite its success, methods that heavily rely on the dependency tree pose challenges in accurately modeling the alignment of the aspects and their words indicative of sentiment, since the dependency tree may provide noisy signals of unrelated associations (e.g., the "conj" relation between "great" and "dreadful" in Figure 2). In this paper, to alleviate this problem, we propose a Bi-Syntax aware Graph Attention Network (BiSyn-GAT+). Specifically, BiSyn-GAT+ fully exploits the syntax information (e.g., phrase segmentation and hierarchical structure) of the constituent tree of a sentence to model the sentiment-aware context of every single aspect (called intracontext) and the sentiment relations across aspects (called inter-context) for learning. Experiments on four benchmark datasets demonstrate that BiSyn-GAT+ outperforms the stateof-the-art methods consistently.

show abstract

“…Aspect-based sentiment analysis (ABSA) (Yang et al, 2018), allowing multiple dimensions of sentiment on a message, gets us part-way to a solution. Multi-entity ABSA (ME-ABSA) (Tao and Fang, 2020) gets us further in this direction by classifying along multiple dimensions across entities, but these models are frequently expressed as classification problems (e.g., positive, neutral, and negative predictions), and we desire a finer-grained numerical approach.…”

Section: Introductionmentioning

confidence: 99%

Towards a Multi-Entity Aspect-Based Sentiment Analysis for Characterizing Directed Social Regard in Online Messaging

Joan¹,

Friedman²,

Schmer-galunder³

et al. 2022

Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)

View full text Add to dashboard Cite

Online messaging is dynamic, influential, and highly contextual, and a single post may contain contrasting sentiments towards multiple entities, such as dehumanizing one actor while empathizing with another in the same message. These complexities are important to capture for understanding the systematic abuse voiced within an online community, or for determining whether individuals are advocating for abuse, opposing abuse, or simply reporting abuse. In this work, we describe a formulation of directed social regard (DSR) as a problem of multi-entity aspect-based sentiment analysis (ME-ABSA), which models the degree of intensity of multiple sentiments that are associated with entities described by a text document. Our DSR schema is informed by Bandura's psychosocial theory of moral disengagement and by recent work in ABSA. We present a dataset of over 2,900 posts and sentences, comprising over 24,000 entities annotated for DSR over nine psychosocial dimensions by three annotators. We present a novel transformer-based ME-ABSA model for DSR, achieving favorable preliminary results on this dataset.

show abstract

Multi-Entity Aspect-Based Sentiment Analysis With Context, Entity and Aspect Memory

Cited by 25 publications

References 17 publications

Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches

Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches

BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis

Towards a Multi-Entity Aspect-Based Sentiment Analysis for Characterizing Directed Social Regard in Online Messaging

Contact Info

Product

Resources

About