Aspect-level Sentiment Analysis using AS-Capsules

Wang, Yequan; Sun, Aixin; Huang, Minlie; Zhu, Xiaoyan

doi:10.1145/3308558.3313750

Cited by 60 publications

(33 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In document level. Bollegala et al [40] proposed a method to perform cross-domain SA using a sentiment-sensitive thesaurus (SST). Blitzer et al [41] extended the structural correspondence learning (SCL).…”

Section: Sentiment Analysismentioning

confidence: 99%

Sentiment Analysis Technique and Neutrosophic Set Theory for Mining and Ranking Big Data From Online Reviews

2021

View full text Add to dashboard Cite

Recently, a huge amount of online consumer reviews (OCRs) is being generated through social media, web contents, and microblogs. This scale of big data cannot be handled by traditional methods. Sentiment analysis (SA) or opinion mining is emerging as a powerful and efficient tool in big data analytics and improving decision making. This research paper introduces a novel method that integrates neutrosophic set (NS) theory into the SA technique and multi-attribute decision making (MADM) to rank the different products based on numerous online reviews. The method consists of two parts: Determining sentiment scores of the online reviews based on the SA technique and ranking alternative products via NS theory. In the first part, the online reviews of the alternative products concerning multiple features are crawled and pre-processed. A neutral lexicon consists of 228 neutral words and phrases is compiled and the Valence Aware Dictionary and sEntiment Reasoner (VADER) for sentiment reasoning is adapted to handle the neutral data. The compiled neutral lexicon, as well as the adapted VADER, are utilized to build a novel adaptation called Neutro-VADER. The Neutro-VADER assigns positive, neutral, and negative sentiment scores to each review concerning the product feature. In this stage, the novel idea is to point out the positive, neutral, and negative sentiment scores as the truth, indeterminacy, and falsity memberships degrees of the neutrosophic number. The overall performance of each alternative concerning each feature based on a neutrosophic number is measured. In the second part, the ranking of alternatives is being evaluated through the simplified neutrosophic number weighted averaging (SNNWA) operator and cosine similarity measure methods. A case study with real datasets (Twitter datasets) is provided to illustrate the application of the proposed method. The results show good performance in handling the neutral data on the SA stage as well as the ranking stage. In the SA stage, findings show that the Neutro-VADER in the proposed method can deal successfully with all types of uncertainties including indeterminacy comparable with the traditional VADER in the other methods. In the ranking stage, the results show a great similarity and consistency while using other ranking methods such as PROMETHEE II, TOPSIS, and TODIM methods.

show abstract

Section: Sentiment Analysismentioning

confidence: 99%

Sentiment Analysis Technique and Neutrosophic Set Theory for Mining and Ranking Big Data From Online Reviews

2021

View full text Add to dashboard Cite

show abstract

“…In this study, we research only the second issue, which also consists of two main technical lines, namely, rule-based [59] and machine learningbased. The variants of recurrent neural networks (RNNs), such as long short-term memory (LSTM) [92], gated recurrent unit (GRU) [93], and the capsule network [94,95] have been widely used for aspect-level sentiment classification [96][97][98][99][100]. Tang et al [96] employed a forward LSTM and a backward LSTM to model the left and right contexts of the aspect separately and then concatenated the context representations for prediction of the sentiment polarity.…”

Section: Recent Researches On Aspect-level Sentiment Classificationmentioning

confidence: 99%

“…Yang et al [98] proposed a new approach with the guidance of contextual, lexical, and syntactic cues, in which a new target representation sub-network was used to capture the semantic and contextual information of targets and a new dependence attention mechanism was utilized to model the syntactic dependency cues between targets and other words. Wang et al [99] proposed the aspect-level sentiment capsules model (AS-Capsules), which utilized the correlation between aspect and sentiment to perform aspect detection and sentiment classification simultaneously, in a joint manner. Chen and Qian [100] proposed a Transfer Capsule Network (TransCap) model, which utilized an aspect routing approach and the dynamic routing approach to transfer document-level knowledge to aspect-level sentiment classification.…”

Section: Recent Researches On Aspect-level Sentiment Classificationmentioning

confidence: 99%

Interactive POS-aware network for aspect-level sentiment classification

Shuang

et al. 2021

Neurocomputing

View full text Add to dashboard Cite

Existing aspect-level sentiment-classification models completely rely on the learning from given datasets. However, these are easily misled by biased samples, resulting in learning some ill-suited rules that limit their potential. The information of some specific part-of-speech (POS) categories often indicates the word sentiment polarity, which can be introduced as prior knowledge to facilitate prediction of the model. Accordingly, we propose an interactive POS-aware network (IPAN) that explicitly introduces the POS information as reliable guidance to assist the model in accurately predicting sentiment polarity. We distinguish the information of different POS categories using a POS-filter gate and reinforce the features extracted from adjectives, adverbs, and verbs via a POS-highlighting attention mechanism. This enables the model to concentrate on the words that contain significant sentiment orientations and to obtain the most practical learning experience. To emphasize the target information, we construct a target-context gate that enables the interaction of the target information with contexts; consequently, the model considerably focuses on target-related sentiment features. The experiments on SemEval2014 and Twitter datasets verify that our IPAN consistently outperforms the current state-ofthe-art methods.

show abstract

“…Multi-task learning is widely used in natural language processing, such as jointly learning Chinese word segmentation and named entity recognition (Peng and Dredze 2017), jointly performing aspect detection and sentiment classification (Wang et al 2019), jointly extracting named entities and relation (Zheng et al 2017). Semantic role labeling model LISA (Strubell et al 2018) simultaneously learned dependency parsing and used a syntactically-informed selfattention mechanism to attend to each token's syntactic parse parent.…”

Section: Multi-task Learningmentioning

confidence: 99%

Leveraging Multi-Token Entities in Document-Level Named Entity Recognition

Dou

Nie

et al. 2020

AAAI

View full text Add to dashboard Cite

Most state-of-the-art named entity recognition systems are designed to process each sentence within a document independently. These systems are easy to confuse entity types when the context information in a sentence is not sufficient enough. To utilize the context information within the whole document, most document-level work let neural networks on their own to learn the relation across sentences, which is not intuitive enough for us humans. In this paper, we divide entities to multi-token entities that contain multiple tokens and single-token entities that are composed of a single token. We propose that the context information of multi-token entities should be more reliable in document-level NER for news articles. We design a fusion attention mechanism which not only learns the semantic relevance between occurrences of the same token, but also focuses more on occurrences belonging to multi-tokens entities. To identify multi-token entities, we design an auxiliary task namely ‘Multi-token Entity Classification’ and perform this task simultaneously with document-level NER. This auxiliary task is simplified from NER and doesn't require extra annotation. Experimental results on the CoNLL-2003 dataset and OntoNotesnbm dataset show that our model outperforms state-of-the-art sentence-level and document-level NER methods.

show abstract

Aspect-level Sentiment Analysis using AS-Capsules

Cited by 60 publications

References 24 publications

Sentiment Analysis Technique and Neutrosophic Set Theory for Mining and Ranking Big Data From Online Reviews

Sentiment Analysis Technique and Neutrosophic Set Theory for Mining and Ranking Big Data From Online Reviews

Interactive POS-aware network for aspect-level sentiment classification

Leveraging Multi-Token Entities in Document-Level Named Entity Recognition

Contact Info

Product

Resources

About