Aspect-based sentiment analysis with graph convolution over syntactic dependencies

Žunić, Anastazia; Corcoran, Padraig; Spasić, Irena

doi:10.1016/j.artmed.2021.102138

Cited by 18 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we investigate the application of BERT to aspect-based SA of drug reviews. We also relate the results to the ones achieved in our previous study, which was based on graph convolution over the dependency graph [8].…”

Section: Related Workmentioning

confidence: 77%

“…The aspect's relations to other words represent important features of its sentiment, but are not taken into account in RNN-based approaches. In our previous work, a graph convolutional network (GCN) designed to operate on syntactic dependencies outperformed the traditional RNN approach by a large margin on the task of aspect-based SA of drug reviews [8]. A GCN approach may not be able to capture the features of longdistance dependence, thus struggling to effectively represent the aspect's context.…”

Section: Related Workmentioning

confidence: 99%

“…To train the model and evaluate its performance, we used a dataset we created specifically for the task of aspect-based SA. It was described in detail in a previous study, which proposed deep learning over the syntactic dependency graph using graph convolution [8].…”

Section: Datamentioning

confidence: 99%

“…Neural networks cannot only learn complex relationships between individual words in a sentence but can also utilise more complex sentence representations, such as graphs, which can be based on syntactic parses. For example, convolution can be successively applied to an aspect of SA by traversing through its syntactic dependencies [8]. More recently, language models that are pre-trained using transformer architectures [9] have demonstrated significant improvements over recurrent neural networks in a variety of NLP tasks, including natural language understanding, named entity recognition and question answering [10].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Case of Aspect in Sentiment Analysis: Seeking Attention or Co-Dependency?

Žunić

Corcoran

Spasić

2022

MAKE

Self Cite

View full text Add to dashboard Cite

(1) Background: Aspect-based sentiment analysis (SA) is a natural language processing task, the aim of which is to classify the sentiment associated with a specific aspect of a written text. The performance of SA methods applied to texts related to health and well-being lags behind that of other domains. (2) Methods: In this study, we present an approach to aspect-based SA of drug reviews. Specifically, we analysed signs and symptoms, which were extracted automatically using the Unified Medical Language System. This information was then passed onto the BERT language model, which was extended by two layers to fine-tune the model for aspect-based SA. The interpretability of the model was analysed using an axiomatic attribution method. We performed a correlation analysis between the attribution scores and syntactic dependencies. (3) Results: Our fine-tuned model achieved accuracy of approximately 95% on a well-balanced test set. It outperformed our previous approach, which used syntactic information to guide the operation of a neural network and achieved an accuracy of approximately 82%. (4) Conclusions: We demonstrated that a BERT-based model of SA overcomes the negative bias associated with health-related aspects and closes the performance gap against the state-of-the-art in other domains.

show abstract

Section: Related Workmentioning

confidence: 77%

Section: Related Workmentioning

confidence: 99%

Section: Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Case of Aspect in Sentiment Analysis: Seeking Attention or Co-Dependency?

Žunić

Corcoran

Spasić

2022

MAKE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Alsayat [ 22 ] employed word-embedding technology to develop the LSTM network, which has high classification accuracy and can understand new, unusual words. Uni et al [ 23 ] used an aspect-based emotion analysis model to achieve automatic emotion categorization, which is superior to typical deep learning architecture. Garcia-ordas et al [ 24 ] suggested an emotion analysis algorithm that can handle any length of audio to realize audio data emotion analysis in real time.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Evaluation of Psychological Tolerance under the Haze: A Case Study of Typical Provinces and Cities in China with Severe Haze

Rui

Gemechu

et al. 2022

IJERPH

View full text Add to dashboard Cite

The interplay of specific weather conditions and human activity results due to haze. When the haze arrives, individuals will use microblogs to communicate their concerns and feelings. It will be easier for municipal administrators to alter public communication and resource allocation under the haze if we can master the emotions of netizens. Psychological tolerance is the ability to cope with and adjust to psychological stress and unpleasant emotions brought on by adversity, and it can guide human conduct to some extent. Although haze has a significant impact on human health, environment, transportation, and other factors, its impact on human mental health is concealed, indirect, and frequently underestimated. In this study, psychological tolerance was developed as a psychological impact evaluation index to quantify the impact of haze on human mental health. To begin, data from microblogs in China’s significantly haze-affected districts were collected from 2013 to 2019. The emotion score was then calculated using SnowNLP, and the subject index was calculated using the co-word network approach, both of which were used as social media evaluation indicators. Finally, utilizing ecological and socioeconomic factors, psychological tolerance was assessed at the provincial and prefecture level. The findings suggest that psychological tolerance differs greatly between areas. Psychological tolerance has a spatio-temporal trajectory in the timeseries as well. The findings offer a fresh viewpoint on haze’s mental effects.

show abstract