Search

User-generated content on various Internet platforms is growing explosively, and contains valuable information that helps decision-making. However, extracting this information accurately is still a challenge since there are massive amounts of data. Thereinto, sentiment analysis solves this problem by identifying people’s sentiments towards the opinion target. This article aims to provide an overview of deep learning for aspect-based sentiment analysis. Firstly, we give a brief introduction to the aspect-based sentiment analysis (ABSA) task. Then, we present the overall framework of the ABSA task from two different perspectives: significant subtasks and the task modeling process. Finally, challenges are proposed and summarized in the field of sentiment analysis, especially in the domain of aspect-based sentiment analysis. In addition, ABSA task also takes the relations between various objects into consideration, which is rarely discussed in the previous work.

Sentiment-controlled text generation aims to generate texts according to the given sentiment. However, most of the existing studies focus only on the document- or sentence-level sentiment control, leaving a gap for finer-grained control over the content of generated results. Fine-grained control allows a generated review to express different opinions toward multiple aspects. Some previous works attempted to generate reviews conditioned on aspect-level sentiments, but they usually suffer from low adaptability and the lack of an annotated dataset. To alleviate these problems, we propose a novel pre-trained extended generative model that can dynamically refer to the prompt sentiment, together with an auxiliary classifier that extracts the fine-grained sentiments from the unannotated sentences, thus we conducted training on both annotated and unannotated datasets. We also propose a query-hint mechanism to further guide the generation process toward the aspect-level sentiments at every time step. Experimental results from real-world datasets demonstrated that our model has excellent adaptability in generating aspect-level sentiment-controllable review texts with high sentiment coverage and stable quality since, on both datasets, our model steadily outperforms other baseline models in the metrics of BLEU-4, METETOR, and ROUGE-L etc. The limitation of this work is that we only focus on fine-grained sentiments that are explicitly expressed. Moreover, the implicitly expressed fine-grained sentiment-controllable text generation will be an important puzzle for future work.