In this paper, we present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 31 fine-grained slots, such as the location of events, recent travel, and close contacts. We show that our corpus can support fine-tuning BERT-based classifiers to automatically extract publicly reported events and help track the spread of a new disease. We also demonstrate that, by aggregating events extracted from millions of tweets, we achieve surprisingly high precision when answering complex queries, such as "Which organizations have employees that tested positive in Philadelphia?" We will release our corpus (with user-information removed), automatic extraction models, and the corresponding knowledge base to the research community.

Purpose - To better understand the online reviews and help potential consumers, businessmen, and product manufacturers effectively obtain users' evaluation on product aspects, this paper explores the distribution regularities of user attention and sentiment toward product aspects from the temporal perspective of online reviews. Design/methodology/approach - Temporal characteristics of online reviews (purchase time, review time, and time intervals between purchase time and review time), similar attributes clustering, and attribute-level sentiment computing technologies are employed based on more than 340k smartphone reviews of three products from JD.COM (a famous online shopping platform in China) to explore the distribution regularities of user attention and sentiment toward product aspects in this article. Findings - The empirical results show that a power-law distribution can fit user attention to product aspects, and the reviews posted in short time intervals contain more product aspects. Besides, the results show that the values of user sentiment of product aspects are significantly higher/lower in short time intervals which contribute to judging the advantages and weaknesses of a product. Research limitations - The paper can't acquire online reviews for more products with temporal characteristics to verify the findings because of the restriction on reviews crawling by the shopping platforms. Originality/value -This work reveals the distribution regularities of user attention and sentiment toward product aspects, which is of great significance in assisting decision-making, optimizing review presentation, and improving the shopping experience.

[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize the attention mechanism in deep learning models. But these studies lack to explain the rationality of this approach. Whether the attention mechanism possesses this feature of human reading needs to be explored. [Design/methodology/approach] We conducted experiments on a sentiment classification task. Firstly, we obtained eye-tracking values from two open-source eye-tracking corpora to describe the feature of human reading. Then, the machine attention values of each sentence were learned from a sentiment classification model. Finally, a comparison was conducted to analyze machine attention values and eye-tracking values. [Findings] Through experiments, we found the attention mechanism can focus on important words, such as adjectives, adverbs, and sentiment words, which are valuable for judging the sentiment of sentences on the sentiment classification task. It possesses the feature of human reading, focusing on important words in sentences when reading. Due to the insufficient learning of the attention mechanism, some words are wrongly focused. The eye-tracking values can help the attention mechanism correct this error and improve the model performance. [Originality/value] Our research not only provides a reasonable explanation for the study of using eye-tracking values to optimize the attention mechanism, but also provides new inspiration for the interpretability of attention mechanism.

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task, which focuses on detecting the sentiment polarity towards the aspect in a sentence. However, it is always sensitive to the multi-aspect challenge, where features of multiple aspects in a sentence will affect each other. To mitigate this issue, we design a novel training framework, called Contrastive Cross-Channel Data Augmentation (C3 DA), which leverages an in-domain generator to construct more multi-aspect samples and then boosts the robustness of ABSA models via contrastive learning on these generated data. In practice, given a generative pretrained language model and some limited ABSA labeled data, we first employ some parameter-efficient approaches to perform the in-domain fine-tuning. Then, the obtained in-domain generator is used to generate the synthetic sentences from two channels, i.e., Aspect Augmentation Channel and Polarity Augmentation Channel, which generate the sentence condition on a given aspect and polarity respectively. Specifically, our C3 DA performs the sentence generation in a cross-channel manner to obtain more sentences, and proposes an Entropy-Minimization Filter to filter low-quality generated samples. Extensive experiments show that our C3 DA can outperform those baselines without any augmentations by about 1% on accuracy and Macro- F1. Code and data are released in https://github.com/wangbing1416/C3DA.

Sentiment analysis is a branch of Natural Language Processing (NLP) which goal is to assign sentiments or emotions to particular sentences or words. Performing this task is particularly useful for companies wishing to take into account customer feedback through chatbots or verbatim. This has been done extensively in the literature using various approaches, ranging from simple models to deep transformer neural networks. In this paper, we will tackle sentiment analysis in the Noisy Intermediate Scale Computing (NISQ) era, using the DisCoCat model of language. We will first present the basics of quantum computing and the DisCoCat model. This will enable us to define a general framework to perform NLP tasks on a quantum computer. We will then extend the two-class classification that was performed by Lorenz et al. (2021) to a four-class sentiment analysis experiment on a much larger dataset, showing the scalability of such a framework.

Document-level Sentiment Analysis (DSA) is more challenging due to vague semantic links and complicate sentiment information. Recent works have been devoted to leveraging text summarization and have achieved promising results. However, these summarization-based methods did not take full advantage of the summary including ignoring the inherent interactions between the summary and document. As a result, they limited the representation to express major points in the document, which is highly indicative of the key sentiment. In this paper, we study how to effectively generate a discriminative representation with explicit subject patterns and sentiment contexts for DSA. A Hierarchical Interaction Networks (HIN) is proposed to explore bidirectional interactions between the summary and document at multiple granularities and learn subject-oriented document representations for sentiment classification. Furthermore, we design a Sentiment-based Rethinking mechanism (SR) by refining the HIN with sentiment label information to learn a more sentiment-aware document representation. We extensively evaluate our proposed models on three public datasets. The experimental results consistently demonstrate the effectiveness of our proposed models and show that HIN-SR outperforms various state-of-the-art methods.

As aspect-level sentiment labels are expensive and labor-intensive to acquire, zero-shot aspect-level sentiment classification is proposed to learn classifiers applicable to new domains without using any annotated aspect-level data. In contrast, document-level sentiment data with ratings are more easily accessible. In this work, we achieve zero-shot aspect-level sentiment classification by only using document-level reviews. Our key intuition is that the sentiment representation of a document is composed of the sentiment representations of all the aspects of that document. Based on this, we propose the AF-DSC method to explicitly model such sentiment composition in reviews. AF-DSC first learns sentiment representations for all potential aspects and then aggregates aspect-level sentiments into a document-level one to perform document-level sentiment classification. In this way, we obtain the aspect-level sentiment classifier as the by-product of the document-level sentiment classifier. Experimental results on aspect-level sentiment classification benchmarks demonstrate the effectiveness of explicit utilization of sentiment composition in document-level sentiment classification. Our model with only 30k training data outperforms previous work utilizing millions of data.

The dataset has 25000 positive and negative reviews in the training set and 25000 positive and negative reviews in the test set. The image below shows the number of unique reviews and unique sentiment values in the dataset. The movie reviews are classified as having either a positive sentiment or a negative sentiment. The image below takes a peek at four reviews and their target sentiments. As can be seen from the keywords of the first three reviews – hooked, wonderful, unassuming, wonderful – lend the review a positive connotation.

Stopwords carry little semantic information and are often removed from text data to reduce dataset size and improve machine learning model performance. Consequently, researchers have sought to develop techniques for generating effective stopword sets. Previous approaches have ranged from qualitative techniques relying upon linguistic experts, to statistical approaches that extract word importance using correlations or frequency-dependent metrics computed on a corpus. We present a novel quantitative approach that employs iterative and recursive feature deletion algorithms to see which words can be deleted from a pre-trained transformer's vocabulary with the least degradation to its performance, specifically for the task of sentiment analysis. Empirically, stopword lists generated via this approach drastically reduce dataset size while negligibly impacting model performance, in one such example shrinking the corpus by 28.4% while improving the accuracy of a trained logistic regression model by 0.25%. In another instance, the corpus was shrunk by 63.7% with a 2.8% decrease in accuracy. These promising results indicate that our approach can generate highly effective stopword sets for specific NLP tasks.

Transformer-based models for transfer learning have the potential to achieve high prediction accuracies on text-based supervised learning tasks with relatively few training data instances. These models are thus likely to benefit social scientists that seek to have as accurate as possible text-based measures but only have limited resources for annotating training data. To enable social scientists to leverage these potential benefits for their research, this paper explains how these methods work, why they might be advantageous, and what their limitations are. Additionally, three Transformer-based models for transfer learning, BERT (Devlin et al. 2019), RoBERTa (Liu et al. 2019), and the Longformer (Beltagy et al. 2020), are compared to conventional machine learning algorithms on three applications. Across all evaluated tasks, textual styles, and training data set sizes, the conventional models are consistently outperformed by transfer learning with Transformers, thereby demonstrating the benefits these models can bring to text-based social science research.