The COVID-19 pandemic has implications beyond physical health, affecting society and economies. Government efforts to slow down the spread of the virus have had a severe impact on many businesses, including restaurants. Mandatory policies such as restaurant closures, bans on social gatherings, and social distancing restrictions have affected restaurant operations as well as customer preferences (e.g., prompting a demand of stricter hygiene standards). As of now, however, it is not clear how and to what extent the pandemic has affected restaurant reviews, an analysis of which could potentially inform policies for addressing this ongoing situation. In this work, we present our efforts to understand the effects of COVID-19 on restaurant reviews, with a focus on Yelp reviews produced during the pandemic for New York City and Los Angeles County restaurants. Overall, we make the following contributions. First, we assemble a dataset of 600 reviews with manual annotations of fine-grained COVID-19 aspects related to restaurants (e.g., hygiene practices, service changes, sympathy and support for local businesses). Second, we address COVID-19 aspect detection using supervised classifiers, weakly-supervised approaches based on keywords, and unsupervised topic modeling approaches, and experimentally show that classifiers based on pre-trained BERT representations achieve the best performance (F1=0.79). Third, we analyze the number and evolution of COVID-related aspects over time and show that the resulting time series have substantial correlation (Spearman's 𝜌=0.84) with critical statistics related to the COVID-19 pandemic, including the number of new COVID-19 cases. To our knowledge, this is the first work analyzing the effects of COVID-19 on Yelp restaurant reviews and could potentially inform policies by public health departments, for example, to cover resource utilization.
The state-of-the-art abusive language detection models report great in-corpus performance, but underperform when evaluated on abusive comments that differ from the training scenario. As human annotation involves substantial time and effort, models that can adapt to newly collected comments can prove to be useful. In this paper, we investigate the effectiveness of several Unsupervised Domain Adaptation (UDA) approaches for the task of cross-corpora abusive language detection. In comparison, we adapt a variant of the BERT model, trained on large-scale abusive comments, using Masked Language Model (MLM) fine-tuning. Our evaluation shows that the UDA approaches result in sub-optimal performance, while the MLM fine-tuning does better in the cross-corpora setting. Detailed analysis reveals the limitations of the UDA approaches and emphasizes the need to build efficient adaptation methods for this task.
The use of attention mechanisms in deep learning approaches has become popular in natural language processing due to its outstanding performance. The use of these mechanisms allows one managing the importance of the elements of a sequence in accordance to their context, however, this importance has been observed independently between the pairs of elements of a sequence (self-attention) and between the application domain of a sequence (contextual attention), leading to the loss of relevant information and limiting the representation of the sequences. To tackle these particular issues we propose the self-contextualized attention mechanism, which trades off the previous limitations, by considering the internal and contextual relationships between the elements of a sequence. The proposed mechanism was evaluated in four standard collections for the abusive language identification task achieving encouraging results. It outperformed the current attention mechanisms and showed a competitive performance with respect to state-of-the-art approaches.
As hate speech spreads on social media and online communities, research continues to work on its automatic detection. Recently, recognition performance has been increasing thanks to advances in deep learning and the integration of user features. This work investigates the effects that such features can have on a detection model. Unlike previous research, we show that simple performance comparison does not expose the full impact of including contextual- and user information. By leveraging explainability techniques, we show (1) that user features play a role in the model’s decision and (2) how they affect the feature space learned by the model. Besides revealing that—and also illustrating why—user features are the reason for performance gains, we show how such techniques can be combined to better understand the model and to detect unintended bias.
Lab studies in cognition and the psychology of morality have proposed some thematic and linguistic factors that influence moral reasoning. This paper assesses how well the findings of these studies generalize to a large corpus of over 22,000 descriptions of fraught situations posted to a dedicated forum. At this social-media site, users judge whether or not an author is in the wrong with respect to the event that the author described. We find that, consistent with lab studies, there are statistically significant differences in uses of first-person passive voice, as well as first-person agents and patients, between descriptions of situations that receive different blame judgments. These features also aid performance in the task of predicting the eventual collective verdicts.
