This study presents a comparative evaluation of sentiment analysis models applied to a large corpus of expert wine reviews from Wine Spectator, with the goal of classifying reviews into binary sentiment categories based on expert ratings. We assess six models: logistic regression, XGBoost, LSTM, BERT, the interpretable Attention-based Multiple Instance Classification (AMIC) model, and the generative language model LLAMA 3.1, highlighting their differences in accuracy, interpretability, and computational efficiency. While LLAMA 3.1 achieves the highest accuracy, its marginal improvement over AMIC and BERT comes at a significantly higher computational cost. Notably, AMIC matches the performance of pretrained large language models while offering superior interpretability, making it particularly effective for domain-specific tasks such as wine sentiment analysis. Through qualitative analysis of sentiment-bearing words, we demonstrate AMIC’s ability to uncover nuanced, context-dependent language patterns unique to wine reviews. These findings challenge the assumption of generative models’ universal superiority and underscore the importance of aligning model selection with domain-specific requirements, especially in applications where transparency and linguistic nuance are critical.

This article analyzes questions of literary production and literary value in the Democratic People's Republic of Korea (DPRK) using quantitative methods and data sets covering a significant part of the country's literary and intellectual output over forty years (1977–2016). The first part of the article adopts a thematic approach, using topic modeling and time series, to map the DPRK's literary output and investigate the influence of genre on literary consecration. The second part looks at questions of style and literary quality in the DPRK through a comparative analysis of multiple novels grouped by degree of literary prestige. It introduces a method to evaluate the originality of an author's writing style using a masked language model (BERT) and uses it to assess the role of conformity and originality in the DPRK's literary field. Even though writers consecrated by the state display a high level of stylistic conformity when writing mandated biographies of the ruling family, their independent output ranks higher in originality than nonconsecrated writers.

A new framework for improving event detection is proposed that employs joint information in news media content and social networks, such as Twitter, to leverage detailed coverage of news media and the timeliness of social media. Specifically, a short text clustering method is employed to detect events from tweets, then the language model representations of the detected events are expanded using another set of events obtained from news articles published simultaneously. The expanded representations of events are employed as a new initialization of the clustering method to run another iteration and consequently enhance the event detection results. The proposed framework is evaluated using two datasets: a tweet dataset with event labels and a news dataset containing news articles published during the same time interval as the tweets. Experimental results show that the proposed framework improves the event detection results in terms of F1 measure compared to the results obtained from tweets only.