With the advent of many movie content platforms, users face a flood of content and consequent difficulties in selecting appropriate movie titles. Although much research has been conducted in developing effective recommender systems to provide personalized recommendations based on customers’ past preferences and behaviors, not much attention has been paid to leveraging users’ sentiments and emotions together. In this study, we built a new graph-based movie recommender system that utilized sentiment and emotion information along with user ratings, and evaluated its performance in comparison to well known conventional models and state-of-the-art graph-based models. The sentiment and emotion information were extracted using fine-tuned BERT. We used a Kaggle dataset created by crawling movies’ meta-data and review data from the Rotten Tomatoes website and Amazon product data. The study results show that the proposed IGMC-based models coupled with emotion and sentiment are superior over the compared models. The findings highlight the significance of using sentiment and emotion information in relation to movie recommendation.

Accident and fatality rates of traffic accidents worldwide are steadily increasing every year; thus, considerable effort has been made to prevent traffic accidents and prepare countermeasures. This study aims to identify the major factors and types that affect the severity of traffic accidents in Seoul by utilizing the Seoul Metropolitan Government’s traffic accident dataset. To achieve this, we perform a comprehensive analysis by adopting various machine learning techniques—not only supervised learning methods but also unsupervised learning methods. As a result of the experiment, we derived several critical factors that were found to affect the severity of traffic accidents via supervised learning methods (i.e., ensemble-based and regression-based algorithms) and discovered dominant accident types via unsupervised learning methods (i.e., clustering-based algorithms). One of our primary findings is that, in contrast to common sense, environmental factors such as weather, season, and day of the week do not significantly affect the severity of traffic accidents in Seoul. Moreover, all methods highlight the importance of pedestrian-related factors, implying that it is highly necessary to prepare more meticulous institutional measures for pedestrians to reduce the negative influence of serious traffic accidents in Seoul.

Clinicians have minimal time to search for and absorb the information needed while performing the duties of their medical practice. Their time-pressured situations requires the relevant information in search to be retrieved and presented in a more succinct form, such as in a short passage, rather than a whole page or document. In this context, clinical decision support (CDS) searches are beneficial when used to retrieve critical medical passages that can assist the practice of medical experts by offering appropriate medical information relevant to the medical case at hand. We present a novel CDS search framework designed for passage retrieval in order to support clinical decision-making using laboratory test results by incorporating proximity information. To do so, we use a knowledge structure that graphically visualizes key concepts and the corresponding relationships in a specific domain where nodes denote with their associative relationships. Furthermore, unlike previous studies that exploit knowledge structures during a re-ranking step, only dealing with initially highly retrieved passages, we utilize a knowledge structure for the purpose of query expansion. By doing so, our approach can unveil passages that are not retrieved during the initial retrieval process by including latent terms in the query list. We compared two models with/without edge pruning to capture a more latent relationship between terms. Our experiment showed that the embedded-based knowledge structure outperformed previous knowledge structure building approaches and other proximity-aware state-of-the-art models.

Tipping, which has evolved beyond its original role as a gesture of appreciation, has become a complex social issue that often causes friction between customers and service workers. Existing technological approaches, instead of clarifying the ambiguity in evaluation criteria, merely provide predefined tipping options that fail to improve customer satisfaction. Such practices lead to “tip fatigue” and foster a sense of coercion regardless of service quality, thereby intensifying social tension. This issue arises from the lack of objective and transparent standards for evaluating service value. To address these limitations, this paper proposes TipMate, an explainable fair tip recommender system based on Large Language Models (LLMs) that holistically evaluates service quality and transparently explains its reasoning. TipMate conducts evaluations grounded in the established service quality theory by systematically integrating (1) visual evidence from the service environment, (2) subjective textual feedback from customers, and (3) contextual data from publicly available reviews. To validate the system’s reasoning capabilities, we constructed OpenR-Tip, a benchmark dataset derived from real-world narratives with synthesized contexts. Experimental results using four state-of-the-art LLMs show that TipMate closely approximates human tipping judgments with a Mean Absolute Error (MAE) of 4.26%, achieving a high average satisfaction score of 4.43/5 in a user study.