GERestaurant: A German Dataset of Annotated Restaurant Reviews for Aspect-Based Sentiment Analysis

TL;DR

GERestaurant presents a German-language ABSA dataset of 3,078 Tripadvisor restaurant reviews with sentence-level annotations for explicit and implicit aspects, their categories, and sentiment polarities. It aligns with SemEval-style guidelines and provides strong transformer-based baselines for ACD, ACSA, E2E-ABSA, and TASD, enabling cross-lingual ABSA research and German-language resource development. The dataset enables detailed analyses of aspect distributions, annotation practices, and language-specific ABSA behavior, and it offers a foundation for future expansion into finer-grained attributes and cross-language transfer. Overall, GERestaurant fills a critical gap in German ABSA resources and demonstrates competitive baseline performance while highlighting practical considerations for dataset construction and evaluation.

Abstract

We present GERestaurant, a novel dataset consisting of 3,078 German language restaurant reviews manually annotated for Aspect-Based Sentiment Analysis (ABSA). All reviews were collected from Tripadvisor, covering a diverse selection of restaurants, including regional and international cuisine with various culinary styles. The annotations encompass both implicit and explicit aspects, including all aspect terms, their corresponding aspect categories, and the sentiments expressed towards them. Furthermore, we provide baseline scores for the four ABSA tasks Aspect Category Detection, Aspect Category Sentiment Analysis, End-to-End ABSA and Target Aspect Sentiment Detection as a reference point for future advances. The dataset fills a gap in German language resources and facilitates exploration of ABSA in the restaurant domain.