Aspect-based Sentiment Analysis for German: Analyzing “Talk of Literature” Surrounding Literary Prizes on Social Media
Since the rise of social media, the authority of traditional professional literary critics has been supplemented – or undermined, depending on the point of view – by technological developments and the emergence of community-driven online layperson literary criticism. So far, relatively little research (Allington 2016, Kellermann et al. 2016, Kellermann and Mehling 2017, Bogaert 2017, Pianzola et al. 2020) has examined this layperson user-generated evaluative “talk of literature” instead of addressing traditional forms of consecration. In this paper, we examine the layperson literary criticism pertaining to a prominent German-language literary award: the Ingeborg-Bachmann-Preis, awarded during the Tage der deutschsprachigen Literatur (TDDL). We propose an aspect-based sentiment analysis (ABSA) approach to discern the evaluative criteria used to differentiate between ‘good’ and ‘bad’ literature. To this end, we collected a corpus of German social media reviews, retrieved from Twitter, and enriched it with manual ABSA annotations: aspects and aspect categories (e.g. the motifs or themes in a text, the jury discussions and evaluations, ...), sentiment expressions and named entities. In a next step, the manual annotations are used as training data for our ABSA pipeline including 1) aspect term category prediction and 2) aspect term polarity classification. Each pipeline component is developed using state-of-the-art pre-trained BERT models. Two sets of experiments were conducted for the aspect polarity detection: one where only the aspect embeddings were used and another where an additional context window of five adjoining words in either direction of the aspect was considered. We present the classification results for the aspect category and aspect sentiment prediction subtasks for the Twitter corpus. These preliminary experimental results show a good performance for the aspect category classification, with a macro and a weighted F1-score of 69% and 83% for the course-grained and 54% and 73% for the fine-grained task, as well as for the aspect sentiment classification subtask, using an additional context window, with a macro and a weighted F1-score of 70% and 71%, respectively.