Replication Data for: Revisiting Weimar Film Reviewers’ Sentiments: Integrating Lexicon-Based Sentiment Analysis with Large Language Models

This dataset contains one excel table (corpus_reviews.xlsx) related to 80 historical film reviews of three Weimar films: "Das Cabinet des Dr. Caligari" (1920), "Nosferatu" (1922) and "Metropolis" (1927). The table also includes metadata related to the origin of the reviews and their full text in their original languages and in English translation. Furthermore, it contains the results of a range of methods for sentiment analysis of the reviews, including manual judgments and different approaches to automated sentiment analysis. The python code used to implement these is included. We first undertake a verbose sentiment analysis of the reviews by running the same prompt over each review through the OpeanAI API (GPT_API_all_reviews.ipynb). A less successful attempt, showing the results of the same prompt using the open source HuggingChat is also included (huggingChat_API_reviews.ipynb). We then apply a lexicon-based sentiment analysis (with Python’s NLTK library and its VADER lexicon) to the result of ChatGPT’s analysis and to the reviews directly (sentiment_analysis.ipynb). We then compare the results (results_analysis.ipynb).