Data and code for project "What makes users click: the effect of news values negativity and surprise in news headlines on the CTR"

This repository includes the following files and corresponding Python codes saved in Jupiter Notebooks: <strong>upworthy-archive-confirmatory-packages-03.12.2020.csv:</strong> Original dataset downloaded from The Upworthy Research Archive (https://osf.io/jd64p/) <strong>cleaned_data.csv</strong>: <strong>upworthy-archive-confirmatory-packages-03.12.2020.csv</strong> cleaned with <strong>notebook_clean_data.ipynb</strong> Data sorted by <em>clickability_test_id</em> Headlines with 0 clicks deleted Variables <em>ctr</em>, <em>mean_ctr</em>, and <em>lift</em> created Only kept first occurrence of headlines that occur multiple times in the dataset per test Deleted tests with only one headline <strong>sample_manual_annotations.csv</strong>: sample of 300 headlines of <strong>cleaned_data.csv </strong>retrieved with <strong>notebook_sample_manual_annotations.ipynb</strong> <strong>inter-annotator_sentiment.csv</strong>: input for <strong>notebook_inter-annotator_scores_confusion_matrix.ipynb</strong> to calculate inter-annotator agreement scores with regard to annotating sentiment <strong>inter-annotator_emotion.csv</strong>: input for <strong>notebook_inter-annotator_scores_confusion_matrix.ipynb</strong> to calculate inter-annotator agreement scores with regard to annotating emotion <strong>input_sentiment.tsv</strong>: input for <strong>notebook_sentiment_emotion_test_set.ipynb </strong>for sentiment analysis on sample of 300 headlines in <strong>sample_manual_annotations.csv</strong> <strong>input_emotion.tsv</strong>: input for <strong>notebook_sentiment_emotion_test_set.ipynb </strong>for emotion analysis on sample of 300 headlines in <strong>sample_manual_annotations.csv</strong> <strong>input_all_headlines.tsv</strong>: input for <strong>notebook_sentiment_emotion_final_annotation.ipynb</strong> to annotate all headlines in <strong>cleaned_data.csv</strong>