TikTok content by Spanish political parties during the 2024 European elections

This dataset includes all posts published on TikTok by the main Spanish political parties during the 2024 European Parliament election campaign (n=114). The dataset includes the four parties with the largest representation in the Spanish Parliament (Congress of Deputies): the center-right People's Party (PP), the center-left Spanish Socialist Workers' Party (PSOE), the far-right Vox, and the left-wing Sumar. The variables included in the dataset are: user name, url, video description, hashtag names, comment count, like count, share count, transcription (voice to text), create date, text, sentiment, sentiment threshold, score, prob_negative, prob_neutral, prob_positive, and engagement.The Python programming language was used for data collection, cleaning, and analysis. Posts were collected through TikTok’s Academic API.Both the video description and the audio transcript of each video were manually reviewed to prevent potential errors in subsequent analyses. After this review, the variables were standardized. Emojis, tags, links, and punctuation marks were removed from each text. Additionally, a list of irrelevant words—including articles, determiners, prepositions, and adverbs—was then created for the analysis. The list combined the output of the “get_stop_word” function from the “stop_words” library with that of the “stopwords” function from NLTK. Subsequently, all text was converted to lowercase, and tokenized. The data is offered in two files (.xlsx and .cvs)