@inproceedings{sidarenka-stede-2016-generating,
    title = "Generating Sentiment Lexicons for {G}erman {T}witter",
    author = "Sidarenka, Uladzimir  and
      Stede, Manfred",
    editor = "Nissim, Malvina  and
      Patti, Viviana  and
      Plank, Barbara",
    booktitle = "Proceedings of the Workshop on Computational Modeling of People`s Opinions, Personality, and Emotions in Social Media ({PEOPLES})",
    month = dec,
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W16-4309/",
    pages = "80--90",
    abstract = "Despite a substantial progress made in developing new sentiment lexicon generation (SLG) methods for English, the task of transferring these approaches to other languages and domains in a sound way still remains open. In this paper, we contribute to the solution of this problem by systematically comparing semi-automatic translations of common English polarity lists with the results of the original automatic SLG algorithms, which were applied directly to German data. We evaluate these lexicons on a corpus of 7,992 manually annotated tweets. In addition to that, we also collate the results of dictionary- and corpus-based SLG methods in order to find out which of these paradigms is better suited for the inherently noisy domain of social media. Our experiments show that semi-automatic translations notably outperform automatic systems (reaching a macro-averaged F1-score of 0.589), and that dictionary-based techniques produce much better polarity lists as compared to corpus-based approaches (whose best F1-scores run up to 0.479 and 0.419 respectively) even for the non-standard Twitter genre."
}